Monday
Room
Seattle 1 & 2
Seattle 3
Emerald 2
09:00-10:30
Making Space Suits
Click here for more about this keynote.
10:30-11:00
Break
11:00-12:30
Activity and Group Interactions
Hide Tokuda
Group Activity Recognition using Belief Propagation for Mobile Devices
Humans are social beings and spend most of their time in groups. Group behavior is emergent, generated by members’ personal characteristics and their interactions. It is therefore difficult to recognize in peer-to-peer (P2P) systems where the emergent behavior itself cannot be directly observed. We introduce 2 novel algorithms for distributed probabilistic inference (DPI) of group activities using loopy belief propagation (LBP). We evaluate their performance using an experiment in which 10 individuals play 6 team sports and show that these activities are emergent in nature through natural processes. Centralized recognition performs very well, upwards of an F-score of 0.95 for large window sizes. The distributed methods iteratively converge to solutions which are comparable to centralized methods. DPI-LBP also reduces energy consumption by a factor of 7 to 40, where a centralized unit or infrastructure is not required.
StudentLife: Assessing Mental Health, Academic Performance and Behavioral Trends of College Students using Smartphones
Much of the stress and strain of student life remains hidden. The StudentLife continuous sensing app assesses the day-today and week-by-week impact of workload on stress, sleep, activity, mood, sociability, mental well-being and academic performance of a single class of 48 students across a 10 week term at Dartmouth College using Android phones. Results from the StudentLife study show a number of significant correlations between the automatic objective sensor data from smartphones and mental health and educational outcomes of the student body. We also identify a Dartmouth term lifecycle in the data that shows students start the term with high positive affect and conversation levels, low stress, and healthy sleep and daily activity patterns. As the term progresses and the workload increases, stress appreciably rises while positive affect, sleep, conversation and activity drops off. The StudentLife dataset is publicly available on the web.
Accommodating User Diversity for In-Store Shopping Behavior Recognition
This paper explores the possibility of using mobile sensing data to detect certain in-store shopping intentions or behaviours of shoppers. We propose a person-independent activity recognition technique called CROSDAC, which captures the diversity in the manifestation of such intentions or behaviours in a heterogeneous set of users in a data-driven manner via a 2-stage clustering-cum-classification technique. Using smartphone based sensor data (accelerometer, compass and Wi-Fi) from a directed, but real-life study involving 86 shopping episodes from 30 users in a mall’s food court, we show that CROSDAC’s mobile sensing-based approach can offer reasonably high accuracy (77:6% for a 2-class identification problem) and outperforms the traditional community driven approaches that unquestioningly segment users on the basis of underlying demographic or lifestyle attributes.
Detecting Smoothness of Pedestrian Flows by Participatory Sensing with Mobile Phones
In this paper, we propose a novel system for estimating crowd density and smoothness of pedestrian flows in public space by participatory sensing with mobile phones. By analyzing walking motion of the pedestrians and ambient sound in the environment that can be monitored by accelerometers and microphones in off-the-shelf smartphones, our system classifies the current situation at each area into four categories that well represent the crowd behavior. Through field experiments using Android smartphones, we show that our system can recognize the current situation with accuracy of 60-78%.
High5: Promoting Interpersonal Hand-to-Hand Touch for Vibrant Workplace with Electrodermal Sensor Watches
Interpersonal touch is our most primitive social language strongly governing our emotional well-being. Despite the positive implications of touch in many facets of our daily social interactions, we find wide-spread caution and taboo limiting touch-based interactions in workplace relationships that constitute a significant part of our daily social life. In this paper, we explore new opportunities for ubicomp technology to promote a new meme of casual and cheerful interpersonal touch such as high-fives towards facilitating vibrant workplace culture. Specifically, we propose High5, a mobile service with a smartwatch-style system to promote high-fives in everyday workplace interactions. We first present initial user motivation from semi-structured interviews regarding the potentially controversial idea of High5. We then present our smartwatch-style prototype to detect high-fives based on sensing electric skin potential levels. We demonstrate its key technical observation and performance evaluation.
Mobile Performance
David Chu
SatScore: Uncovering and Avoiding a Principled Pitfall in Responsiveness Measurements of App Launches
BatteryExtender: An Adaptive User-Guided Tool for Power Management of Mobile Devices
The battery life of mobile devices is one of their most important resources. Much of the literature focuses on accurately profiling the power consumption of device components or enabling application developers to develop energy-efficient applications through fine-grained power profiling. However,there is a lack of tools to enable users to extend battery life on demand. What can users do if they need their device to last for a specific duration in order to perform a specific task? To this extent, we developed BatteryExtender, a user-guided power management tool that enables the reconfiguration of the device’s resources based on the workload requirement, similar to the principle of creating virtual machines in the cloud. It predicts the battery life savings based on the new configuration, in addition to predicting the impact of running applications on the battery life. Through our experimental analysis, BatteryExtender decreased the energy consumption between 10.03% and 20.21%, and in rare cases by up to 72.83%. The accuracy rate ranged between 92.37% and 99.72%.
Powerlet: An Active Battery Interface for Smartphones
Mobile Video Ad Caching on Smartphones
It is clear today that mobile video is a major traffic source and that online advertising is a steadily growing business. These trends are leading towards mobile video advertising becoming ubiquitous. We make two contributions towards better understanding mobile video ads and how their impact on mobile device resources can be minimized. We perform the first characterization of a well-defined set of mobile video ads on YouTube, the largest online video service. We then use our findings to design a video ad caching system for smartphones, aiming at minimizing the number of ad downloads to relieve mobile devices from the extra overhead induced by the ever increasing amount of ads. Our trace-driven simulations show that our caching system can save up to 50% data transfer.
UbiComp and Design
Gregory Abowd
CAMY: Applying a Pet Dog Analogy to Everyday Ubicomp Products
Ubicomp products have become more important in providing emotional experiences as users increasingly assimilate these products into their everyday lives. In this paper, we explored a new design perspective by applying a pet dog analogy to support emotional experience with ubicomp products. We were inspired by pet dogs, which are already intimate companions to humans and serve essential emotional functions in daily live. Our studies involved four phases. First, through our literature review, we articulated the key characteristics of pet dogs that apply to ubicomp products. Secondly, we applied these characteristics to a design case, CAMY, a mixed media PC peripheral with a camera. Like a pet dog, it interacts emotionally with a user. Thirdly, we conducted a user study with CAMY, which showed the effects of pet-like characteristics on users’ emotional experiences, specifically on intimacy, sympathy, and delightedness. Finally, we presented other design cases and discussed the implications of utilizing a pet dog analogy to advance ubicomp systems for improved user experiences.
Identity Crisis of Ubicomp? Mapping 15 Years of the Field's Development and Paradigm Change
The rapid growth of the Ubicomp field has recently raised concerns regarding its identity. These concerns have been compounded by the fact that there exists a lack of empirical evidence on how the field has evolved until today. In this study we applied co-word analysis to examine the status of Ubicomp research. We constructed the intellectual map of the field as reflected by 6858 keywords extracted from 1636 papers published in the HUC, UbiComp and Pervasive conferences during 1999-2013. Based on the results of a correspondence analysis we identify two major periods in the whole corpus: 1999-2007 and 2008-2013. We then examine the evolution of the field by applying graph theory and social network analysis methods to each period. We found that Ubicomp is increasingly focusing on mobile devices, and has in fact become more cohesive in the past 15 years. Our findings refute the assertion that Ubicomp research is now suffering an identity crisis.
The 4C Framework: Principles of Interaction in Digital Ecosystems
Recent years have seen an increased research interest in multi-device interactions and digital ecosystems. This research addresses new opportunities and challenges when users are not simply interacting with one system or device at a time, but orchestrate ensembles of them as a larger whole. One of these challenges is to understand what principles of interaction work well for what, and to create such knowledge in a form that can inform design. Our contribution to this research is a framework of interaction principles for digital ecosystems, which can be used to analyze and understand existing systems and design new ones. The 4C framework provides new insights over existing frameworks and theory by focusing specifically on explaining the interactions taking place within digital ecosystems. We demonstrate this value through two examples of the framework in use, firstly for understanding an existing digital ecosystem, and secondly for generating ideas and discussion when designing a new one.
Creative Collaboration With a Social Robot
This research builds on the UbiComp vision of systems that do not do things for people but engage people in their computational environment so that people can do things for themselves better. In this investigation, we sought to make good on a proof-of-concept where people interact with a social robot whereby the robot helps people to be more humanly creative. Twenty seven participants interacted with ATR’s humanoid robot Robovie (through a WoZ interface) in a creativity task. Results supported our proof of concept insofar as 100% of the participants generated creative ideas, and 63% incorporated the robot’s ideas into their own ideas for their creative output. Of the participants who had the highest creativity scores, 83% incorporated the robot’s ideas into their own. Discussion focuses on next steps toward building the Natural Language Processing system, and integrating the system into a more extensive networked UbiComp environment.
12:30-14:00
Lunch
14:00-15:30
In the Home
Shwetak Patel
From Today's Augmented Houses to Tomorrow's Smart Homes: New Directions for Home Automation Research
A considerable amount of research has been carried out towards making long-standing smart home visions technically feasible. The technologically augmented homes made possible by this work are starting to become reality, but thus far living in and interacting with such homes has introduced significant complexity while offering limited benefit. As these technologies are increasingly adopted, the knowledge we gain from their use suggests a need to revisit the opportunities and challenges they pose. Synthesizing a broad body of research on smart homes with observations of industry and experiences from our own empirical work, we provide a discussion of ongoing and emerging challenges, namely challenges for meaningful technologies, complex domestic spaces, and human-home collaboration. Within each of these three challenges we discuss our visions for future smart homes and identify promising directions for the field.
UbiComp for Animal Welfare: Envisioning Smart Environments for Kenneled Dogs
Whilst the ubicomp community has successfully embraced a number of societal challenges for human benefit, including healthcare and sustainability, the well-being of other animals is hitherto underrepresented. We argue that ubicomp technologies, including sensing and monitoring devices as well as tangible and embodied interfaces, could make a valuable contribution to animal welfare. This paper particularly focuses on dogs in kenneled accommodation, as we investigate the opportunities and challenges for a smart kennel aiming to foster canine welfare. We conducted an in-depth ethnographic study of a dog rehoming center over four months; based on our findings, we propose a welfare-centered framework for designing smart environments, integrating monitoring and interaction with information management. We discuss the methodological issues we encountered during the research and propose a smart ethnographic approach for similar projects.
Intruders Versus Intrusiveness: Teens' and Parents' Perspectives on Home-Entryway Surveillance
We investigated how household deployment of Internet-connected locks and security cameras could impact teenagers' privacy. In interviews with 13 teenagers and 11 parents, we investigated reactions to audit logs of family members' comings and goings. All parents wanted audit logs with photographs, whereas most teenagers preferred text-only logs or no logs at all. We unpack these attitudes by examining participants' parenting philosophies, concerns, and current monitoring practices. In a follow-up online study, 19 parents configured an Internet-connected lock and camera system they thought might be deployed in their home. All 19 participants chose to monitor their children either through unrestricted access to logs or through real-time notifications of access. We discuss directions for auditing interfaces that could improve home security without impacting privacy.
Monitoring Household Activities and User Location with a Cheap, Unobtrusive Thermal Sensor Array
We demonstrate that a cheap (30USD) small, low power 8x8 thermal sensor array can by itself provide a broad range of information relevant for human activity monitoring in home and office environments. In particular the sensor can track people with an accuracy in the range of 1m (which is sufficient to recognize activity relevant regions), detect the operation mode of various appliances such as toaster, water cooker or egg cooker and actions such as opening a refrigerator, the oven or taking a shower. While there are sensing modalities for each of the above types of information (e.g. current sensors for appliances) the fact that they can all be detected by such a simple sensor is highly relevant for practical activity recognition systems. Compared to vision (or thermal imaging systems) the system has the advantage is being less privacy invasive allowing it for example to monitor bathroom activities (as shown in one of our evaluation scenarios). The paper describes the sensor, the methods used for activity detection and the evaluation.
Exploring Interactive Furniture with EmotoCouch
People respond emotionally to other people, animals, or even objects like furniture. While current furniture is static in appearance, embedded electronics can enable furniture to change its appearance. A couch could show excitement during a party or anger when a pet scratches it. But would emotional furniture delight or annoy people? To explore the potential for emotional furniture, we built EmotoCouch. Through colored light, visual patterns, and haptic feedback, EmotoCouch expresses six emotional states: Excited, Happy, Calm, Depressed/Sad, Afraid, and Angry. This video describes the construction of EmotoCouch, feedback gathered through surveys and user interviews, and shows example EmotoCouch usage situations.
Contextual Awareness on Mobile Devices
Daniel Ashbrook
Group Affiliation Detection Using Model Divergence for Wearable Devices
Methods for recognizing group affiliations using mobile devices have been proposed using centralized instances to aggregate and evaluate data. However centralized systems do not scale well and fail when the network is congested. We present a method for distributed, peer-to-peer (P2P) recognition of group affiliations in multi-group environments, using the divergence of mobile phone sensor data distributions as an indicator of similarity. The method assesses pairwise similarity between individuals using model parameters instead of sensor observations, and then interprets that information in a distributed manner. An experiment was conducted with 10 individuals in different group configurations to compare P2P and conventional centralized approaches. Although the output of the proposed method fluctuates, we can still correctly detect 93% of group affiliations by applying a filter. We foresee applications in mobile social networking, life logging, smart environments, crowd situations and possibly crowd emergencies.
Public Restroom Detection on Mobile Phone via Active Probing
Although there are clear benefits to automatic image capture services by wearable devices, image capture sometimes happens in sensitive spaces where camera use is not appropriate. In this paper, we tackle this problem by focusing on detecting when the user of a wearable device is located in a specific type of private space—the public restroom—so that the image capture can be disabled. We present an infrastructure-independent method that uses just the microphone and the speaker on a commodity mobile phone. Our method actively probes the environment by playing a 0.1 seconds sine wave sweep sound and then analyzes the impulse response (IR) by extracting MFCCs features. These features are then used to train an SVM model. Our evaluation results show that we can train a general restroom model which is able to recognize new restrooms. We demonstrate that this approach works on different phone hardware. Furthermore, the volume levels, occupancy and presence of other sounds do not affect recognition in significant ways. We discuss three types of errors that the prediction model has and evaluate two proposed smoothing algorithms for improving recognition.
Exploiting Usage Statistics for Energy-efficient Logical Status Inference on Mobile Phones
Logical statuses of mobile users, such as isBusy and isAlone, are the key enabler for a plethora of context-aware mobile applications. While on-board hardware sensors, such as motion, proximity, and location sensors, have been extensively studied for logical status inference, the continuous usage incurs formidable energy consumption and therefore user experience degradation. In this paper, we argue that smartphone usage statistics can be used for logical status inference with negligible energy cost. To validate this argument, this paper presents a continuous inference engine that (1) intercepts multiple operating system events, in particular foreground app, notifications, screen states, and connected networks; (2) extracts informative features from OS events; and (3) efficiently infers the logical status of mobile users. The proposed inference engine is implemented for unmodified Android phones, and an evaluation on a four-week trial has shown promising accuracy in identifying four logical statuses of mobile users with over 87% accuracy while the average energy impact on the battery life is less than 0.5%.
How much light do you get? Estimating daily light exposure using smartphones
We present an approach to estimate a persons light exposure using smartphones. We used web-sourced weather reports combined with smartphone light sensor data, time of day, and indoor/outdoor information, to estimate illuminance around the user throughout a day. Since light dominates every human’s circadian rhythm and influences the sleep-wake cycle, we developed a smartphone-based system that does not require additional sensors for illuminance estimation. To evaluate our approach, we conducted a free-living study with 12 users, each carrying a smartphone, a head-mounted light reference sensor, and a wrist-worn light sensing device for six consecutive days. Estimated light values were compared to the head-mounted reference, the wrist-worn device and a mean value estimate. Our results show that illuminance could be estimated at less than 20% error for all study participants, outperforming the wrist-worn device. In 9 out of 12 participants the estimation deviated less than 10% from the reference measurements.
Indoor Location
Jin Nakazawa
Graph-based Data Fusion of Pedometer and WiFi Measurements for Mobile Indoor Positioning
We propose a graph-based, low-complexity sensor fusion approach for ubiquitous pedestrian indoor positioning using mobile devices. We employ our fusion technique to combine relative motion information based on step detection with WiFi signal strength measurements. The method is based on the well-known particle filter methodology. In contrast to previous work, we provide a probabilistic model for location estimation that is formulated directly on a fully discretized, graph-based representation of the indoor environment. We generate this graph by adaptive quantization of the indoor space, removing irrelevant degrees of freedom from the estimation problem. We evaluate the proposed method in two realistic indoor environments using real data collected from smartphones. In total, our dataset spans about 20 kilometers in distance walked and includes 13 users and four different mobile device types. Our results demonstrate that the filter requires an order of magnitude less particles than state-of-the-art approaches while maintaining an accuracy of a few meters. The proposed low-complexity solution not only enables indoor positioning on less powerful mobile devices, but also saves much-needed resources for location-based end-user applications which run on top of a localization service.
MobileRF: A Robust Device-Free Tracking System Based on a Hybrid Neural Network HMM Classifier
We present a device-free indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person’s movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to accurately perform tracking. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90% region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.
Introducing Indoor-ALP: An Adaptive Indoor Location Prediction System
Location prediction enables us to use a person’s mobility history to realize various applications such as efficient temperature control, opportunistic meeting support, and automated receptionists. Indoor location prediction is a challenging problem, particularly due to a high density of possible locations and short transition distances between these locations. In this paper we present Indoor-ALPS, an Adaptive Indoor Location Prediction System that uses temporal-spatial features to create individual daily models for the prediction of when a user will leave their current location (transition time) and the next location she will transition to. We tested Indoor-ALPS on the Augsburg Indoor Location Tracking Benchmark and compared our approach to the best performing temporal-spatial mobility prediction algorithm, Prediction by Partial Match (PPM). Our results show that Indoor-ALPS improves the temporal- spatial prediction accuracy over PPM for look-aheads up to 90 minutes by 6.2%, and for up to 30 minute look-aheads by 10.7%. These results demonstrate that Indoor-ALPS can be used to support a wide variety of indoor mobility prediction-based applications.
LoCo: A Ready-to-Deploy Framework for Efficient Room Localization using Wi-Fi
In recent years, there has been an explosion of social and collaborative applications that leverage location to provide users novel and engaging experiences. Current location technologies work well outdoors but fare poorly indoors. In this paper we present LoCo, a new framework that can provide highly accurate room-level location using a supervised classification scheme. We provide experiments that show this technique is orders of magnitude more efficient than current state-of-the-art WiFi localization techniques. Low classification overhead and computational footprint make classification practical and efficient even on mobile devices. Our framework has also been designed to be easily deployed and leveraged by developers to help create a new wave of location driven applications and services.
15:30-16:00
Break
16:00-17:30
Cities & Transportation
Tanzeem Choudhury
Sensing WiFi Packets in the Air: Practicality and Implications in Urban Mobility Monitoring
Mobile sensing systems employ various sensors in smartphones to extract human-related information. As the demand for sensing systems increases, a more effective mechanism is required to sense information about human life. In this paper, we present a systematic study on the feasibility and gaining properties of a crowdsensing system that primarily concerns sensing WiFi packets in the air. We propose that this method is effective for estimating urban mobility by using only a small number of participants. During a seven-week deployment, we collected smartphone sensor data, including approximately four million WiFi packets from more than 130,000 unique devices in a city. Our analysis of this dataset examines core issues in urban mobility monitoring, including feasibility, spatio-temporal coverage, scalability, and threats to privacy. Collectively, our findings provide valuable insights to guide the development of new mobile sensing systems for urban life monitoring.
Assessing the Potential of Ride-Sharing Using Mobile and Social Data -- A Tale of Four Cities
This paper assesses the potential of ride-sharing for reducing traffic in a city -- based on mobility data extracted from 3G Call Description Records (CDRs), for the cities of Madrid and Barcelona (BCN), and from OSNs, such as Twitter and Foursquare (FSQ), collected for the cities of New York (NY) and Los Angeles (LA). First, we analyze these data sets to understand mobility patterns, home and work locations, and social ties between users. Then, we develop an efficient algorithm for matching users with similar mobility patterns, considering a range of constraints, including social distance. The solution provides an upper bound to the potential decrease in the number of cars in a city that can be achieved by ridesharing. Our results indicate that this decrease can be as high as 31%, when users are willing to ride with friends of friends.
CitySpectrum: A Non-negative Tensor Factorization Approach
People flow at a citywide level is in a mixed state with several basic patterns (e.g. commuting, working, commercial), and it is therefore difficult to extract useful information from such a mixture of patterns directly. In this paper, we proposed a novel tensor factorization approach to modeling city dynamics in a basic life pattern space (CitySpectral Space). To obtain the CitySpectrum, we utilized Non-negative Tensor Factorization (NTF) to decompose a people flow tensor into basic life pattern tensors, described by three bases i.e. the intensity variation among different regions, the time-of-day and the sample days. We apply our approach to a big mobile phone GPS log dataset (containing 1.6 million users) to model the fluctuation in people flow before and after the Great East Japan Earthquake from a CitySpectral perspective. In addition, our framework is extensible to a variety of auxiliary spatial-temporal data. We parametrize a people flow with a spatial distribution of the Points of Interest (POIs) to quantitatively analyze the relationship between human mobility and POI distribution. Based on the parametric people flow, we propose a spectral approach for a site-selection recommendation and people flow simulation in another similar area using POI distribution.
Classifying the Mode of Transportation on Mobile Phones using GIS Information
Determining the mode of transport of an individual is an important element of contextual information. In particular, we focus on differentiating between different forms of motorized transport such as car, bus, subway etc. Our approach uses location information and features derived from transit route information (schedule information, not real-time) published by transit agencies. This enables no up-front training or learning of routes and can be deployed instantly to a new place since most transit agencies publish this information. Combined with motion detection using phone accelerometers, we obtain a classification accuracy of around 90% on 50+ hours of car and transit data.
Sensing and Communication
Yoshihiro Kawahara
Capacitive Near-Field Communication for Ubiquitous Interaction and Perception
Smart objects within instrumented environments offer an always available and intuitive way of interacting with a system. Connecting these objects to other objects in range, or even to smartphones and computers, enables substantially innovative interaction and sensing approaches. In this paper, we investigate the concept of Capacitive Near-Field Communication to enable ubiquitous interaction with everyday objects in a short-range spatial context. Our central contribution is a generic framework describing and evaluating the communication method in Ubiquitous Computing. We prove the relevance of our approach by an open-source implementation of a low-cost object tag and a transceiver offering a high-quality communication link at typical distances up to 15 cm. Moreover, we present three case studies considering tangible interaction for the visually impaired, natural interaction with everyday objects, and sleeping behavior analysis.
MaLoc: A Practical Magnetic Fingerprinting Approach to Indoor Localization using Smartphones
Using magnetic field data as fingerprints for localization in indoor environment has become popular in recent years. Particle filter is often used to improve accuracy. However, most of existing particle filter based approaches either are heavily affected by motion estimation errors, which makes the system unreliable, or impose strong restrictions on smartphone such as fixed phone orientation, which is not practical for real-life use. In this paper, we present an indoor localization system named MaLoc, built on our proposed augmented particle filter. We create several innovations on the motion model, the measurement model and the resampling model to enhance the traditional particle filter. To minimize errors in motion estimation and improve the robustness of particle filter, we augment the particle filter with a dynamic step length estimation algorithm and a heuristic particle resampling algorithm. We use a hybrid measurement model which combines a new magnetic fingerprinting model and the existing magnitude fingerprinting model to improve the system performance and avoid calibrating different smartphone magnetometers. In addition, we present a novel localization quality estimation method and a localization failure detection method to address the "Kidnapped Robot Problem" and improve the overall usability. Our experimental studies show that MaLoc achieves a localization accuracy of 1~2.8m on average in a large building.
A Battery-free Object Localization and Motion Sensing Platform
Indoor object localization can enable many ubicomp applications, such as asset tracking and object-related activity recognition. Most location and tracking systems rely on either battery-powered devices which create cost and maintenance issues or cameras which have accuracy and privacy issues. This paper introduces a system that is able to detect the 3D position and motion of a battery-free RFID tag embedded with an ultrasound detector and an accelerometer. Combining tags' acceleration with location improves the system's power management and supports activity recognition. We characterize the system's localization performance in open space as well as implement it in a smart wet lab application. The system is used to track real-time location and motion of the tags in the wet lab as well as recognize pouring actions performed on the objects to which the tag is attached. The median localization accuracy is $7.6cm$ -- $(3.1,5,1.9)cm$ for each $(x,y,z)$ axis -- with max update rates of 15 Sample/s using single RFID reader antenna.
Pulse: Low Bitrate Wireless Magnetic Communication for Smartphones
Gadget Show
Tom Martin
17:30-19:30
ISWC:Demos & Posters
SHE: Smart Home Energy Management System for Appliance Identification and Personalized Scheduling
The home appliance scheduling is a promising energy saving technique that has significant commercial potential. In this demo, Smart Home Energy Management System (SHE) is developed on Android platform to schedule users’ appliances. SHE monitors the power consumption to identify the operations of home appliances using a privacy preserving technique called Non-Intrusion Load Monitoring (NILM). The operations are integrated with dynamic electric price and environment data to mine users’ personal demand and preference on appliance operation. Finally, SHE generates personalized scheduling strategies to meet the different users’ demands at the minimal cost.
RFID-Die: Battery-free Orientation Sensing Using an Array of Passive Tilt Switches
We demonstrate the combination of tilt switches with RFID for building fully passive orientation-sensitive devices. We show the functionality of this approach with a simple die that can be read out with an NFC-enabled smartphone. As the proposed orientation system does not require battery powering, it is of interest to various wearable-computing and smart-home applications that benefit from long system runtime.
Squeeze the Moment: Denoting Diary Events by Squeezing
In this demonstration, we showcase SqueezeDiary, a novel mobile diary application that uses squeeze gestures for denoting instances of events. SqueezeDiary consists of a mobile phone and a small squeeze sensor that communicate over a Bluetooth connection. To record an event instance, the user simply squeezes the sensor, and the phone records memory cues for review later. SqueezeDiary provides features for users to swiftly record instances as they continue to live through the experience, and only reflect on the instances during their downtime.
Physics Education with Google Glass gPhysics Experiment App
We present a fully functional application prototype gPhysics App \ based on the Google Glass platform which is designed to \ perform an educational physical experiment in the area of acoustics. \ The initial applications aims towards students whose task is to find the \ relationship between the frequency of the sound generated \ by hitting a water glass and the amount of water.
Memo-it: Don't write your diary, Sense it
The profusion of sensors embedded in modern mobile devices collect an increasing amount of information about the activities performed by a user. Leveraging the episodic memory model defined by neuroscientists, Memo-it exploits this information to create a multi-scale structured representation of the user's activities in a semi-automated fashion, while preserving the privacy of the user's data. In addition to building a digital diary of the user, the semantic approach taken by Memo-it is able to answer multi-dimensional queries, and to enable the inter-operability of memories between users.
MiniOrb: A Sensor Interaction Platform for Indoor Climate Preferences
MiniOrb is a combined sensor and interaction platform built to understand and encourage the gathering of data around personal indoor climate preferences in office environments. It consists of a sensor device, gathering localised environmental data and an attached tangible interaction and ambient display device. This device allows users to understand their local environment and record office comfort preferences. In addition to the tangible interaction device we built a web-based mobile application that allowed users to record comfort preferences through a different interface. We describe the design goals and technical setup of the MiniOrb platform.
Multi-device Activity Logging
In this paper we are presenting i-Log, a system able to collect user's personal information, generate streams of data from smartphone's integrated sensors and attached wearable devices. We decided to focus our attention on these general purpose devices as we believe they can generate truthful readings because of their easy integration with our day-life activities, while invasive dedicated logging devices can alter our normal routines. The system consists of a Mobile Application that collects data from the smartphone and additional wearables. We designed it to be user friendly, unobtrusive and able to provide smart sensing strategies to preserve battery life.
Stereoscopic 3D Mobile Maps for Indoor Navigation in Multi-Level Buildings
We present our research demonstrator where autostereoscopic 3D (S3D) display equipped mobile devices, enabling the perception of depth, are used to provide a user interface (UI) for indoor navigation. The design approach suits especially for aiding navigation within multi-level buildings, such as shopping malls, airports and museums. Compared to the current 2D design approach of displaying building floor levels side-by-side, the use of stereoscopic 3D offers potential to improve understanding of the space, glanceability of map based UIs, and the ability to navigate between locations on different floor levels.
Collaborative Geometry-Aware Augmented Reality
Augmented reality (AR) has progressed to the point where geometry-aware real-time applications involving multiple users are now possible. We present an approach for a collaborative augmented reality environment using an RGB-D camera and KinectFusion, collecting visual and depth data from a static environment that is used as a fiducial for multiple users. This allows for collaborative augmented reality environments where digital data and real world objects can appear to interact.
HoppingDuster : Self-adaptive Cleaning Robot based on Aerial Vehicle
In this demo, we show a new concept of cleaning robot, called HoppingDuster. \ HoppingDuster is based on an aerial vehicle, which can fly to stairs or furnitures to be cleaned, \ and hop or hover to wipe or blow down dust on them toward the floor so that \ the ground cleaning robot can vacuum the dust.
Networked On-Line Audio Dilation
Audio Dilation is a technique that slows down the tempo of audio signals without changing the pitch or otherwise distorting the sounds. Networked On-line Audio Dilation is an Android application that allows users to dilate audio while engaged in a full-duplex networked conversation. The capability can potentially be used to improve comprehension for hearing or cognitively impaired individuals, or for non-native speakers of foreign languages.
Hunting Relics: A Collaborative Exergame on an Interactive Floor for Children
Exergames on interactive floors are appropriate to promote exercise and socialization in ludic environments. However, they lack of mechanisms to help children of early age to develop age-appropriate motor skills. In this paper, we present the design and development of an exergame to promote the collaborative exercising in young children (4-6 years old) using interactive floors. Also we take advantage of the socialization aspects catalyzed by interactive floors to promote collaboration among potential users. We close discussing design considerations, we argue an interactive floor exergame should incorporate to appropriately promote exercise and collaboration in young children.
A Noise Map of New York City
The Moment
The Moment is a mobile application for people with depression or bipolar disorder to monitor their emotional ups and downs, reveal their emotional patterns, and eventually find a peaceful way to live with their emotions, rather than fighting with them. The goal is to make the user more aware of her mood swings and the precursors to them; to reveal patterns of the swings; to provide a record for healthcare providers; to build a library of personalized interventions for future use; and to create an effective network of social supports.
Drone, Your Brain, Ring Course – Accept the Challenge and Prevail!
Brain Computer Interface systems (BCIs) rely on lengthy training phases that can last up to months due to the inherent variability in brainwave activity between users. We propose a BCI architecture based on the co-learning between the user and the system through different feedback strategies. We apply our system to the piloting of an AR.Drone 2.0 quadricopter with a series of hoops delimiting an exciting circuit. We show that our architecture provides better task performance than traditional BCI paradigms within a shorter time frame. We further demonstrate the enthusiasm of users towards our BCI-based interaction modality.
Supporting Walking School Buses
Walking School Buses (WSBs) typically feature a coordinator who is assigned to walk a designated route, calling at several pick-up points that parents can use to join their children to the ``bus''. Parents often feel limited by the rigidity of the scheduled walking bus arrival so they choose instead to rely on car journeys to the school. In this work we demonstrate a mobile system that allows parents to visualise real-time predictions of walking bus arrival times and thus supports more flexible travel coordination behaviours, providing greater opportunities for parents to utilise walking bus services and reduce car usage.
Shiny -- An Activity Logging Platform for Google Glass
We describe an activity logging platform for Google Glass based on our previous work. \ We introduce new multi-modal methods for quick non-disturbing interactions \ for activity logging control and real time ground truth labeling, consisting \ of swipe gesture, head gesture and laser pointer tagging methods. \ The methods are evaluated in user studies towards estimating their effectiveness. \
Expression: A Dyadic Conversation Aid using Google Glass for People with Visual Impairments
Limited access to non-verbal cues hinders the dyadic conversation or social interaction of people who are blind or visually impaired. This paper presents Expression — an integrated assistive solution using Google Glass. The key function of the system is to enable the user to perceive social signals during a natural face-to-face conversation. Empirical evaluation of the system is presented with qualitative (Likert score: 4.383/5) and quantitative results (overall F-measure of the nonverbal expression recognition: 0.768).
ColPhone: A Smartphone is just a piece of the puzzle
Multiple smartphone coexistence has been a fact of life. However, each smartphone is though of as a single unit. We believe that cooperation between coexisting smartphones can provide users with a cheap hardware upgrade (e.g processing). In addition to sharing of sensing information that can be collected by only one phone saving others energy of redundant tasks (e.g. GPS readings). In this work, we propose COLlaboration smartPHONE (colPhone) a framework that manages the collaboration between smarphones. ColPhone aims to achieve mutual benefit for collaborators by utilizing idle resources on smartphone in the proximity.
An Immersive Fire Training System Using Kinect
We presents a simulation training system to help children learn fire hazards knowledge and escape skills. The first part of this system is an application designed for theoretical study, which is featured by gesture interaction using Microsoft Kinect and large screen display environment. It includes three modules, namely animation, quizzes, and a 3D serious game. The second part is a simulated environment of fire escape route, which aims to test learning outcomes. Experimental results show the fire escape skills of 100 children are greatly improved.
Bring Your Own Device: Ubiquitous approach to digital affinity diagram collaboration
We propose a system where groups can participate in onsite brainstorming using various form-factor devices: tablet, laptop, or desktop for collaboration. We utilize socket server technology to achieve a high level of synchronization for all individual actions during brainstorming. Our system uses a method called affinity diagramming in which users illustrate, group and link their ideas to create an easily understood structure. Using ubiquitous devices - both mobile and stationary - in brainstorming can help teams work together to share resources, exchange and organize ideas to build solutions that enhance our lives.
Memory Specs–An Annotation System on Google Glass using Document Image Retrieval
We present a system working on a wearable computer that can annotate and retrieve annotations for signs, posters, public displays etc. We evaluate our system in a poster session scenario with 5 use cases: \ retrieving annotations, adding notes, taking pictures and recording audio and attaching them to posters.
When Your Sensor Earns Money: Exchanging Data for Cash with Bitcoin
Bitcoin is an emerging technology which allows two entities to \ exchange value overt the Internet without trust. Embracing that those entities \ could well be machines we present a system that allows a sensor to offer its \ measurement data directly to a world-wide data market. Thus, we describe a prototypical \ implementation of the process of exchanging data for electronic cash between a sensor \ and a requester by leveraging the Bitcoin network and discuss its current limitations.
A Tangible Approach to Time Management
Information work generally occurs within a multi-tasking environment with attention focused on the computer screen, constant task switching and frequent interruptions. In this environment, software-based task management techniques may blend in too much to be optimally effective. The Time Machine is proposed as a physical interface distinctly separated from the task environment with real-world manifestations of arbitrary concepts of tasks and time, while providing constant visibility of status through an ambient display for self-reflection. The Time Machine aims to promote distributed cognition and utilize the stage-based model of personal informatics and the Pomodoro technique toward productive and enjoyable task management.
Smarter Eyewear– Using Commercial EOG Glasses for Activity Recognition
In this paper we present a first evaluation of soon commercially available \ Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. \ We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses.
Contents-Aware Gesture Interaction Using Wearable Motion Sensor
Motion-based hand gesture recognition using a wearable motion sensor equipped on the wrist-band helps decreasing recognition errors compared with that of video-based recognition systems. However, the user interaction is often interrupted even in the low-error conditions because an inappropriate gesture recognition mode is applied on the system or user can’t find out how to handle it using gestures. We propose a novel gesture interaction technique using visual attention to suggest user an appropriate gesture on the condition of selectable contents on the screen. We applied this interaction method on the content navigation interface for the TV.
Including Affect-Driven Adaptation to the Pac-Man Video Game
Building affect-driven adaptive environments is a task geared toward creating environments able to change based on the affective state of a target user. In our project, the environment is the well-known game, Pac-Man. To provide affect-driven adaptive capabilities, diverse sensors were utilized to gather a user’s physiological data and an emotion recognition framework was used to fuse the sensed data and infer affective states. The game changes driven by those affective states aim to improve the user experience by keeping or increasing player’s engagement.
Negative Energy Detector using Cellphone Bluetooth and Contact list
We present a novel metric to measure people's capacity to make their encounters negative. Then Latent Dirichlet Allocation topic model and multimodal exposure features(MME) are used to study the behavior differences, extracting the probable contact patterns of different kinds of people and how they contact with each other. Finally, to make practical, a MME Feed-forward Neural Network is given out to judge people's role in emotion contamination, with using people's own mobile-phones contact list. Taking the MIT Social Evolution dataset as an example, the experimental results verify the efficacy of our techniques on real-world data.
FlierMeet: Cross-Space Public Information Reposting with Mobile Crowd Sensing
Bulletin boards serve an important function for public information sharing. Posted fliers advertise services, events and other announcements. However, fliers posted offline suffer from problems such as limited spatial-temporal coverage and inefficient search aid. In recent years, with the development of sensor-enhanced mobile devices, mobile crowd sensing has been used in a variety of application areas. In this paper we present FlierMeet, a crowd-powered sensing system for cross-space public information reposting, tagging and sharing. The tags are auto-labeled based on a set of visual and crowd-object interaction features. Initial deployments and experiments prove the effectiveness of our system.
Towards Automated Thermal Profiling of Buildings at Scale Using Unmanned Aerial Vehicles and 3D-Reconstruction
With increases in energy demand and problems due to climate change, governments are increasingly focused on building efficiency. To help inform these improvements, energy audits are often performed with thermal cameras; however, the data collection process is labor intensive and does not offer a comprehensive view of the buildings. We introduce our vision for a new, more scalable approach: automated 3D thermal profiling of buildings using unmanned aerial vehicles (UAV) and 3D-reconstruction. To demonstrate feasibility, we used an unmodified Parrot AR.Drone 2.0 and a FLIR thermal camera to collect RGB and thermal images of a building and generate 3D reconstructions.
Programming Tool of Context-Aware Applications for Behavior Change
We have been developing a toolkit that provides hardware and software for users who have no programming experience to easily invent and test context-aware applications that can help them make changes in their behaviors. We have found that this toolkit needs to balance simplicity of interaction with the facilitation of a wide range of user experiences. To address this issue, we identified key temporal rule patterns from a user-generated collection of behavior change applications, and created programming elements with which users can compose applications of those patterns.
Holes, Pits, and Valleys: Guiding Large-Display Touchless Interactions with Data-Morphed Topographies
Large displays enable efficient visualization of large datasets. To interact with these large datasets, touchless interfaces can support fluid interaction at different distances from the display. Touchless gestures, however, lack haptic feedback. Hence, users’ gestures may unintentionally move off the interface elements and require additional physical effort to perform intended actions. To address this problem, we propose data-morphed topographies for touchless interactions: constraints on users’ cursor movements that guide touchless interaction along the structure of the visualized data. We envision applying three data-morphed topographies—holes, pits, and valleys—to common problem-solving tasks in visual analytics.
Wearable Sensors in Ecological Rehabilitation Environments
Rehabilitation after injury or stroke is a long process towards regaining function, mobility, and independence. Changes exhibited tend to be subtle and highly dependent on the patient, their injury, and the intensity of rehabilitation efforts. To provide a fine-grained assessment of patient progress, motion was captured during inpatient rehabilitation therapy. We utilized wearable inertial sensors to collect data from participants at an inpatient rehabilitation facility. Performance was recorded in an ecological environment on a sequence of ambulatory tasks. Sensor signals were processed to compute metrics describing ambulation. A comparison of metrics one week apart suggests quantifiable changes in movement.
MugShots: Everyday Objects as Social Catalysts
We explore how everyday objects can serve as social catalysts to increase social interaction in the workplace. As an initial exploration, we created MugShots, a coffee mug with a wireless OLED display. Users can wirelessly transmit images onto the mug, revealing different self- identities though an everyday object, in turn triggering interest and conversation with others. We present a prototype of MugShots along with a 10 person pilot study to gauge the feasibility of this idea.
SAP Dissimilarity based High Performance Wi-Fi Indoor Localization
To handle the fluctuation of wireless signal and the unstability of Access Point (AP), we discover some underlying characteristics of Wi-Fi indoor localization from the view of signal strength and AP based on massive observations. Therefore, a new dissimilaritybased localization method SAP (Signal-AP) is proposed to implement high performance indoor localization. The performance of SAP shows that SAP not only improves the localization accuracy, but also shows desirable scalability of environment.
Extreme mediation: Observing mental and physical health in everyday life
The excessive use of smartphones resulting in extreme mediation has been identified to result in psychological problems including anxiety, depression, and an overall neural change that is impacting people of all ages on many levels. An exploratory study using Experience Sampling Method (ESM) concluded a significant increase in positive mood, conscious awareness of the surrounding environment, and an increased number of participants self-reporting physical activity lasting 15 minutes on days without smartphone use. Results suggest the need to avoid increased use of non-invasive technology such as smartphones resulting in deterioration of mental and physical health.
Detecting Traffic Congestions Using Cell Phone Accelerometers
In this paper, we propose a system that detects traffic congestions by using a single cell phone accelerometer. The proposed system comprises a vehicular movement detection module, and a module for likelihood estimation of traffic congestions. Experimental results based on real datasets have demonstrated the effectiveness of the proposed system.
My Data Store: Toward User Awareness and Control on Personal Data
Smartphones and their capability of collecting personal and contextual information have tremendously increased data production. The availability of such data represents an opportunity for organizations and individuals to enable new application scenarios. However, it has also increased the public concern on data privacy. We present My Data Store, a tool enabling people to control and share their personal data. We tested it with 63 participants that used it to manage their own data collected from mobile phones and through experience sampling applications. Preliminary results show improvement over the users’ awareness of their personal data and the tool's perceived usefulness.
Plex: Finger-Worn Textile Sensor for Mobile Interaction during Activities
Plex is a finger-worn textile sensor for eyes-free mobile interaction during daily activities. Usually an interaction with fingers couples bending and pressing. In Plex, we separate bending and pressing by placing each sensing element in discrete faces of a finger. Our proposed simple and low-cost fabrication process using conductive elastomers and threads transforms an elastic fabric into a finger-worn interaction tool. Plex preserves an inter-finger natural tactile feedback and proprioception. We also explore the interaction design and implement applications \
Wearable Computing for Older Adults – Initial Insights into Head-Mounted Display Usage
In this paper we present an explorative, qualitative study with three older adults that used a wearable computer with a head mounted display during everyday activities. We derive requirements from the usage of existing applications, describe emerging usage patterns, highlight promising applications, and the reaction of the public.
Yet Another Approach for Food Recognition: Monitoring Power Leakage from Microwave Oven
We demonstrate a food recognition method by monitoring power leakage from a domestic microwave oven. Universal Software Radio Peripheral (USRP) is applied as a low-cost spectrum analyzer to measure the microwave oven leakage as received signal strength indication (RSSI). By analyzing 184 features designed after analyzing measured RSSI of 18 categories of food , we attain an average recognition accuracy of 82.3% with various distances between the microwave oven and the USRP and different data downsampling frequencies for raw data processing. \
Logmusic : Context-Based Social Music Recommendation Service on Mobile Device
Our choice of music in a daily life is greatly affected by our current mood and suggestions by others. We believe that people experience similar mood changes facing similar changes in weather, temperature, time, and location, and for this we suggest a service we named ‘Logmusic’, a context-based social music recommendation service. This service is expected to enhance user’s music experience and promote sense of unity among users, and contribute to build unique cultures within local communities.
Living with the User: Design Drama for Dementia Care through Responsive Scripted Experiences in the Home
Participation in forms of drama and narrative can provoke empathy and creativity in user-centred design processes. Here we explore the potential for responsive scripted experiences, delivered through the combination of sensors and output devices in a home. The approach is being developed in the context of Dementia care, where the capacity for rich user participation is limited. A system can act as a proxy for a person with Dementia, allowing designers to gain insight as to what it is like to care for and live with this person. We describe the rationale, a prototype system architecture, potential uses and challenges.
Locator: A Self-adaptive Framework for the Recognition of Relevant Places
A high number of algorithms for the recognition of users’ relevant places exist. However, none of them provide an optimal solution across all users and scenarios. We present a preliminary design of Locator – a self-adaptive framework for recognizing users’ relevant places. Locator learns for different contextual situations, combinations of algorithms and sensors that achieve the best performance in recognizing relevant places. We conducted a 5-weeks study and collected sensor and ground-truth data from 6 users. Our preliminary results indicate the shortcomings of relying on one algorithm and sensor for recognizing places and thus motivates the rational behind our approach.
Future Directions for Providing Better IoT Infrastructure
Internet of Things (IoT) supports a connection between objects and humans, enabling the ubiquitous computing in our daily lives. Future research directions in IoT infrastructure should consider real-time communication and scalability to provide a better experience to the users. We justify this sentence by developing an IoT micro-benchmark, which was evaluated over a real IoT middleware. Considering the observed gaps, this article describes the ideas on redesigning the IoT infrastructure, not imposing any modifications in the users’ source code. The modeling combines cloud virtualization and elasticity, service decomposition and multithreading programming.
Evaluating the Use of Ambient and Tangible Interaction Approaches for Personal Indoor Climate Preferences
We describe the preliminary results of a field study which evaluated the use of MiniOrb, a system that employs ambient and tangible interaction mechanisms to allow inhabitants of office environments to report on subjectively perceived office comfort levels. The purpose of this study was to explore the role of ubiquitous computing in the individual control of indoor climate and specifically answer the question to what extent ambient and tangible interaction mechanisms are suited for the task of capturing individual comfort preferences in a non-obtrusive manner.
3D FDM–PAM: Rapid and Precise Indoor 3D Localization using Acoustic Signal for Smartphone
In this paper, we present an indoor 3D positioning method for smartphones using acoustic signals. In our proposed 3D Frequency Division Multiplexing-Phase Accordance Method (3D FDM-PAM), four speakers simultaneously emit burst signals comprising two carrier waves at different frequencies to enable the rapid calculation of the position of the smartphone. Through experiments, we show that 3D FDM-PAM can achieve a standard deviation of less than 2.8 cm at 7.8 measurements per second. The worst positioning error was 48.3 cm at the 95th percentile. We investigate the causes of error and discuss potential improvements to the localization performance.
The Myth of Subtle Notifications
Push notifications keep user informed and engaged with the events around the mobile applications. However not all the notifications are of the same importance level to the user. We explore how mobile notifications are regarded as increasing number of applications are adopting notification services. We logged notification management traces from 10 individuals for 15 days to understand how they perceived mobile notifications and their importance, accompanying our results with semi-structured interviews.
Crowdsensing Traces Using Bluetooth Low Energy (BLE) Proximity Tags
Designing massive scale crowdsensing experiments using smartphones can be very challenging. In this work, we define a new approach for designing massive crowdsensing applications by offloading sensing from smartphones to low cost off-the-shelf Bluetooth Low Energy (BLE) proximity tags. We discuss the usage of advertisements in BLE tags as a new energy-efficient sensing resource for massive scale crowd mobility trace collection.
LifeDelivery : Recruiting Participants to Deliver Users’ Daily Goods!
Based on crowdsourcing, systems applied in large area and based on vehicle-mounted movement mode are developed to deliver people’s packages through crowd. In contrast, we focus on system used in little communities, which is capable of delivering people’s daily goods in campus. Due to the different demands and behavior features of students, they give others help just to make friends but not for money. Based on this difference, we presented LifeDelivery, a crowdsourcing service able to use Friends Mechanism and Cloud Perception Technology to recruit participants to deliver daily goods. And this will bring convenience to users and help students.
Designing a Mobile System for Public Safety Using Open Crime Data and Crowdsourcing
We explore ways to improve public safety by using open crime data and crowdsourcing. We first conducted an online survey to better understand the public safety needs of the Syracuse University (SU) community. We then developed an Android app in collaboration with the Department of Public Safety (DPS) at SU; the app integrates published safety incidents and SU campus alerts. \ To design effective crowdsourcing of public safety information, we further conducted a lab experiment to investigate what factors affect people's sharing decisions. The results suggest that both time of day and type of location significantly affect people's sharing decisions. \
Smartphone Application Launch with Smarter Scheduling
The time it takes to launch a smartphone application is unpredictable. In this work, we explore how these unpredictable launch times are affected by constraints associated with reading (writing) from (to) flash storage. We conduct the first large-scale measurement study on the Android I/O delay using the data collected from our Android application running on 1480 devices within 188 days. Among others, we observe that reads experience up to 626% slowdown when blocked by concurrent writes. We design a pilot solution, wherein by prioritizing reads over writes we are able to reduce the launch delay by up to 37.8%.
The Proxemic Web: Designing for Proxemic Interactions with Responsive Web Design
The Proxemic Web is a proposal for extending responsive web design as a means to enable proxemic interactions through the web browser.
A Multi-tiered Model for Context-Aware Systems
Context awareness is considered one of the most important challenges to be tackled in the field of ubiquitous computing (ubicomp). In this perspective, this paper describes a general model for context-aware systems. The model is organized in multiple tiers, each one addressing a specific design characteristic related to the area. The proposition can be applied in the design and assessment of context-aware systems.
MemoryRetrospect : Lifelogging with Social Awareness
As a promising procedure of mobile application. So far, lifelogging has already some initial attempts on photos, audios and video records. However, they are just simple information recording tools, in which the receivers cannot feel the senders with empathy in space or time. In this poster, we propose a concept called MemoryRetrospect, which combines Lifelogging with Social Awareness. It considers not only our daily photos and videos, but also the weather, the locations and time. When and how to open the e-records can be set by the senders' willing.
Eco-Feedback for Non-Consumption
Eco-feedback is a strategy to increase awareness of resource use and to encourage conservation. We applied eco-feedback on household food waste with the prospective to increase awareness and explore its impact on food related decision-making. In this paper we present a prototype of an eco-feedback system for food waste, which was deployed in a student house. In preliminary findings, participants indicated positive effects on dealing with leftovers, food preparation and reflection about food waste issues, when eco-feedback was deployed. Findings are used for the next design iteration of the concept and, for more concluding results, in a larger-scale evaluation.
Towards Targeted Gestures: Adding Directional Context to Gestures Using Doppler Effect
Human beings often give non-verbal instructions through motions of the hand and arm, such as pointing or waving. These motions convey not just actions, but the direction or target of those actions. In this paper, we integrate direction into gesture definitions by detecting frequency shifts created by relative motion between a receiver and transmitter and combining this with inertial motion data captured by a smartphone. With the combined data we are able separate similar gestures with 71.7% accuracy in a typical home use environment.
Activity Recognition Exploiting Classifier Level Fusion of Acceleration and Physiological Signals
We investigate how to effectively combine physiological signals with acceleration signals to conduct activity recognition task. Firstly, features are extracted from acceleration and physiological signals, including heart rate variability (HRV). Secondly, classifier level fusion is utilized to combine the models built by acceleration and physiological features separately. Experiment results show that activity recognition task can benefit from HRV features, and classifier level fusion has its superiority over feature level fusion.
Influencing Driver Behavior through Future Expressway Traffic Predictions
We propose a method for changing the driver's departure time by predicting the future traffic conditions and informing the driver on how long the driver will expect to wait in a traffic jam based on the time at which the driver chooses to depart from the rest area.
Providing Services on Demand By User Action Modeling on Smart Phones
We propose a novel approach to schedule services like Wi-Fi and 3G on smartphones. Using Wi-Fi as an example, we show that intelligent scheduling based on a user's activity level leads to lower power consumption without adversely affecting the user experience. Data from various sensors is used to model and predict a user's activity, which is then used to schedule the wireless services.
Atmos: A Hybrid Crowdsourcing Approach to Weather Estimation
Atmos leverages a crowd-sourcing network of mobile devices for the collection of in situ weather related sensory data, provided by available on-board sensors, along with human input, to generate highly localized information about current and future weather conditions.
Contexto: Lessons Learned from Mobile Context Inference
Our study examines how data collected from a rich set of sensors installed on mobile devices can be utilized to infer users' behavior and environment. We present the knowledge acquired from a two-week study of various new user contexts which are relevant to students' daily activities. We compare various machine learning methods and report their effectiveness for inferring the users' context from the collected data. We also present our findings on how to evaluate context inference systems, on the importance of explicit and latent labeling for context inference and on the effect of new users on the results' accuracy.
Non-Invasive Rapid and Efficient Firmware Update for Wireless Sensor Networks
To maintain software of sensor nodes in wireless sensor networks efficiently, it is necessary to minimize the size of transferred data in firmware update. We propose a non-invasive rapid and efficient incremental firmware update algorithm called MoRE. In MoRE algorithm, the host transfers only the information of different parts between old and new firmware image to reduce the size of transferred data. The sensor node makes new binary image from its current image and the transferred messages. The MoRE shows comparable performance to previous works without invasive methods.
Implicit Gaze based Annotations to Support Second Language Learning
This paper explores if implicit gaze based annotations \ can support reading comprehension tasks of second language learners. \ We show how to use eye tracking to add implicit annotations to the \ text the user reads.
Sensing and Sharing Temperature to Support Remote Relationships
Among the data that can now be readily sensed and shared, temperature has potential to support relationships, because people perceive warmth as intimate and temperature as indicative of comfort and wellness. We interviewed 20 participants who interacted with prototypes of temperature sensing and sharing systems. Participants believed that shared temperature information could strengthen their relationship by supporting coordination, reassurance, and intimacy. They also perceived challenges common in UbiComp – such as difficulty interpreting data and tradeoffs between intimacy and privacy. We discuss nuances and guidelines for using temperature information and how these results can inform future research and designs.
Protecting Mobile Users from Visual Privacy Attacks
An increasing number of people are using mobile devices in public places such as buses, trains, airports, coffee shops, and restaurants. This new working practice incurs un-authorized visual access of the mobile display by the bystanders, which we call visual privacy attack. In this paper, we propose a solution that captures the surrounding environment through user's mobile phone camera and determines whether any un-authorized person is obtaining visual access to the user's mobile screen. We develop an Android application, iAlert, that alerts the user based on whether or not the displayed text on the screen is readable by bystanders.
Arfid: A Reconfigurable Fabric of Input Devices for the Internet of Things
Arfid is a "fabric" for reconfigurable input devices that connects low-cost, battery-free inputs to arbitrarily specified functions in their surroundings via a buildingwide network of RFID readers. Users can reassign controllers' functions using a simple web interface.
SPELL: Affecting Thermal Comfort Through Perceptive Techniques
Thermostats allow people to set the temperature they desire, even if personal thermal comfort perception is tied to a number of external stimuli. We prototype a system that influences people's thermal comfort through other stimuli instead of temperature changing envisioning a smart system for heating control that proactively compensates temperature variations using light color variations.
Cricking: Browsing Physical Space with Smart Glass
We are presenting a browsable physical space with clicking solution. Our target space is a shelf equipped with Radio Frequency Identification (RFID) containing changing number of DVD´s and books. The mouse is replaced by a smartphone acting as a touch pad, the cursor is replaced by a controllable moving head beam light that projects a spot on the shelf and the information about the products near the cursor's position is then shown on a heads-up display (HUD) such as Google Glass.
Portrait Pigeon: An Interactive Photo Messaging Wall for Seniors
Physical communication artifacts, such as printed photos, support important forms of offline communication for older adults, and we examine how physical photos can be augmented to facilitate lightweight online social communication. This approach embeds online messaging into a familiar artifact - photos. This paper presents Portrait Pigeon, a ubiquitous lightweight messaging platform for seniors that integrates in-home photo displays into online communication.
Mobile Augmented Reality for Browsing Physical Spaces
We present a system that uses Radio Frequency Identification (RFID) to obtain information about the objects on a shelf, and Augmented Reality (AR) to let users click on a live image of that shelf shown on a handheld device, accessing the information about the objects located in the vicinity of the clicked spot. A smart shelf with RFID has been set up to which a AR marker has been added to be able to map physical to screen coordinates. The resulting experience is close to browsing a shelf, clicking on it and obtaining information about the objects it contains.
A Safety Assessment System for Sidewalks at Night Utilizing Smartphones' Light Sensors
Along with the popularization of smartphones, which have various sensors such as accelerometers and GPS, location based services are also growing in popularity. \ Additionally, with the growth demand of in security awareness, pedestrian navigation systems are required to provide safety information. \ Thus, we propose and develop an illuminance inferring method utilizing smartphone's light sensors for assessing a safety level of sidewalks at night. \
Interfacing Information in Affective User Studies
In affective user studies, visual interfacing of data has received little attention. Such interfaces can support qualitative understanding, conveying insight about static and temporally evolving information. In this paper we present User Portrait - an abstraction and visualization method that condenses the essence of a study's data in a single figure. It is an inverted pyramid design, where the information abstraction is communicated on the top view, while the details are displayed on a need-to-know basis. The method has been applied to a longitudinal study of student affect vs. exam performance, effectively visualizing its voluminous data set. \
Motivational Affordances and Personality Types in Personal Informatics
This poster investigates how various affordances in gamified personal informatics applications affect motivation levels to track and achieve goals for users with different personality types. We conducted a study to examine how user personality traits relate to (1) motivational affordances in behavior tracking applications and (2) the specific behaviors users prefer to track.
ContextSense: Unobtrusive Discovery of Incremental Social Context using Dynamic Bluetooth Data
User-centric ambient social contexts can be effectively captured by dynamic bluetooth data. However, conventional approaches for training classifiers struggle with social contexts that are incrementally constructed and continuously discovered in everyday environments. Incremental social contexts can confuse a classifier because it assumes that the number and composition of context classes is fixed throughout training and inference phases. To address this challenge we propose ContextSense, an ELM-based learning method for continuous and unobtrusive discovery of new social contexts incrementally from dynamic bluetooth data. Experimental results show that ContextSense can automatically cope with "incremental social context" classes that appear unpredictably in real-world.
Attelia: Sensing User’s Attention Status on Smart Phones
In progressing ubiquitous computing where number of devices, applications and the web services are ever increasing, human user's attention is a new bottleneck in computing. This paper proposes Attelia, a novel middleware that senses user's attention status on user's smart phones in real-time, without any dedicated psycho-physiological sensors. To find better delivery timings of interruptive notifications from various applications and services to mobile users, Attelia detects breakpoints of user's activity on the smart phones, with "Application as a Sensor"(AsaS) approach and machine learning technique. Our evaluation of Attelia shows it can detect breakpoints of users with accuracy of 80-90%.
BiliCam: Using Mobile Phones to Monitor Newborn Jaundice
We present BiliCam, a low-cost system that uses smartphone cameras to assess newborn jaundice. Although jaundice is common in healthy newborns, early detection of extreme jaundice is essential to prevent brain damage or death. Current detection techniques, however, require clinical tests with blood samples or other specialized equipment. Consequently, newborns often depend on visual assessments of their skin color at home, which is known to be unreliable.
Human Joint Angle Estimation with an E-textile Sensor
Sensors vs. Human: Comparing Sensor Based State Monitoring with Questionnaire Based Self-Assessment in Bipolar Disorder Patients
MagNail: Augmenting Nails with a Magnet to Detect User Actions using a Smart Device
Single Capacitive Touch Sensor That Detects Multi-touch Gestures
Canine Reachability of Snout-based Wearable Inputs
Washability of E-Textile Stretch Sensors and Sensor Insulation
Lower-Limb Goniometry using Stitched Sensors: Effects of Manufacturing and Wear Variables
Examination of Human Factors for Wearable Line-of-Sight Detection System
Bridging the Gap between Law & HCI: Designing Effective Regulation of Human Autonomy in Everyday UbicompSystems
Smart Garments: An On-Body Interface for Sensory Augmentation and Substitution
Ambient Assisted Living: Towards a Model of Technology Adoption and Use Among Elderly Users
Automated mobile systems for multi-dimensional well-being sensing and feedback
Improving Smartphone Responsiveness through I/O Optimizations
Animal Computer Interaction: Specialized Technology to aid Assistance Dogs
Adaptive Sensor Cooperation for Predicting Human Mobility
Supporting Serendipitous Learning with Mobile Devices
Responsive and Emotive Wearable Technology: devices, bodies, data and communication
The Measurable Me: The Influence of Self-Quantification on the Online User's Decision Making Process
Designing New Input Modalities for Wearables & Digitized Home
Meaningful Game Elements for Personal Informatics
An Assistive EyeWear Prototype that Interactively Converts 3D Object Locations into Spatial Audio
In Interaction with Wearable Activity Recognition Technologies
Foray's into Disability Discrimination Legislation and Wearable Computing
Gestural Activity Recognition for Canine-Human Communication
Garment-Integrated Wearable Sensing for Knee Joint Monitoring
Tuesday
Room
Seattle 1 & 2
Seattle 3
Emerald 2
09:00-10:30
Mobile Applications
Christine Lv
Detecting Hybrid and Electric Vehicles Using a Smartphone
Pedestrians have difficulty noticing hybrid vehicles (HVs) and electrical vehicles (EVs) quietly approaching from behind. We propose a vehicle detection scheme using a smartphone carried by a pedestrian. A notification of a vehicle approaching can be delivered to wearable devices such as Google Glass. We exploit the high-frequency switching noise generated by the motor unit in HVs and EVs. Although people are less sensitive to these high-frequency ranges, these sounds are prominent even on a busy street, and it is possible for a smartphone to detect these signs . The ambient sound captured at 48 kHz is converted to a feature vector in the frequency domain. A J48 classifier implemented on a smartphone can determine whether an EV or HV is approaching. We have collected a large amount of vehicle data at various locations. The false-positive and false-negative rates of our detection scheme are 1.2% and 4.95%, respectively. The first alarm was detected as early as 11.6 s before the vehicle approached the observer. The scheme can also determine the vehicle speed and vehicle type.
Mobile Maestro: Enabling Immersive Multi-Speaker Audio Applications on Commodity Mobile Devices
The goal of this work is to provide an abstraction of ideal sound environments to a new emerging class of Mobile Multi-speaker Audio (MMA) applications. Typically, it is challenging for MMA applications to implement advanced sound features (e.g., surround sound) accurately in mobile environments, especially due to unknown, irregular loudspeaker configurations. Towards an illusion that MMA applications run over specific loudspeaker configurations (i.e., speaker type, layout), this work proposes AMAC, a new Adaptive Mobile Audio Coordination system that senses the acoustic characteristics of mobile environments and controls individual loudspeakers adaptively and accurately. The prototype of AMAC implemented on commodity smartphones shows that it provides the coordination accuracy in sound arrival time in several tens of microseconds and reduces the variance in sound level substantially.
User Interaction-based Profiling System for Android Application Tuning
Quality improvement in mobile applications should be based on the consideration of several factors, such as users’ diversity in spatio-temporal usage, as well as the device’s resource usage, including battery life. Although application tuning should consider this practical issue, it is difficult to ensure the success of this process during the development stage due to the lack of information about application usage. This paper proposes a user interaction-based profiling system to overcome the limitations of development-level application debugging. In our system, the analysis of both device behavior and energy consumption is possible with fine-grained process-level application monitoring. By providing fine-grained information, including user interaction, system behavior, and power consumption, our system provides meaningful analysis for application tuning. The proposed method does not require the source code of the application and uses a web-based framework so that users can easily provide their usage data. Our case study with a few popular applications demonstrates that the proposed system is practical and useful for application tuning.
SENSeTREAM: Enhancing Online Live Experience with Sensor-Federated Video Stream Using Animated Two-Dimensional Code
We propose a novel technique that aggregates multiple sensor streams generated by totally different types of sensors into a visually enhanced video stream. This paper shows major features of SENSeTREAM and demonstrates enhancement of user experience in an online live music event. Since SENSeTREAM is a video stream with sensor values encoded in a two-dimensional graphical code, it can transmit multiple sensor data streams while maintaining their synchronization. A SENSeTREAM can be transmitted via existing live streaming services, and can be saved into existing video archive services. We have implemented a prototype SENSeTREAM generator and deployed it to an online live music event. Through the pilot study, we confirmed that SENSeTREAM works with popular streaming services, and provide a new media experience for live performances. We also indicate future direction for establishing visual stream aggregation and its applications.
Wearable Input/Output
Kent Lyons
The Tongue and Ear Interface: A Wearable System for Silent Speech Recognition
We address the problem of performing silent speech recognition where vocalized audio is not available (e.g. due to a user's medical condition) or is highly noisy (e.g. during firefighting or combat). We describe our wearable system to capture tongue and jaw movements during silent speech. The system has two components: the Tongue Magnet Interface (TMI), which utilizes the 3-axis magnetometer aboard Google Glass to measure the movement of a small magnet glued to the user's tongue, and the Outer Ear Interface (OEI), which measures the deformation in the ear canal caused by jaw movements using proximity sensors embedded in a set of earmolds. We collected a data set of 1901 utterances of 11 distinct phrases silently mouthed by six able-bodied participants. Recognition relies on using hidden Markov model-based techniques to select one of the 11 phrases. We present encouraging results for user dependent recognition.
Hands-free gesture control with a capacitive textile neckband
We present a novel sensing modality for hands-free gesture controlled user interfaces, based on active capacitive sensing. Four capacitive electrodes are integrated into a textile neckband, allowing continuous unobtrusive head movement monitoring. We explore the capability of the proposed system for recognising head gestures and postures. A study involving 12 subjects was carried out, recording data from 15 head gestures and 19 different postures. We present a quantitative evaluation based on this dataset, achieving an overall accuracy of 79.1% for head gesture recognition and 40.4% for distinguishing between head postures (69.9% when merging the most adjacent positions), respectively. These results indicate that our approach is promising for hands-free control interfaces. An example application scenario of this technology is the control of an electric wheelchair for people with motor impairments, where recognised gestures or postures can be mapped to control commands.
FabriTouch: Exploring Flexible Touch Input on Textiles
Touch-sensitive fabrics let users operate wearable devices unobtrusively and with rich input gestures similar to those on modern smartphones and tablets. While hardware prototypes exist in the DIY crafting community, HCI designers and researchers have little data about how well these devices actually work in realistic situations. FabriTouch is the first flexible touch-sensitive fabric that provides such scientifically validated information. We show that placing a FabriTouch pad onto clothing and the body instead of a rigid support surface significantly reduces input speed but still allows for basic gestures. We also show the impact of sitting, standing, and walking on horizontal and vertical swipe gesture performance in a menu navigation task. Finally, we provide the details necessary to replicate our FabriTouch pad, to enable both the DIY crafting community and HCI researchers and designers to build on our work.
SwitchBack: An On-Body RF-Based Gesture Input Device
We present SwitchBack, a novel e-textile input device that can register multiple forms of input (tapping and bi-directional swiping) with minimal calibration. The technique is based on measuring the input impedance of a 7 cm microstrip short-circuit stub consisting of a strip of conductive fabric separated from a conductive fabric ground plane (also made of conductive fabric) by a layer of denim. The input impedance is calculated by measuring the stub's reflection coefficient using a simple RF reflectometer circuit, operating at 900MHz. The input impedance of the stub is affected by the dielectric properties of the surrounding material, and changes in a predictable manner when touched. We present the theoretical formulation, device and circuit design, and experimental results. Future work is also discussed.
Wearable Jamming Mitten for Virtual Environment Haptics
This paper presents a new mitten incorporating vacuum layer jamming technology to provide haptic feedback to a user. We demonstrate that layer jamming technology can be successfully applied to a mitten, and discuss advantages layer jamming provides as a wearable technology through its low profile form factor. Jamming differs from traditional wearable haptic systems by restricting a user's movement, rather than applying an actuation force on the user's body. Restricting the user's movement is achieved by varying the stiffness of wearable items, such as gloves. We performed a pilot study where the qualitative results showed users found the haptic sensation of the jamming mitten similar to grasping the physical counterpart.
MagicWatch: Interacting & Segueing
Seeking for more friendly, more efficient, and more effective human-computer interaction ways is an eternal hot topic. This video demonstrates a MagicWatch that can sense user gestures, understand user intensions, and achieve expected tasks with the underlying core techniques and the support of a back-end context aware smart system on a cloud platform. The MagicWatch can act as a pointer, a remote controller, and an information portal. Just using hand, you can point a building, a person, or a screen; you can control a device, for instance, changing TV channel, adjusting temperature, or switching slides; and you can get necessary information from the cloud. Moreover, this video highlights MagicWatch seamless interactions with objects in its surrounding and easy segueing cyber-physical spaces.
Health & Children
Inseok Hwang
Using Electrodermal Activity to Recognize Ease of Engagement in Children during Social Interactions
The recent emergence of comfortable wearable sensors has focused almost entirely on monitoring physical activity, ignoring opportunities to monitor more subtle phenomena, such as the quality of social interactions. We argue that it is compelling to address whether physiological sensors can shed light on quality of social interactive behavior. This work leverages the use of a wearable electrodermal activity (EDA) sensor to recognize ease of engagement of children during a social interaction with an adult. In particular, we monitored 51 child-adult dyads in a semi-structured play interaction and used Support Vector Machines to automatically identify children who had been rated by the adult as more or less difficult to engage. We report on the classification value of several features extracted from the child's EDA responses, as well as several other features capturing the physiological synchrony between the child and the adult.
Persuasive Technology to Improve Eating Behavior using a Sensor-Embedded Fork
This paper describes the design of a digital fork and a mobile interactive and persuasive game for a young child who is a picky eater and/or easily distracted during mealtime. The system employs Ubicomp technology to educate children on the importance of a balanced diet while motivating proper eating behavior. To sense a child's eating behavior, we have designed and prototyped a sensor-embedded digital fork, called the Sensing Fork. Furthermore, we have developed a story-book and persuasive game, called the Hungry Panda, on a smartphone. This capitalizes on the capabilities of the Sensing Fork to interact with and modify children's eating behavior during mealtime. We report the results of a real-life study that involves mother-child subjects and tested the effectiveness of the Sensing Fork and Hungry Panda game in addressing children's eating problems. Our findings exhibit positive effects for changing children's eating behavior.
BiliCam: Using Mobile Phones to Monitor Newborn Jaundice
Health sensing through smartphones has received considerable attention in recent years because of the devices’ ubiquity and promise to lower the barrier for tracking medical conditions. In this paper, we focus on using smartphones to monitor newborn jaundice, which manifests as a yellow discoloration of the skin. Although a degree of jaundice is common in healthy newborns, early detection of extreme jaundice is essential to prevent permanent brain damage or death. Current detection techniques, however, require clinical tests with blood samples or other specialized equipment. Consequently, newborns often depend on visual assessments of their skin color at home, which is known to be unreliable. To this end, we present BiliCam, a low-cost system that uses smartphone cameras to assess newborn jaundice. We evaluated BiliCam on 100 newborns, yielding a 0.85 rank order correlation with the gold standard blood test. We also discuss usability challenges and design solutions to make the system practical.
Classifying Children with 3D Depth Cameras for Enabling Children's Safety Applications
In this work, we present ChildSafe, a classification system which exploits human skeletal features collected using a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, ranging in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for designing various child protection applications.
SoberDiary: A Phone-based Support System for Assisting Recovery from Alcohol Dependence
Alcohol dependence is a chronic disorder associated with severe harm in multiple areas, and relapsing is easy despite treatment. After alcohol-dependent patients complete alcohol withdrawal treatment and return to their regular lives, they face further challenges in order to maintain sobriety. This study proposes SoberDiary, a phone-based support system that enables alcohol-dependent patients to self-monitor and self-manage their own alcohol use behavior and remain sober in their daily lives. Results from a 4-week user study involving 11 clinical patients show that, using SoberDiary, patients can self-monitor and self-manage their alcohol use behavior, reducing their total alcohol consumption and the number of drinking or heavy drinking days that occur following intervention.
10:30-11:00
Break
11:00-12:30
Sensing in the Home
Anind Dey
Identifying Outlets at which Electrical Appliances are Used by Electrical Wire Sensing to Gain Positional Information about Appliance Use
This paper presents a new method for estimating which outlet an electrical appliance is plugged into by using the electrical wiring installed in the building. By making use of the voltage drop caused by the wire, we can estimate the distance between the sensor and an electrical appliance plugged into an outlet on an electrical circuit. If we have a floor plan of an environment of interest showing a wiring diagram and where a sensor is attached, we can determine which outlet an electrical appliance is plugged into from the distance between the sensor and the appliance. The estimated outlet position of an appliance is very useful for understanding real-world events and developing real-world applications, e.g., providing user location and appliance location aware services, daily activity recognition, and estimating a user's indoor location through electrical appliance use under specific conditions.
A Self-Calibrating Approach to Whole-Home Contactless Power Consumption Sensing
In this paper, we present a significant improvement over past work on non-contact end-user deployable sensor for real time whole home power consumption. The technique allows users to place a single device consisting of magnetic pickups on the outside of a power or breaker panel to infer whole home power consumption without the need for professional installation of current transformers (CTs). The new approach does not require precise placement on the breaker panel, a key requirement in previous approaches. This is enabled through a self-calibration technique using a neural network that dynamically learns the transfer function despite the placement of the sensor and the construction of the breaker panel itself. We also demonstrate the ability to actually infer true power using this technique, unlike past solutions that have only been able to capture apparent power. We have evaluated our technique in six homes and one industrial building, including one seven-day deployment. Our results show we can estimate true power consumption with an average accuracy of 95.0% during naturalistic energy use in the home.
Smart-Mat: Recognizing and Counting Gym Exercises with Low-cost Resistive Pressure Sensing Matrix
There is a large class of routine physical exercises that are performed on the ground, often on dedicated ’mats’ (e.g. push-ups, crunches, bridge). Such exercises involve coordinated motions of different body parts and are difficult to recognize with a single body worn motion sensors (like a step counter). Instead a network of sensors on different body parts would be needed, which is not always practicable. As an alternative we describe a cheap, simple textile pressure sensor matrix, that can be unobtrusively integrated into exercise mats to recognize and count such exercises. We evaluate the system on a set of 10 standard exercises. In an experiment with 7 subjects, each repeating each exercise 20 times, we achieve a user independent recognition rate of 82.5% and a user independent counting accuracy of 89.9%. The paper describes the sensor system, the recognition methods and the experimental results.
Powering Wireless Sensor Nodes with Ambient Temperature Changes
Power remains a challenge in the widespread deployment of long-lived wireless sensing systems, which has led researchers to consider power harvesting as a potential solution. In this paper, we present a thermal power harvester that utilizes naturally changing ambient temperature in the environment as the power source. In contrast to traditional thermoelectric power harvesters, our approach does not require a spatial temperature gradient; instead it relies on temperature fluctuations over time, enabling it to be used freestanding in any environment in which temperature changes throughout the day. By mechanically coupling linear motion harvesters with a temperature sensitive bellows, we show the capability of harvesting up to 21 mJ of energy per cycle of temperature variation within the range 5 ’ to 25 ’. We also demonstrate the ability to power a sensor node, transmit sensor data wirelessly, and update a bistable E-ink display after as little as a 0.25 ’ ambient temperature change.
Eyewear Computing
Ozan Cakmakci
A Comparison of Order Picking Assisted by Head-Up Display (HUD), Cart-Mounted Display (CMD), Light, and Paper Pick List
Wearable and contextually aware technologies have great applicability in task guidance systems. Order picking is the task of collecting items from inventory in a warehouse and sorting them for distribution; this process accounts for about 60% of the total operational costs of these warehouses. Current practice in industry includes paper pick lists and pick-by-light systems. We evaluated order picking assisted by four approaches: head-up display (HUD); cart-mounted display (CMD); pick-by-light; and paper pick list. We report accuracy, error types, task time, subjective task load and user preferences for all four approaches. The findings suggest that pick-by-HUD and pick-by-CMD are superior on all metrics to the current practices of pick-by-paper and pick-by-light.
The Effects of Visual Displacement on Simulator Sickness in Video See-Through HMDs
We present an experiment exploring the role of visual displacement to simulator sickness in a video see-through head-mounted display (HMD). To identify the effect of visual displacement on simulator sickness, we examined the effect of visual displacement conditions (ranging from 50 to 300 mm) on simulator sickness and investigated the adaptation of simulator sickness over three days. The results indicated that the total symptom score of simulator sickness in the 300 mm visual displacement condition was significantly higher than that of simulator sickness in the other visual displacement conditions. In addition, the total symptom score of simulator sickness became significantly lower over 1–3 days in the 200 mm visual displacement condition and 1–2 days in the 300 mm visual displacement condition, which means that adaptation was found over three days. However, only partial adaptation was shown in the visual displacement 300, thereby suggesting that high sensory conflict in visual displacement 300 results in increased time to adapt. These results indicate that simulator sickness in video see-through HMDs are adaptable over time, which supports previous studies.
Understanding the Wearability of Head-Mounted Devices from a Human-Centered Perspective
Extensive efforts have been dedicated to developing wearables, but existing solutions focus mainly on feasibility and innovation. Thus, although many devices are named ‘wearable’, users face some wearability issues. Previously adopted trial and error approaches have effectively produced wearables, but not focused on human factors. Through an extensive analysis of online comments about head-mounted devices, this paper presents their problem space from a human perspective. The analysis of online comments from existing and potential users enabled us to identify key aspects of the wearability of head-mounted devices, bridging the gap between design decisions and users’ requirements.
Looking At or Through? Using Eye Tracking to Infer Attention Location for Wearable Transparent Displays
Wearable near-eye displays pose interesting challenges for interface design. These devices present the user with a duality of visual worlds, with a virtual window of information overlaid onto the physical world. Because of this duality, we suggest that the wearable interface would benefit from understanding where the user's visual attention is directed. We explore the potential of eye tracking to address this problem, and describe four eye tracking techniques designed to provide data about where the user's attention is directed. We also propose some attention-aware user interface techniques demonstrating the potential of the eyes for wearable displays user interface management.
Walkthrough Research: Methodological Potentials for Head-mounted Cameras as Reflexive Tools in Museum Contexts
This study investigates the potential of head-mounted video cameras as a technique for understanding human experience in museums. The technique is a design-research study at the intersection of visual-anthropology, ubiquitous computing and interaction design, and takes up the reflexive of digital humanities and ethnographies, in that the goal of the research is not to capture or provide determination of an experience, but instead to provide digital tools for reflection and understanding. The work uses a head-mounted video camera in museum spaces, and a set of simple image processing techniques to explore potential methods for understanding the relationship between people, objects, and environments in museum space.
Data Mining
Eran Toch
MobileMiner: Mining Your Frequent Behavior Patterns on Your Phone
Smartphones can collect considerable context data about the user, ranging from apps used to places visited. Frequent user patterns discovered from longitudinal, multi-modal context data could help personalize and improve overall user experience. Our long term goal is to develop novel middleware and algorithms to efficiently mine user behavior patterns entirely on the phone by utilizing idle processor cycles. Mining patterns on the mobile device provides better privacy guarantees to users, and reduces dependency on cloud connectivity. As an important step in this direction, we develop a novel general-purpose service called MobileMiner that runs on the phone and discovers frequent co-occurrence patterns indicating which context events frequently occur together. Using longitudinal context data collected from 106 users over 1-3 months, we show that MobileMiner efficiently generates patterns using limited phone resources. Further, we find interesting behavior patterns for individual users and across users, ranging from calling patterns to place visitation patterns. Finally, we show how our co-occurrence patterns can be used by developers to improve the phone UI for launching apps or calling contacts.
A Hierarchical Hidden Semi-Markov Model for Modeling Mobility Data
Ubiquity of portable location-aware devices and popularity of online location-based services, have recently given rise to the collection of datasets with high spatial and temporal resolution. The subject of analyzing such data has consequently gained popularity due to numerous opportunities enabled by understanding objects’ (people and animals, among others) mobility patterns. In this paper, we propose a hidden semi-Markov-based model to understand the behavior of mobile entities. The hierarchical state structure in our model allows capturing spatio-temporal associations on the locational history both at stay-points and on the paths connecting them. We compare the accuracy of our model with a number of existing spatio-temporal models using two real datasets. Furthermore, we perform sensitivity analysis on our model to evaluate its robustness in presence of common issues in mobility datasets such as existence of noise and missing values. Results of our experiments show superiority of the proposed scheme compared with the other models.
Mining Multivariate Time Series with Mixed Sampling Rates
Fitting sensors to humans and physical structures is becoming more and more common. These developments provide many opportunities for ubiquitous computing, as well as challenges for analyzing the resulting sensor data. From these challenges, an underappreciated problem arises: modeling multivariate time series with\emph{mixed sampling rates}. Although mentioned in several application papers using sensor systems, this problem has been left almost unexplored, often hidden in a preprocessing step or solved manually as a one-pass procedure (feature extraction/construction). This leaves an opportunity to formalize and develop methods that address mixed sampling rates in an automatic fashion. We approach the problem of dealing with multiple sampling rates from an aggregation perspective. We propose Accordion, a new embedded method that constructs and selects aggregate features iteratively, in a memory-conscious fashion. Our algorithms work on both classification and regression problems. We describe three experiments on real-world time series datasets, with satisfying results.
Predicting Activity Attendance in Event-Based Social Networks: Content, Context and Social Influence
The newly emerging event-based social networks (EBSNs) connect online and offline social interactions, offering a great opportunity to understand behaviors in the cyber-physical space. While existing efforts have mainly focused on investigating user behaviors in traditional social network services (SNS), this paper aims to exploit individual behaviors in EBSNs, which remains an unsolved problem. In particular, our method predicts activity attendance by discovering a set of factors that connect the physical and cyber spaces and influence individual's attendance of activities in EBSNs. These factors, including content preference, context (spatial and temporal) and social influence, are extracted using different models and techniques. We further propose a novel Singular Value Decomposition with Multi-Factor Neighborhood (SVD-MFN) algorithm to predict activity attendance by integrating the discovered heterogeneous factors into a single framework, in which these factors are fused through a neighborhood set. Experiments based on real-world data from Douban Events demonstrate that the proposed SVD-MFN algorithm outperforms the state-of-the-art prediction methods.
12:30-14:00
Lunch
14:00-15:30
Energy & Environment
Cecilia Mascolo
Energy Diet: Energy Feedback on a Bathroom Scale
Energy Diet is a design concept for a digital bathroom scale that displays personal health information in the form of body weight alongside environmental health information in the form of carbon weight. We intentionally conflate these two types of feedback in an effort to encourage people to regularly monitor their energy use as they weigh themselves and to reflect on the complex relationships between personal health and environmental health. To inform our design we tested paper prototypes and administered two surveys with 500 participants. We then created a working prototype that we deployed in four participants’ homes for one month each. This paper discusses findings and design implications from our surveys and in-home deployment. Overall, seeing carbon weight together with body weight on a scale helped participants to conceptualize energy consumption and to reflect on a range of daily activities and their environmental impacts.
Energy Advisors at Work: Charity Work Practices to Support People in Fuel Poverty
We present an ethnographic study of energy advisors working for a charity that provides support, particularly to people in fuel poverty. Our fieldwork comprises detailed observations that reveal the collaborative, interactional work of energy advisors and clients during home visits, supplemented with interviews and a participatory design workshop with advisors. We identify opportunities for Ubicomp technologies that focus on supporting the work of the advisor, including complementing the collaborative advice giving in home visits, providing help remotely, and producing evidence in support of accounts of practices and building conditions useful for interactions with landlords, authorities and other third parties. We highlight six specific design challenges that relate the domestic fuel poverty setting to the wider Ubicomp literature. Our work echoes a shift in attention from energy use and the individual consumer, specifically to matters of advice work practices and the domestic fuel poverty setting, and to the discourse around inclusive Ubicomp technologies.
Conversations with my Washing Machine: An in-the-wild Study of Demand Shifting with Self-generated Energy
Domestic microgeneration is the onsite generation of low- and zero-carbon heat and electricity by private households to meet their own needs. In this paper we explore how an everyday household routine ’ that of doing laundry ’ can be augmented by digital technologies to help households with photovoltaic solar energy generation to make better use of self-generated energy. This paper presents an 8-month in-the-wild study that involved 18 UK households in longitudinal energy data collection, prototype deployment and participatory data analysis. Through a series of technology interventions mixing energy feedback, proactive suggestions and direct control the study uncovered opportunities, potential rewards and barriers for families to shift energy consuming household activities and highlights how digital technology can act as mediator between household laundry routines and energy demand-shifting behaviors. Finally, the study provides insights into how a ’smart’ energy-aware washing machine shapes organization of domestic life and how people ’communicate’ with their washing machine.
Indoor Air Quality Monitoring System for Smart Buildings
Sensing the body
Paul Lukowicz
Unobtrusive Gait Verification for Mobile Phones
Continuously and unobtrusively identifying the phone's owner using accelerometer sensing and gait analysis has a great potential to improve user experience on the go. However, a number of challenges, including gait modeling and training data acquisition, must be addressed before unobtrusive gait verification is practical. In this paper, we describe a gait verification system for mobile phone without any assumption of body placement or device orientation. Our system uses a combination of supervised and unsupervised learning techniques to verify the user continuously and automatically learn unseen gait pattern from the user over time. We demonstrate that it is capable of recognizing the user in natural settings. We also investigated an unobtrusive training method that makes it feasible to acquire training data without explicit user annotation.
Enhancing Action Recognition through Simultaneous Semantic Mapping from Body-Worn Motion Sensors
Locations and actions are interrelated: some activities tend to occur at specific places, for example a person is more likely to twist his wrist when he is close to a door (to turn the knob). We present an unsupervised fusion method that takes advantage of this characteristic to enhance the recognition of location-related actions (e.g., open, close, switch, etc.). The proposed LocAFusion algorithm acts as a post-processing filter: At run-time, it constructs a semantic map of the environment by tagging action recognitions to Cartesian coordinates. It then uses the accumulated information about a location i) to discriminate between identical actions performed at different places and ii) to correct recognitions that are unlikely, given the other observations at the same location. LocAFusion does not require prior statistics about where activities occur, which allows for seamless deployment to new environments. The fusion approach is agnostic to the sensor modalities and methods used for action recognition and localization. For evaluation, we implemented a fully wearable setup that tracks the user with a foot-mounted motion sensor and the ActionSLAM algorithm. Simultaneously, we recognize hand actions through template matching on the data of a wrist-worn inertial measurement unit. In 10 recordings with 554 performed object interactions, LocAFusion consistently outperformed location-independent action recognition (8-31% increase in F1 score), identified 96% of the objects in the semantic map and overall correctly labeled 82% of the actions in problems with up to 23 classes.
Your activity tracker knows when you quit smoking
This paper discusses outcomes of our exploratory research aiming to discover ways of utilising continuous long term respiratory rate data collected from actigraphy (wrist-worn accelerometers.) We show that by monitoring changes in respiratory rate during sleep, we can detect and visualise various physical conditions that were previously not detectable using such simple wearable sensors, namely; the subjective level of drunkenness, fever, and smoking cessation. This study provides valuable insight into the potential of actigraphy, not simply as a tool for detecting common daily activities, but as a base for building a generic lifelog system that can evaluate the more qualitative aspects of your life.
BioScope: An Extensible Bandage System for Facilitating Data Collection in Nursing Assessments
To facilitate the collection of patient biosignals, designing extensible sensing devices in which sensor management is simplified is essential. This paper presents BioScope, an extensible sensing system that facilitates collecting data used in nursing assessments. We conducted experiments to demonstrate the potential of the system. The results obtained in this study can be applied in improving the design, thus enabling BioScope to facilitate data collection in numerous potential applications.
Gait analysis using shoe-worn inertial sensors: how is foot clearance related to walking speed?
Spatiotemporal gait analysis with body worn inertial sensors improves diagnosis in clinical practice. Most of the gait performance measures are affected by walking speed. However, it has not been investigated that how much information foot clearance parameters share with the key parameters of gait performance domains. Using shoe-worn inertial sensors and previously validated algorithm we measured spatiotemporal as well as clearance gait parameters in a cohort of able-bodied adults over the age of 65 (N=879). Principal components analysis showed that variability of foot clearance parameters contribute to the main variability in gait data. Moreover, only weak to moderate correlation of gait speed and stride length with some clearance parameters has been observed. We recommend the assessment of clearance parameters during gait analysis in addition to parameters such as gait speed, bearing in mind the importance of foot clearance measures in obstacle negotiation, slipping and tripping related falls.
Public Displays & Interactions
Judy Kay
Projective Testing of Diurnal Collective Emotion
Projective tests are personality tests that reveal individuals’ emotions (e.g., Rorschach inkblot test). Unlike direct question-based tests, projective tests rely on ambiguous stimuli to evoke responses from individuals. In this paper we develop one such test, designed to be delivered automatically, anonymously and to a large community through public displays. Our work makes a number of contributions. First, we develop and validate in controlled conditions a quantitative projective test that can reveal emotions. Second, we demonstrate that this test can be deployed on a large scale longitudinally: we present a four-week deployment in our university’s public spaces where 1431 tests were completed anonymously by passers-by. Third, our results reveal strong diurnal rhythms of emotion consistent with results we obtained independently using the Day Reconstruction Method (DRM), literature on affect, well-being, and our understanding of our university’s daily routine.
PriCal: Context-adaptive Privacy in Ambient Calendar Displays
PriCal is an ambient calendar display that shows a user's schedule similar to a paper wall calendar. PriCal provides context-adaptive privacy to users by detecting present persons and adapting event visibility according to the user's privacy preferences. We present a detailed privacy impact assessment of our system, which provides insights on how to leverage context to enhance privacy without being intrusive. PriCal is based on a decentralized architecture and supports the detection of registered users as well as unknown persons. In a three-week deployment study with seven displays, ten participants used PriCal in their real work environment with their own digital calendars. Our results provide qualitative insights on the implications, acceptance, and utility of context-adaptive privacy in the context of a calendar display system, indicating that it is a viable approach to mitigate privacy implications in ubicomp applications.
Mercury: An Application Store for Open Display Networks
As the cost of display hardware falls so the number of public display networks being deployed is increasing rapidly. While these networks have traditionally taken the form of digital signage used for advertising and information there is increasing interest in the vision of ’open display networks’. A key component of any open display network is an effective channel for disseminating applications created by third-parties and recent research has proposed a display-oriented ’application store’ as one such channel. In this paper we present a critical analysis of the requirements and design of display application stores ’ providing insights designed to help the implementers of future application stores.
AiD: Augmented Information Display
Augmented Information Display (AiD) is an LCD-based communicative display device that transmits both visible (RGB) and invisible (infrared) information using temporal and spectral multiplexing. A field-sequential backlight system switches between a standard white or RGB LED backlight and a near-infrared (NIR) LED backlight at 120Hz frequency. The visible and invisible information are transmitted through the same LCD electro-optics elements but during different time intervals that synchronize with the corresponding backlights. We implemented several prototype software systems to demonstrate the potential applications of this novel display platform, such as an augmenting digital signage display, an information beacon for positioning systems, and an accessibility system for people with hearing impairments.
15:30-16:00
Break
16:00-17:30
Input & Interaction
Eric Larson
IdentityLink: User-Device Linking through Visual and RF-Signal Cues
Mobile devices have become people's indispensable companion, since they allow each individual to be constantly connected with the outside world. In order to keep connected, the devices periodically send out data, which reveal some information about the device owner. Data sent by these devices can be captured by any external observer. Since the observer can observe only the wireless data, the actual person using the device is unknown. In this work, we propose IdentityLink, an approach leveraging the captured wireless data and computer vision to infer the user-device links, i.e., inferring which device is carried by which user. Knowing the user-device links opens up new opportunities for applications such as identifying unauthorized personnel in enterprises or finding criminals by law enforcement. By conducting experiments in a realistic scenario, we demonstrate how IdentityLink can be effectively applied to real practice.
Leveraging Directional Antenna Capabilities for Fine-Grained Gesture Recognition
This paper presents a recognition scheme for fine-grain gestures. The scheme leverages directional antenna and short- range wireless propagation properties to recognize a vocabulary of action-oriented gestures from the American Sign Language. Since the scheme only relies on commonly available wireless features such as Received Signal Strength (RSS), signal phase differences, and frequency subband selection, it is readily deployable on commercial-off-the-shelf IEEE 802.11 devices. We have implemented the proposed scheme and evaluated it in two potential application scenarios: gesture-based electronic activation from wheelchair and gesture-based control of car infotainment system. The results show that the proposed scheme can correctly identify and classify up to 25 fine-grain gestures with an average ac- curacy of 92% for the first application scenario and 84% for the second scenario.
BendID: Flexible Interface for Localized Deformation Recognition
We present BendID, a bendable input device that recognizes the location, magnitude and direction of its deformation. We use BendID to provide users with a tactile metaphor for pressure based input. The device is constructed by layering an array of indium tin oxide (ITO)-coated PET film electrodes on a Polymethylsiloxane (PDMS) sheet, which is sandwiched between conductive foams. The pressure values that are interpreted from the ITO electrodes are classified using a Support Vector Machine (SVM) algorithm via the Weka library to identify the direction and location of bending. A polynomial regression model is also employed to estimate the overall magnitude of the pressure from the device. A model then maps these variables to a GUI to perform tasks. In this preliminary paper, we demonstrate this device by implementing it as an interface for 3D shape bending and a game controller.
GazeHorizon: Enabling Passers-by to Interact with Public Displays by Gaze
AirLink: Sharing Files Between Multiple Devices Using In-Air Gestures
We introduce AirLink, a novel technique for sharing files between multiple devices. By waving a hand from one device towards another, users can directly transfer files between them. The system utilizes the devices’ built-in speakers and microphones to enable easy file sharing between phones, tablets and laptops. We evaluate our system in an 11-participant study with 96.8% accuracy, showing the feasibility of using AirLink in a multiple-device environment. We also implemented a real-time system and demonstrate the capability of AirLink in various applications.
Human Behavior
Sunny Consolvo
Privacy Behaviors of Lifeloggers using Wearable Cameras
A number of wearable ’lifelogging’ camera devices have been released recently, allowing consumers to capture images and other sensor data continuously from a first-person perspective. Unlike traditional cameras that are used deliberately and sporadically, lifelogging devices are always ’on’ and automatically capturing images. Such features may challenge users’ (and bystanders’) expectations about privacy and control of image gathering and dissemination. While lifelogging cameras are growing in popularity, little is known about privacy perceptions of these devices or what kinds of privacy challenges they are likely to create. To explore how people manage privacy in the context of lifelogging cameras, as well as which kinds of first-person images people consider ’sensitive,’ we conducted an in situ user study (N = 36) in which participants wore a lifelogging device for a week, answered questionnaires about the collected images, and participated in an exit interview. Our findings indicate that: 1) some people may prefer to manage privacy through in situ physical control of image collection in order to avoid later burdensome review of all collected images; 2) a combination of factors including time, location, and the objects and people appearing in the photo determines its ’sensitivity;’ and 3) people are concerned about the privacy of bystanders, de- spite reporting almost no opposition or concerns expressed by bystanders over the course of the study.
Money Walks: A Human-Centric Study on the Economics of Personal Mobile Data
In the context of a myriad of mobile apps which collect personally identifiable information (PII) and a prospective market place of personal data, we investigate a user-centric monetary valuation of mobile PII. During a 6-week long user study in a living lab deployment with 60 participants, we collected their daily valuations of 4 categories of mobile PII (communication, e.g. phonecalls made/received, applications, e.g. time spent on different apps, location and media, e.g. photos taken) at three levels of complexity (individual data points, aggregated statistics and processed, i.e. meaningful interpretations of the data). In order to obtain honest valuations, we employ a reverse second price auction mechanism. Our findings show that the most sensitive and valued category of personal information is location. We report statistically significant associations between actual mobile usage, personal dispositions, and bidding behavior. Finally, we outline key implications for the design of mobile services and future markets of personal data.
Connecting Personal-scale Sensing and Networked Community Behavior to Infer Human Activities
Mobile-Social
Koji Yatani
CheckInside: A Fine-grained Indoor Location-based Social Network
Existing location-based social networks (LBSNs), e.g. Foursquare, depend mainly on GPS or network-based localization to infer users' locations. However, GPS is unavailable indoors and network-based localization provides coarse-grained accuracy. This limits the accuracy of current LBSNs in indoor environments, where people spend 89% of their time. This in turn affects the user experience, in terms of the accuracy of the ranked list of venues, especially for the small-screens of mobile devices; misses business opportunities; and leads to reduced venues coverage. In this paper, we present CheckInside: a system that can provide a fine-grained indoor location-based social network. CheckInside leverages the crowd-sensed data collected from users' mobile devices during the check-in operation and knowledge extracted from current LBSNs to associate a place with its name and semantic fingerprint. This semantic fingerprint is used to obtain a more accurate list of nearby places as well as automatically detect new places with similar signatures. A novel algorithm for handling incorrect check-ins and inferring a semantically-enriched floorplan is proposed as well as an algorithm for enhancing the system performance based on the user implicit feedback. Evaluation of CheckInside in four malls over the course of six weeks with 20 participants shows that it can provide the actual user location within the top five venues 99% of the time. This is compared to 17% only in the case of current LBSNs. In addition, it can increase the coverage of current LBSNs by more than 25%.
Breaking Boundaries: The Uses & Gratifications of Grindr
People-nearby applications' (PNAs) are a form of ubiquitous computing that connect users based on their physical location data. One example is Grindr, a popular PNA that facilitates connections among gay and bisexual men. Adopting a uses and gratifications approach, we conducted two studies. In study one, 63 users reported motivations for Grindr use through open-ended descriptions. In study two, those descriptions were coded into 26 items that were completed by 525 Grindr users. Factor analysis revealed six uses and gratifications: social inclusion, sex, friendship, entertainment, romantic relationships, and location-based search. Two additional analyses examine (1) the effects of geographic location (e.g., urban vs. suburban/rural) on men’s use of Grindr and (2) how Grindr use is related to self-disclosure of information. Results highlight how the mixed-mode nature of PNA technology may change the boundaries of online and offline space, and how gay and bisexual men navigate physical environments.
Probabilistic Identification of Visited Point-of-Interest for Personalized Automatic Check-in
Automatic check-in, which is to identify a user's visited points of interest (POIs) from his or her trajectories, is still an open problem because of positioning errors and the high POI density in small areas. In this study, we propose a probabilistic visited-POI identification method. The method uses a new hierarchical Bayesian model for identifying the latent visited-POI label of stay points, which are automatically extracted from trajectories. This model learns from labeled and unlabeled stay point data (i.e., semi-supervised learning) and takes into account personal preferences, stay locations including positioning errors, stay times for each category, and prior knowledge about typical user preferences and stay times. Experimental results with real user trajectories and POIs of Foursquare demonstrated that our method achieved statistically significant improvements in precision at 1 and recall at 3 over the nearest neighbor method and a conventional method that uses a supervised learning-to-rank algorithm.
Challenges and Opportunities in Data Mining Contact Lists for Inferring Relationships
The smartphone contact list has the potential to be a valuable source of data about personal relationships. To understand how we might data mine the information that people store in their contact lists, we collected the contact lists of 54 participants. Initially we found that the majority of contact list features were unused. However, a further examination of the ’name’ field revealed a broad variety of contact-naming behaviors. We observed contact ’name’ fields that included affiliations, relationship role labels, multiple names, phone types, and references to companies / services / places. People’s appropriation and usage of contact lists have implications for automated attempts to merge or mine contact lists that assume people use the features and structure of the contact list tool as intended. They also offer new opportunities for data mining to better describe relationships between users and their contacts.
17:30-18:15
Town Hall Meeting
18:30-22:30
Argot: A Wearable One-Handed Keyboard Glove
The Argot glove is a one-handed, wearable input device that allows a user to type all English letters, numbers, and symbols without use of a traditional keyboard. The device design considers variables and constraints such as dexterity, feedback, mobility, learnability, speed of input, errors and false inputs, permanence, and comfort, as well as previous user knowledge. The glove design was informed by experimental investigations aimed at balancing tradeoffs between physical variables (reach, dexterity, haptics) and cognitive variables (learnability, text-entry method). It uses weak magnetic interactions during “key†presses to provide passive haptic feedback and reduce the need for precision in proprioceptive hand positioning.
Show images
MUVIB - Music & Vibration
The idea behind this design is to create a design with which it is possible to change the perception that the individual has with music, changing therefore their relationship with it. The result is a product of the category design for all, to be used by both deaf and able-bodied individuals without difference. MUVIB is composed of two mutually connected bracelets that allow music to transform into vibration. To the able bodied, the interaction with the sound, and in our particular case with a particular type of sound, music as can be of various nature. For the deaf the concept changes, while this diverse ability does not allow them to enjoy all the physical and mental benefits that music put in place. For all these reasons we decided to work on this issue, thinking of a device that could flatten this difference in perception, placing both targets on a level field. Thanks to MUVIB the hearing and the deaf will be able to benefit from the effects that these two vibrators bracelets bring the entire body, creating different situations where come into play factors such as pleasure, relaxation and adrenaline.
Show images
Flowers on a Pond
A solar powered LED dress with two lighting models which are presented in a specialised pattern making system
Ballet Hero: Building a Garment for Memetic Embodiment in Dance Learning
This paper describes the analysis and design of a wearable technology garment intended to aid with the instruction of ballet technique to adult beginners. A phenomenological framework is developed, and used to assess physiological training tools. Following this, a garment is developed that incorporates visual feedback inspired by animation techniques that more directly convey the essential movements of ballet. The garment design is presented, and a discussion is provided on the challenges in constructing an e-textile garment using contemporary materials and techniques.
Show images
Naero, light your energy
Naero is a practical wearable object that helps managing the physical exercise in a more efficient way. It is composed of two parts: a t-shirt made in a smart fabric that transforms the lactate present in sweat into energy and an electric circuit with an accelerometer and a Light Emitting Diode (LED) that works as interface. The purpose of Naero is to warn about the passage to the anaerobic respiration, and help the person who's doing the physical activity to prevent muscle pain and tiredness. When the LED is on it means that the fabric is starting to produce energy from the sweat, and the comparison with the data of the accelerometer gives important information about the performance of the user. This smart object can help a varied target, from professional athletes to aged persons or people doing sphysical rehabilitation. The presence of lactate in sweat is an important indicator and today athletes measure its value with an invasive medical test. With Naero this information can be checkedby the user himself, in a pleasant and simple way.
Show images
Baroesque Barometric Skirt
The Baroesque Barometric Skirt visualises data from the wearer's environment alongside physiological data of the wearer. The skirt changes visually as the wearer moves around environments and also as the body reacts to its present situation. This garment-device starts a conversation around the connections between the environmental and physiological data of the wearer. This short paper charts the evolution of the Baroesque Barometric Skirt from purpose to design, to making the skirt and constructing the electronics and code that become integral to it. The Baroesque Barometric skirt contributes a new way of sensing and presenting environmental and physiological data together.
Show images
Haley Sound around the clock
Haley is a digital clock with acoustic function. It notices sounds and transmits information to an app. The app creates a mapping area with different classes of sound level in different places, to have a complete panning shot of the noise in your life location.
You can use it like a simple mark time to take with you, on your jeans pocket or on your bag like an accessory, and when you press a button it can quantify the dB (decibell) around you. With this object you can control the noise pollution in your surrounding space and choose the places on the basis of your necessity.
You can use it like a simple mark time to take with you, on your jeans pocket or on your bag like an accessory, and when you press a button it can quantify the dB (decibell) around you. With this object you can control the noise pollution in your surrounding space and choose the places on the basis of your necessity.
Show images
JACKIT
Today our life is dominated by technology. It happens often that we trust our devices too much and when they run down we are completely floored. In this case we just desire a bit of extra energy to solve our troubles.
Jackit is a jacket made of a new textile combination of knitted copper and constantan and a textile fiber that can change depending on the use of the jacket. This textile uses the Seebeck effect to produce energy and recharges a power bank connected inside the jacket. The Seebeck effect uses the different temperature between the one of the human body and the external temperature to produce energy. The energy of the power bank can then be used to charge various electric devices. The amount of energy obtained depends on the outside air temperature.
Jackit is a jacket made of a new textile combination of knitted copper and constantan and a textile fiber that can change depending on the use of the jacket. This textile uses the Seebeck effect to produce energy and recharges a power bank connected inside the jacket. The Seebeck effect uses the different temperature between the one of the human body and the external temperature to produce energy. The energy of the power bank can then be used to charge various electric devices. The amount of energy obtained depends on the outside air temperature.
Show images
TWINY emotional logging
Taking stress out of people's lives is a great step to a better life in the future. To create a healthier lifestyle it is important to prevent stress related illnesses. The goal of this project is to make people aware of their state of mind and conscious of how they feel. Twiny is an elastic bracelet that gathers physical parameters through sensors: connecting emotions to physical state, Twiny gives the possibility to learn how to control mood, organizing time and trying to make people feel comfortable. Matching feelings data with calendar and health state, Twiny is able to build a grid of feelings, suggesting how to react to a bad mood or, for instance a constant migraine. Twiny attempts to correlate data down to every physical rash caused from stress to the body. Making people aware of their unconscious feelings will help them build a better lifestyle. Twiny, which wirelessly sends data to an application, allows users to control their own parameters every time they need.
Show images
E-Textile Swatchbook Exchange: Sharing Physical Work Samples
The E-Textile Swatch Exchange is a platform for sharing physical work samples in the field of electronic textiles. The exchange wishes to emphasize the importance of physicality and quality workmanship in an increasingly digital world. Individuals and collaborative efforts participate in the exchange by submitting a unique swatch design of their own, and in turn receive a compiled collection of everybody else's swatches. This means that everybody participating needs to make as many multiples of their swatch as the total number of participants. There are no guidelines defining what the swatches could or should be, only that they relate to the field of E-Textiles.
S.A.R.A. – synesthetic augmented reality application
S.A.R.A. – (synesthetic augmented reality application) is an App exploring the potential of using a mobile device as a unique and wearable musical interface.
'TellMe': Therapeutic Clothing for Children with Autism Spectrum Disorder (ASD) in Daily Life
Special education and treatment methods in the early ages are the keys to relieving Autism Spectrum Disorder (ASD) symptoms. These smart clothing items ‘TellMe' are designed to treat ASD symptoms in boys by encouraging them to speak out and express themselves while playing with and enjoying the clothing. Therapeutic functions, including different types of sensors (a flexible film-like pressure sensor, a light sensor, and a motion sensor) and actuators (LEDs, a DC motor, and a vibration motor), are incorporated to the clothing. By playing with the interactive robot characters on the clothing, such as speaking into the microphone or activating the sensors and other actuators, a child wearing the garment can naturally learn and practice how to express his feelings, emotions, and opinions.
Show images
Innovative Explorations in Apparel Design to Create Engineered Outfits with Lighting Technologies
The future of innovation in clothing lies within wearable technologies, advanced design development processes and advanced construction techniques. The integration of functional apparel design and engineering has attracted a lot of attention in the last decade. The objective of our work is to explore new avenues that connect design and technology, and to improve upon traditional techniques in apparel product development and construction. We will discuss the techniques used in our research project to explore fast prototyping techniques including laser cutting, 3D body scanning, draping on a half scale mannequin, 3D printing, and the inclusion of wearable electronics. The use of these fast prototyping techniques can reduce the cost in production and simplify the development process.
Show images
Digital Lace: A Collision of Responsive Technologies
Designing with properties such as colour-change and light using electronics and digital control brings new challenges within art and design, and a range of new possibilities for aesthetics, tactility and functionality. Heimtextil 2014 (accessed April 2014) [1] promotes emerging materials and technologies as one of four trends which highlight the increasing demand for unique products utilizing novel material properties and digital making. However, there is still limited insight into the creative potential of these materials that are fundamental to the exploitation of ‘smart' material properties, the development of new ‘responsive' surfaces and digital tools that facilitate designing with colour-change and light-emitting properties specific to textiles. This submission to the Fiber arts category presents new material concepts as Digital Lace: a novel, multifaceted textile which will be presented as an interactive table runner for a digitally manufactured console table. Digital Lace explicitly pools together the digital-craft skills base and disparate expertise of printed textile practitioner and thermochromic specialist, (name) and constructed textile practitioner and light-emitting optical fibre specialist, (name). Within the context of ‘smart', material development and experimentation, Digital lace exploits and amalgamates the responsive technologies of dye and fibre with digital-control.
Show images
Oiko-Nomic Threads
Oiko-nomic Threads is a collective art project for an algorithmically controlled knitting machine and open data. The installation represents a system commenting on the notion of work through the production of a textile in real-time. By means of rethinking, modifying and redening the functionality of an obsolete knitting machine and employing nancial data from the databases of the Greek National Manpower Employment Oces as well as selected patterns inspired by Greek folk art, a textile is generated algorithmically. This way, the woven textile is to be understood as both a document of its own making as well as a dynamic base of archival resources which presents a computer-generated interpretation of the original nancial data.
Fiori in Aria
Indoor air pollution can provoke temporary uneasiness, headhache, sometimes sore throats or burning eyes and noses, but in the long term it can cause serious health problems both for young people, for the elderly and for those with existing diseases. It's easy to understand that knowing the quality of the air we are breathing is valuable. But most of all, having an easy readable object that shows you if you are in an unhealthy situation can simplify the task. A textile flower that opens and closes if the air quality is good or not could be a pleasurable object to wear and a indicator of the air quality.
Wednesday
Room
Seattle 1 & 2
Seattle 3
Emerald 2
09:00-10:30
Body Signals
Alanson Sample
Intelligent Sleep Stage Mining Service with Smartphones
Sleep quality plays a significant role in personal health. A great deal of effort has been paid to design sleep quality monitoring systems, providing services ranging from bedtime monitoring to sleep activity detection. However, as sleep quality is closely related to the distribution of sleep duration over different sleep stages, neither the bedtime nor the intensity of sleep activities is able to reflect sleep quality precisely. To this end, we present Sleep Hunter, a mobile service that provides a fine-grained detection of sleep stage transition for sleep quality monitoring and intelligent wake-up call. The rationale is that each sleep stage is accompanied by specific yet distinguishable body movements and acoustic signals. Leveraging the built-in sensors on smartphones, Sleep Hunter integrates these physical activities with sleep environment, inherent temporal relation and personal factors by a statistical model for a fine-grained sleep stage detection. Based on the duration of each sleep stage, Sleep Hunter further provides sleep quality report and smart call service for users. Experimental results from over 30 sets of nocturnal sleep data show that our system is superior to existing actigraphy-based sleep quality monitoring systems, and achieves satisfying detection accuracy compared with dedicated polysomnography-based devices.
Health Chair: Implicitly Sensing Heart and Respiratory Rate
People interact with chairs frequently, making them a potential location to perform implicit health sensing that requires no additional effort by users. We surveyed 550 participants to understand how people sit in chairs and inform the design of a chair that detects heart and respiratory rate from the armrests and backrests of the chair respectively. In a laboratory study with 18 participants, we evaluated a range of common sitting positions to determine when heart rate and respiratory rate detection was possible (32% of the time for heart rate, 52% for respiratory rate) and evaluate the accuracy of the detected rate (83% for heart rate, 73% for respiratory rate). We discuss the challenges of moving this sensing to the wild by evaluating an in-situ study totaling 40 hours with 11 participants. We show that, as an implicit sensor, the chair can collect vital signs data from its occupant through natural interaction with the chair.
Towards Circadian Computing: "Early to Bed and Early to Rise" Makes Some of Us Unhealthy and Sleep Deprived
We often think of ourselves as individuals with steady capabilities. However, converging strands of research indicate that this is not the case. Our biochemistry varies significantly over the course of a 24 hour period. Consequently our levels of alertness, productivity, physical activity, and even sensitivity to pain fluctuate throughout the day. This offers a considerable opportunity for the UbiComp community to identify novel measurements and interventions that can leverage these daily variations. To illustrate this potential, we present results from an empirical study with 9 participants over 97 days investigating whether such variations manifest in low-level smartphone use, focusing on daily rhythms related to sleep. Our findings demonstrate that phone usage patterns can be used to detect and predict individual daily variations indicative of temporal preference, sleep duration, and deprivation. We also identify opportunities and challenges for measuring and enhancing well-being using these simple and effective markers of circadian rhythms.
Heart Rate Monitoring through the Surface of a Drinkware
There is a growing demand for daily heart rate (HR) monitoring in the fields of healthcare, fitness, activity recognition, and entertainment. Although various HR monitoring systems have been proposed, most of these employ a wearable device, which may be a burden and disturb one's daily living. To achieve the goal of pervasive HR monitoring in our daily living, we present the HR monitoring method through the surface of a drinkware. The proposed method employs the surface of a drinkware as a broad sensing region, by expanding the principal of a basic photo-based HR sensor. The sensing surface works even with a curved shape, and it can be applied on various types of drinkwares. This approach enables unobtrusive HR monitoring during the beverage consumption. As a prototype, we implemented the proposed method on an ordinary transparent tumbler, and evaluated its HR monitoring performance.
Industry panel
Florian Michahelles, Siemens Corporation
Transitioning from ubiquitous and wearable computing research to business practice
The research communities of ubicomp and ISWC researchers have been anticipating various trends, such as wearable technologies, hands-free interfaces, bring-your-own device, and navigation systems, by more than a decade ago. Prototypes once evaluated in user studies with 20 students get downloaded as an app, activity recognition algorithms can be sourced in chipsets, and hardware prototyping platforms become available as smart thing infrastructures. Whereas consumer-focused industries may benefit from these trends more directly, also professional domains in industry are starting to adapt ubicomp and wearable technologies.
It is the goal of this panel to collect use cases of successful transitions from research to practice, to understand the challenges of moving from research to product, and to identify open research question yet to be solved.
The panel brings a number of experts from the fields together to discuss
- sample cases of ubiquitous and wearable computing research results taking effect in industry,
- ingredients of successful transition from research to practice,
- challenges of turning research prototypes into a products,
- how research generates impact on practice.
Sensing the Crowd
Nic Lane
Steered Crowdsensing: Incentive Design towards Quality-Oriented Place-Centric Crowdsensing
Crowdsensing technologies are rapidly evolving and are expected to be utilized on commercial applications such as location-based services. Crowdsensing collects sensory data from daily activities of users without burdening users, and the data size is expected to grow into a population scale. However, quality of service is difficult to ensure for commercial use. Incentive design in crowdsensing with monetary rewards or gamifications is, therefore, attracting attention for motivating participants to collect data to increase data quantity. In contrast, we propose Steered Crowdsensing, which controls the incentives of users by using the game elements on location-based services for directly improving the quality of service rather than data size. For a feasibility study of steered crowdsensing, we deployed a crowdsensing system focusing on application scenarios of building processes on wireless indoor localization systems. In the results, steered crowdsensing realized deployments faster than non-steered crowdsensing while having half as many data.
CrowdRecruiter: Selecting Participants for Piggyback Crowdsensing under Probabilistic Coverage Constraint
This paper proposes a novel participant selection framework, named CrowdRecruiter, for mobile crowdsensing. CrowdRecruiter operates on top of energy-efficient Piggyback Crowdsensing (PCS) task model and minimizes incentive payments by selecting a small number of participants while still satisfying probabilistic coverage constraint. In order to achieve the objective when piggybacking crowdsensing tasks with phone calls, CrowdRecruiter first predicts the call and coverage probability of each mobile user based on historical records. It then efficiently computes the joint coverage probability of multiple users as a combined set and selects the near-minimal set of participants, which meets coverage ratio requirement in each sensing cycle of the PCS task. We evaluated CrowdRecruiter extensively using a large-scale real-world dataset and the results show that the proposed solution significantly outperforms three baseline algorithms by selecting 10.0% - 73.5% fewer participants on average under the same probabilistic coverage constraint.
Diagnosing New York City's Noises with Ubiquitous Data
Orchestration Support for Participatory Sensing Campaigns
In this paper we argue the need for orchestration support for participatory campaigns to achieve campaign quality, and automatisation of said support to achieve scalability, both issues contributing to stakeholder usability. This goes further than providing support for defining campaigns, an issue tackled in prior work. We provide a formal definition for a campaign by extracting commonalities from the state of the art and expertise in organising noise mapping campaigns. Next, we formalise how to ensure campaigns end successfully, and translate this formal notion into an operational recipe for dynamic orchestration. We then present a framework for automatising campaign definition, monitoring and orchestration which relies on workflow technology. The framework is validated by re-enacting several campaigns previously run through manual orchestration and quantifying the increased efficiency.
10:30-11:00
Break
11:00-12:30
Security
Alastair Beresford
Secure Bootstrapping of Cloud-Managed Ubiquitous Displays
Secure and Private Proofs for Location-Based Activity Summaries in Urban Areas
Activity-based social networks, where people upload and share information about their location-based activities (e.g., the routes of their activities), are increasingly popular. Such systems, however, raise privacy and security issues: The service providers know the exact locations of their users; the users can report fake location information in order to, for example, unduly brag about their performance. In this paper, we propose a secure privacy-preserving system for reporting location-based activity summaries (e.g., the total distance covered and the elevation gain). Our solution is based on a combination of cryptographic techniques and geometric algorithms, and it relies on existing Wi-Fi access-point networks deployed in urban areas. We evaluate our solution by using real data sets from the FON community networks and from the Garmin Connect activity-based social network, and we show that it can achieve tight (up to a median accuracy of 76%) verifiable lower-bounds of the distance covered and of the elevation gain, while protecting the location privacy of the users with respect to both the social network operator and the access-point network operator(s).
Zero-Effort Payments: Design, Deployment, and Lessons
This paper presents Zero-Effort Payments (ZEP), a seamless mobile computing system designed to accept payments with no effort on the customer’s part beyond a one-time opt-in. With ZEP, customers need not present cards nor operate smartphones to convey their identities. ZEP uses three complementary identification technologies: face recognition, proximate device detection, and human assistance. We demonstrate that the combination of these technologies enables ZEP to scale to the level needed by our deployments. We designed and built ZEP, and demonstrated its usefulness across two real-world deployments lasting five months of continuous deployment, and serving 274 customers. The different nature of our deployments stressed different aspects of our system. These challenges led to several system design changes to improve scalability and fault-tolerance.
SmudgeSafe: Geometric Image Transformations for Smudge-resistant User Authentication
Touch-enabled user interfaces have become ubiquitous, such as on ATMs or portable devices. At the same time, authentication using touch input is problematic, since finger smudge traces may allow attackers to reconstruct passwords. We present SmudgeSafe, an authentication system that uses random geometric image transformations, such as translation, rotation, scaling, shearing, and flipping, to increase the security of cued-recall graphical passwords. We describe the design space of these transformations and report on two user studies: A lab-based security study involving 20 participants in attacking user-defined passwords, using high quality pictures of real smudge traces captured on a mobile phone display; and an in-the-field usability study with 374 participants who generated more than 130,000 logins on a mobile phone implementation of SmudgeSafe. Results show that SmudgeSafe significantly increases security compared to authentication schemes based on PINs and lock patterns, and exhibits very high learnability, efficiency, and memorability.
Assistive devices
Janet van der Linden
Passive Haptic Learning of Braille Typing
Passive Haptic Learning (PHL) is the acquisition of sensorimotor skills without active attention to learning. One method is to "teach" motor skills using vibration cues delivered by a wearable, tactile interface while the user is focusing on another, primary task. We have created a system for Passive Haptic Learning of typing skills. In a study containing 16 participants, users demonstrated significantly reduced error typing a phrase in Braille after receiving passive instruction versus control (32.85% average decline in error vs. 2.73% increase in error). PHL users were also able to recognize and read more Braille letters from the phrase (72.5% vs. 22.4%). In a second study, containing 8 participants thus far, we passively teach the full Braille alphabet over four sessions. Typing error reductions in participants receiving PHL were more rapid and consistent, with 75% of PHL vs. 0% of control users reaching zero typing error. By the end of the study, PHL participants were also able to recognize and read 93.3% of all Braille alphabet letters. These results suggest that Passive Haptic instruction facilitated by wearable computers may be a feasible method of teaching Braille typing and reading.
An Assistive EyeWear Prototype that interactively converts 3D Object Locations into Spatial Audio
We present an end-to-end prototype for an assistive EyeWear system aimed at Vision Impaired users. The system uses computer vision to detect objects on planar surfaces and sonifies their 3D locations using spatial audio. A key novelty of the system is that it operates in real time (15Hz), allowing the user to interactively affect the audio feedback by actively moving a headworn sensor. A quantitative user study was conducted on 12 blindfolded subjects performing an object localisation and placement task using our system. This detailed study of near field interactive spatial audio for users operating at around arm's length departs from existing studies focused on far-field audio and non-interactive systems. The object localisation accuracy achieved on naive users suggests that the EyeWear prototype has a lot of potential as a real world assistive device. User feedback collected from exit surveys and mathematical modelling of user errors provide several promising avenues to further improve system performance.
CrossNavi: Enabling Real-time Crossroad Navigation for the Blind with Commodity Phones
Crossroad is among the most dangerous parts outside for the visually impaired people. Numerous studies have exploited navigating systems for the visually impaired community, providing services ranging from block detection, route planning to realtime localization. However, none of them have addressed the safety issue in crossroad and integrated three key factors necessary for a practical crossroad navigation system: detecting the crossroad, locating zebra patterns, and guiding the user within zebra crossing when passing the road. Our CrossNavi application responds to these needs, providing an integrated crossroad navigation service that incorporates all the essential functionalities mentioned above. The overall service is fulfilled by the collaboration of built-in sensors on commodity phones, and requires minimal human participation. We describe the technical aspects of its design, implementation, interface, and further improvements to make the system practical on a wider basis. Experimental results from three visually impaired volunteers show that the system exhibits promising behavior in both urban and rural areas.
Chroma: A Wearable Augmented-Reality Solution for Color Blindness
Color blindness is a highly prevalent vision impairment that inhibits people's ability to understand colors. Although classified as a mild disability, color blindness has important effects on the daily activity of people, preventing them from performing their tasks in the most natural and effective ways. In order to address this issue we developed Chroma, a wearable augmented-reality system based on Google Glass that allows users to see a filtered image of the current scene in real-time. Chroma automatically adapts the scene-view based on the type of color blindness, and features dedicated algorithms for color saliency. Based on interviews with 23 people with color blindness we implemented four modes to help colorblind individuals distinguish colors they usually can't see. Although Glass still has important limitations, initial tests of Chroma in the lab show that colorblind individuals using Chroma can improve their color recognition in a variety of real-world activities. The deployment of Chroma on a wearable augmented-reality device makes it an effective digital aid with the potential to augment everyday activities, effectively providing access to different color dimensions for colorblind people.
UbiComp at Work
Nigel Davies
The architecture of innovation: Tracking face-to-face interactions with ubicomp technologies
The layouts of the buildings we live in shape our everyday lives. In office environments, building spaces affect employees' communication, which is crucial for productivity and innovation. However, accurate measurement of how spatial layouts affect interactions is a major challenge and traditional techniques may not give an objective view. We measure the impact of building spaces on social interactions using wearable sensing devices. We study a single organization that moved between two different buildings, affording a unique opportunity to examine how space alone can affect interactions. The analysis is based on two large scale deployments of wireless sensing technologies: short-range, lightweight RFID tags capable of detecting face-to-face interactions. We analyze the traces to study the impact of the building change on social behavior, which represents a first example of using ubiquitous sensing technology to study how the physical design of two workplaces combines with organizational structure to shape contact patterns.
Lunch Line: Using Public Displays and Mobile Devices to Encourage Healthy Eating in an Organization
In this paper, we explore using large digital displays in combination with a personal mobile application to publicly and privately encourage people to make healthy choices. We designed, built, and deployed an experimental system called Lunch Line that promoted healthy eating. Lunch Line includes a public display that enables passersby to view the reported eating behavior of a group of people and take on daily "food challenges," and a mobile web application that allows users to record personal food choices, report challenge achievement, and compare their choices with other users and with USDA recommendations. Results from a 3-week field evaluation at a company cafeteria showed that our integrated system was effective in drawing public attention, delivering challenges, enabling self-tracking and self-reflection, and providing feedback on personal and group choices. We share lessons on how to design future systems that integrate situated public displays and personal mobile devices to encourage healthy choices.
Exploring Delegate Engagement with an Augmented Conference
We describe a qualitative study of delegate engagement with technology in academic conferences through a large- scale deployment of prototype technologies. These deployments represent current themes in conference technologies, such as providing access to content and opportunities for socialising between delegates. We consider not just the use of individual technologies, but also the overall impact of an assemblage of interfaces, ranging from ambient to interactive and mobile to situated. Based on a two-week deployment followed by interviews and surveys of attendees, we discuss the ways in which delegates engaged with the prototypes and the implications this had for their experience of the conferences. From our findings, we draw three new themes to inform the development of future conference technologies.
Container Throughput Estimation Leveraging Ship GPS Traces and Open Data
12:30-14:00
Lunch
14:00-15:30
Children's Therapy
Hao-Hua Chu
Robot-based Augmentative and Alternative Communication for Nonverbal Children with Communication Disorders
Nonverbal children with communication disorders have difficulties communicating through oral language. To facilitate communication, Augmentative and Alternative Communication (AAC) is commonly used in intervention settingss. Different forms of AAC have been used; however, one key aspect of AAC is that children have different preferences and needs in the intervention process. One particular AAC method does not necessarily work for all children. Although robots have been used in different applications, this is one of the first times that robots have been used for improvement of communication in nonverbal children. In this work, we explore robot-based AAC through humanoid robots that assist therapists in interventions with nonverbal children. Through playing activities, our study assessed changes in gestures, vocalization, speech, and verbal expression in children. Our initial results show that robot-based AAC intervention has a positive impact on the communication skills of nonverbal children.
Moving Towards a Real-Time System for Automatically Recognizing Stereotypical Motor Movements in Individuals on the Autism Spectrum Using Wireless Accelerometry
This paper extends previous work automatically detecting stereotypical motor movements (SMM) in individuals on the autism spectrum. Using three-axis accelerometer data obtained through wearable wireless sensors, we compare recognition results for two different classifiers ’ Support Vector Machine and Decision Tree ’ in combination with different feature sets based on time-frequency characteristics of accelerometer data. We use data collected from six individuals on the autism spectrum who participated in two different studies conducted three years apart in classroom settings, and observe an average accuracy across all participants over time ranging from 81.2% (TPR: 0.91; FPR: 0.21) to 99.1% (TPR: 0.99; FPR: 0.01) for all combinations of classifiers and feature sets. We also provide analyses of kinematic parameters associated with observed movements in an attempt to explain classifier-feature specific performance. Based on our results, we conclude that real-time, person-dependent, adaptive algorithms are needed in order to accurately and consistently measure SMM automatically in individuals on the autism spectrum over time in real-word settings.
SensoryPaint: A Multimodal Sensory Intervention for Children with Neurodevelopmental Disorders
Multimodal and natural user interfaces offer an innovative approach to sensory integration therapies. We designed and developed SensoryPaint, a multimodal system that allows users to paint on a large display using physical objects, body-based interactions, and interactive audio. We evaluat-ed the impact of SensoryPaint through two user studies: a lab-based study of 15 children with neurodevelopmental disorders in which they used the system for up to one hour, and a deployment study with four children with autism, during which the system was integrated into existing daily sensory therapy sessions. Our results demonstrate that a multimodal large display, using whole body interactions combined with tangible interactions and interactive audio feedback, balances children’s attention between their own bodies and sensory stimuli, augments existing therapies, and promotes socialization. These results offer implications for the design of other ubicomp systems for children with neurodevelopmental disorders and for their integration into therapeutic interventions.
Collective use of a Situated Display to Encourage Positive Behaviors in Children with Behavioral Challenges
Situated displays can support behavior management for children with behavioral challenges. However, existing tools are often static, rarely engaging, and tend to focus only on individual behavior. In this work, we designed and deployed a situated display to support teamwork and cooperation in children with behavioral challenges. We evaluated this tool in two classrooms of a public school specializing in behavioral interventions with 28 children over four weeks. The results of this work demonstrate that situated displays focused on collective behavioral performance can support reflection on individual performance, improve behavior for students with behavioral challenges, as well as encourage teamwork and cooperative behavior in classrooms. These results also indicate a variety of issues to be considered when designing situated displays for these environments, including considerations for the representation of ambiguity and failure as well as the relationship between novelty and engagement.
Interruptability & Notifications
Hans Gellersen
InterruptMe: Designing Intelligent Prompting Mechanisms for Pervasive Applications
The mobile phone represents a unique platform for interactive applications that can harness the opportunity of an immediate contact with a user in order to increase the impact of the delivered information. However, this accessibility does not necessarily translate to reachability, as recipients might refuse an initiated contact or disfavor a message that comes in an inappropriate moment. In this paper we seek to answer whether, and how, suitable moments for interruption can be identified and utilized in a mobile system. We gather and analyze a real-world smartphone data trace and show that users' broader context, including their activity, location, time of day, emotions and engagement, determine different aspects of interruptibility. We then design and implement InterruptMe, an interruption management library for Android smartphones. An extensive experiment shows that, compared to a context-unaware approach, interruptions elicited through our library result in increased user satisfaction and shorter response times.
Assessing the Availability of Users to Engage in Just-in-Time Intervention in the Natural Environment
Wearable wireless sensors for health monitoring are enabling the design and delivery of just-in-time interventions (JITI). Critical to the success of JITI is to time its delivery so that the user is available to be engaged. We take a first step in modeling users' availability by analyzing 2,064 hours of physiological sensor data and 2,717 self-reports collected from 30 participants in a week-long field study. We use delay in responding to a prompt to objectively measure availability. We compute 99 features and identify 30 as most discriminating to train a machine learning model for predicting availability. We find that location, affect, activity type, stress, time, and day of the week, play significant roles in predicting availability. We find that users are least available at work and during driving, and most available when walking outside. Our model finally achieves an accuracy of 74.7% in 10-fold cross-validation and 77.9% with leave-one-subject-out.
Geofencing 2.0: Taking Location-based Notifications to the Next Level
Recently, Location-based Services (LBS) became proactive by supporting smart notifications in case the user enters or leaves a specific geographical area, well-known as Geofencing. However, different geofences cannot be temporally related to each other. Therefore, we introduce a novel method to formalize sophisticated Geofencing scenarios as state and transition-based geofence models. Such a model considers temporal relations between geofences as well as duration constraints for the time being within a geofence or in transition between geofences. These are two highly important aspects in order to cover sophisticated scenarios in which a notification should be triggered only in case the user crosses multiple geofences in a defined temporal order or leaves a geofence after a certain amount of time. As a proof of concept, we introduce a prototype of a suitable user interface for designing complex geofence models in conjunction with the corresponding proactive LBS.
Large-Scale Evaluation of Call Availability Prediction
We contribute evidence to which extent sensor- and contextual information available on mobile phones allow to predict whether a user would pick up a call or not. Using an app publicly available for Android phones, we logged anonymous data from 31311 calls of 418 different users. The data shows that information easily available in mobile phones, such as the time since the last call, the time since the last ringer mode change, or the device posture, can predict call availability with an accuracy of 83.2% (Kappa = .646). Personalized models can increase the accuracy to 87% on average. Features related to when the user was last active turned out to be strong predictors. This shows that simple contextual cues approximating user activity are worthwhile investigating when designing context-aware ubiquitous communication systems.
Cars & Driving
Gerd Kortuem
Car-level Congestion and Position Estimation for Railway Trips Using Mobile Phones
We propose a method to estimate car-level train congestion using Bluetooth RSSI observed by passengers' mobile phones. Our approach employs a two-stage algorithm where car-level location of passengers is estimated to infer car-level train congestion. We have learned Bluetooth signals attenuate due to passengers' bodies, distance and doors between cars through the analysis of over 50,000 Bluetooth real samples. Based on this prior knowledge, our algorithm is designed as a Bayesian-based likelihood estimator, and is robust to the change of both passengers and congestion at stations. The car-level positions are useful for passengers' personal navigation inside stations and car-level train congestion information helps determine better strategies of taking trains. Through a field experiment, we have confirmed the algorithm can estimate the location of 16 passengers with 83% accuracy and also estimate train congestion with 0.82 F-measure value in average.
Modeling Heterogeneous Routing Decisions in Trajectories for Driving Experience Learning
Road latent cost, which quantifies how desirable each road is for traveling, is important information to enable many smart-city applications such as route recommendation. Arguably, vehicle trajectories are a good source to learn these costs as drivers intelligently incorporate them into their routing decisions. However, major past approaches misinterpret drivers' behaviors and suffer from trajectory sparsity problem, mainly because they adopt an edge-centric perspective which fails to exploit the sequential information in the entire trajectories. To address these shortcomings, we model drivers' routing decision process which targets at global path optimality, and present a framework to reliably discover those costs by exploiting entire trajectories while isolating the influence of heterogeneous destinations. Extensions are also made to address several issues in practice. Extensive experiments on real world data show that the road costs learned in this way significantly outperform past approaches in several urban computing tasks and require less data for learning.
PocketParker: Pocketsourcing Parking Lot Availability
Searching for parking spots generates frustration and pollution. To address these parking problems, we present PocketParker, a crowdsourcing system using smartphones to predict parking lot availability. PocketParker is an example of a subset of crowdsourcing we call pocketsourcing. Pocketsourcing applications require no explicit user input or additional infrastructure, running effectively without the phone leaving the user's pocket. PocketParker detects arrivals and departures by leveraging existing activity recognition algorithms. Detected events are used to maintain per-lot availability models and respond to queries. By estimating the number of drivers not using PocketParker, a small fraction of drivers can generate accurate predictions. Our evaluation shows that PocketParker quickly and correctly detects parking events and is robust to the presence of hidden drivers. Camera monitoring of several parking lots as 105 PocketParker users generated 10,827 events over 45 days shows that PocketParker was able to correctly predict lot availability 94% of the time.
Elastic Pathing: Your Speed is Enough to Track You
Today people have the opportunity to opt-in to usage-based automotive insurances for reduced premiums by allowing companies to monitor their driving behavior. Several companies claim to measure only speed data to preserve privacy. With our elastic pathing algorithm, we show that drivers can be tracked by merely collecting their speed data and knowing their home location, which insurance companies do, with an accuracy that constitutes privacy intrusion. To demonstrate the algorithm's real-world applicability, we evaluated its performance with datasets from central New Jersey and Seattle, Washington, representing suburban and urban areas. Our algorithm predicted destinations with error within 250 meters for 14% traces and within 500 meters for 24% traces in the New Jersey dataset (254 traces). For the Seattle dataset (691 traces), we similarly predicted destinations with error within 250 and 500 meters for 13% and 26% of the traces respectively. Our work shows that these insurance schemes enable a substantial breach of privacy.
15:30-16:00
Break
16:00-17:30
Open Data Kit: Applications of Mobile Devices in the Developing World
Click here for more about this keynote.