Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 06/10/2020
Room #1

Unconference time 10:00 - 10:30

Please see email or Slack for information about drop-in sessions

Welcome address from Organizing Committee 10:30 - 10:45

Atlanta time zone

Welcome message from Conference Manager and EAI 10:45 - 11:00

Keynote Address: #WeAreNotWaiting (and neither should you) 11:00 - 11:50

Dana Lewis, founder of the Open Source Artificial Pancreas System discusses the OpenAPS movement

Health & Families 12:00 - 13:20

Four full presentations addressing issues of health technologies within the context of Families
12:00 - 12:00
Supporting Caring among Intergenerational Family Members through Family Fitness Tracking

We present results from a qualitative study involving eight intergenerational families (27 participants) to understand how a family tracking intervention can help support care among intergenerational family members. Our findings show that family members communicate and stay aware of each other’s’ health through shared fitness data and conversations triggered by fitness sharing. We identified different challenges and preferences among the three age groups in our study: older adults enjoyed family fitness sharing but often encountered various technical challenges, the middle-aged group served as a key person to care for the rest of the family members, and the young generation could not fully engage in fitness sharing due to their busy schedule and privacy concerns. These findings suggest the design of family fitness sharing to account for the age differences in intergenerational families and support the unique needs of family fitness sharing.
Authors: Qingyang Li (University of California, Irvine), Clara Caldeira (University of California, Irvine), Daniel Epstein (University of California, Irvine), Yunan Chen (University of California Irvine),
Hide Authors & Abstract

Show Authors & Abstract
12:20 - 12:40
Design Space Analysis of Health Technologies for Families: A Systematic Review

Diverse disciplines, including Human-Computer Interaction have explored how health technologies can support families in dealing with health conditions and in promoting healthy living. With the changing of family structures and the increase of variety in family backgrounds, however, there is still a need to understand the extent which existing studies have addressed family health needs by proposing technological solutions. In this paper, we present a systematic review of the literature in order to see which family health topics have been researched extensively or not, and to identify hidden aspects and opportunities for family-centered health technology research. We had a final sample of 55 papers from diverse sources in this process. Our findings highlight characteristics of the studies, families, and health design. We also describe existing technological solutions and evaluation measures. Based on our findings, we discuss factors that were comprehensively studied and others that need further exploration in future research related to family-centered health technology.
Authors: Jomara Sandbulte (Pennsylvania State University), Kathleen Byrd (Pennsylvania State University), Rachael Owens (Pennsylvania State University), John Carroll (Pennsylvania State University),
Hide Authors & Abstract

Show Authors & Abstract
12:40 - 13:00
Bodeum: Encouraging Working Parents to Provide Emotional Support for Stay-at-Home Parents in Korea

Although gender equality is commonly found globally, many countries in Asia still show stereotypical gender roles within family relationships between fathers and mothers. In those countries, most stay-at-home mothers are mainly responsible for childcare and housework while fathers work so that some stay-at-home mothers are highly stressed by single childcare. To relieve their parenting stress, emotional support from their spouse is an important factor. However, working parents in single-income families tend to underestimate the childcare difficulties of their spouses. In this work, we propose Bodeum, a proof-of-concept mobile system to facilitate spousal communication by sharing stay-at-home parent’s stress level, their childcare activities, and their baby’s status with working parents to encourage emotional support for stay-at-home parents. A 2-week feasibility study with nine families in South Korea suggests that Bodeum enhanced spousal communication about parenting stress and showed potential for parenting mothers to lower their perceived parenting stress.
Authors: seokwoo song (SAMSUNG RESEARCH), Naomi Yamashita (NTT Communication Science Laboratories, Soraku-gun, Kyoto, Japan), John Kim (KAIST),
Hide Authors & Abstract

Show Authors & Abstract
13:00 - 13:20
Sociotechnical Design Opportunities for Pervasive Family Sleep Technologies

Getting the right amount of high quality sleep is crucial for overall health and wellbeing, and pervasive and ubiquitous computing technologies have shown promise for allowing individuals to track and manage their sleep quality. However, sleep technology research has traditionally focused on individual-level solutions. In this paper, we elucidate social requirements for family sleep technologies. We take a family informatics approach to sleep, through an in-home interview study with 10 families with young children. We describe families’ current practices, values, and perceived role for technology, showing that sleep technology has many opportunities beyond individual-level tracking. We also provide design dimensions and implications for family-based sleep technologies, especially the potential for technologies that support family activities and rituals, encourage children’s independence, and provide comfort.
Authors: Anna Cherenshchykova (IUPUI), Andrew Miller (IUPUI),
Hide Authors & Abstract

Show Authors & Abstract

Short Presentations 13:30 - 14:30

Nine short presentations reflecting a range of innovative work
13:30 - 13:35
Understanding Reflection Needs for Personal Health Data in Diabetes

To empower users of wearable medical devices, it is important to enable methods that facilitate reflection on previous care to improve future outcomes. In this work, we conducted a two-phase user-study involving patients, caregivers, and clinicians to understand gaps in current approaches that support reflection and user needs for new solutions. Our results show that users desire to have 'specific summarization metrics', 'solutions that minimize cognitive effort', and 'solutions that enable data integration' to support meaningful reflection on diabetes management. In addition, we developed and evaluated a visualization called PixelGrid that presents key metrics in a matrix-based plot. Majority of users (84\%) found the matrix-based approach to be useful for identifying salient patterns related to certain times and days in blood glucose data. Through our evaluation we identified that users desire data visualization solutions with complementary textual descriptors, 'concise and flexible' presentation, 'contextually-fitting' content, and 'informative and actionable' insights. Directions for future research on tools that automate pattern discovery, detect abnormalities, and provide recommendations to improve care were also identified.
Authors: Temiloluwa Prioleau (Dartmouth College), Ashutosh Sabharwal (Rice University), Madhuri Vasudevan (Baylor College of Medicine),
Hide Authors & Abstract

Show Authors & Abstract
13:35 - 13:40
Data-Driven Implications for Translating Evidence-Based Psychotherapies into Technology-Delivered Interventions

Mobile mental health interventions have the potential to reduce barriers and increase engagement in psychotherapy. However, most current tools fail to meet evidence-based principles. In this paper, we describe data-driven design implications for translating evidence-based interventions into mobile apps. To develop these design implications, we analyzed data from a month-long field study of an app designed to support dialectical behavioral therapy, a psychotherapy that aims to teach concrete coping skills to help people better manage their mental health. We investigated whether particular skills are more or less effective in reducing distress or emotional intensity. We also characterized how an individual's disorders, characteristics, and preferences may correlate with skill effectiveness, as well as how skill-level improvements correlate with study-wide changes in depressive symptoms. We then developed a model to predict skill effectiveness. Based on our findings, we present design implications that emphasize the importance of considering different environmental, emotional, and personal contexts. Finally, we discuss promising future opportunities for mobile apps to better support evidence-based psychotherapies, including using machine learning algorithms to develop personalized and context-aware skill recommendations.
Authors: Jessica Schroeder (University of Washington), Jina Suh (University of Washington, Microsoft Research), Chelsey Wilks (Harvard University), Mary Czerwinski (Microsoft Research), Sean Munson (University of Washington), James Fogarty (University of Washington), Tim Althoff (University of Washington),
Hide Authors & Abstract

Show Authors & Abstract
13:40 - 13:45
The Thought Journal App: Designed to confront thoughts that influence sleep

Problems initiating or maintaining sleep are prevalent and impact the quality of life negatively. Negative thinking patterns may perpetuate insomnia by inducing a state of arousal and consequently disrupting sleep. ‘Thought challenging’ is a common strategy to adopt a positive and peaceful mindset, but requires high awareness to internalize rational reasoning. Regular self-report and feedback may support the acquisition of fundamental reflection skills. We developed a thought journal in a mobile app to facilitate thought challenging. With the app, the users can reflect on daily situations and get visualized summaries as feedback. We carried out one week trial to explore perceived benefit, motivation, user engagement, and its integration with a sleep support tool. The results showed that using the app improved self-reflection skills and visualized summaries are perceived as motivating to log thoughts.
Authors: Begum Erten Uyumaz (Eindhoven University of Technology), Umut Uyumaz (Eindhoven University of Technology), Mili Docampo Rama (Philips Design), Sebastiaan Overeem (Kempenhaeghe Sleep Medicine Research Centre), Jun Hu (Eindhoven University of Technology), Loe Feijs (Eindhoven University of Technology),
Hide Authors & Abstract

Show Authors & Abstract
13:45 - 13:50
Emotional Alignment Between Older Adults and Online Personalities: Implications for Assistive Technologies

We elicited the emotional ratings of 22 older adults (>50 yrs) to a visual presentation of a set of six manually curated online seller personalities, taken from the world wide web and homogenized (filtered and cleaned). We found significant correlations between the ratings the participants provided about the seller's emotional self (and their own), and their tendency to buy a generic memory product from the same seller. We further found a correlation between the variance in the ratings of sellers and the tendency to buy. Overall the paper shows that the sentiments portrayed by online memory supplement sellers is a significant element in the marketability of the product. This has implications for the design and deployment of effective eHealth resources, as well as for development of emotionally aligned online presences and virtual assistants for older adults seeking to live more independently in the face of memory impairments such as Alzheimer's.
Authors: Moojan Ghafurian (University of Waterloo), Jesse Hoey (University of Waterloo), Daniel Tchorni (University of Waterloo), Annika Ang (University of British Columbia), Mallorie Tam (University of British Columbia), Julie Robillard (University of British Columbia),
Hide Authors & Abstract

Show Authors & Abstract
13:50 - 13:55
Daily Journals : Extracting Insights for Well-being

Journals and diaries are the mediums through which individuals ex-press and self report their routines, daily activities and experiences.Analyzing such self reported activities from journals and diariesover a period of time uncovers significant activities that affectedthe individual’s sentiments. Such analysis, aids better self-reflectionand improvement, through a better understanding of events andactivities that affect her well-being. We present an automated tool,WEACT(Well-being-Emotions-ACTivities) to detect, extract andclassify one’s self reported activities and to gauge her sentimentfrom journal text using Natural Language Processing and DeepLearning techniques. This paper discusses the WEACT system andshowcases WEACT’s results through a study, where WEACT helpsto extract activities that have had a significant impact on the in-dividual’s sentiments in the study period. We believe, WEACT isthe first of its kind tool, provisioning automatic extraction of selfreported activities from text of journals and diaries with 92.84%precision and 71.8% recall. It classifies extracted activities with anoverall 70.16% precision and 76.6% recall. WEACT is able to un-cover study participants’ activities that significantly affected theiremotional valence with an accuracy of 74.6%. The system will bedeployed through mobile and web interfaces, that will enable usersto create journal entries anytime anywhere.
Authors: Deepa Adiga (Tata Consultancy Services), Maitry Bhavsar (Tata Consultancy Services), Unnati Palan (Tata Consultancy Services), Sachin Patel (Tata Consultancy Services),
Hide Authors & Abstract

Show Authors & Abstract
13:55 - 14:00
Laughter as a Controller in a Stress Buster Game

Laughter has been known to have therapeutic benefits ranging from reducing stress and inflammation in the short term to lowering cholesterol and blood pressure in the longer term. Studies have also shown that even faked laughter could provide some of these benefits. In this paper, we present the design and validation of a game, ``Laugh Out Loud'', in which laughter acts as the controller of the game mechanics. The goal of the game is to bloom a wilted flower by laughing. The primary components of this system are a laughter detector and a game interface. The laughter detector is a machine learning algorithm that analyses signals recorded by the microphone in real time and measures the intensity and duration of laughter. The game interface displays a wilted flower that starts blooming step by step as the player laughs, with a fully bloomed flower seen at the final level. Each level has an increasing level of difficulty, which means that the player has to laugh louder and longer for crossing the higher levels. The game interface is implemented as an Android app, with the intention of making the well-being intervention available anytime, anywhere. To validate the game, we conducted a study in which 48 participants were asked to play the game, one at a time, while seated alone in a closed room. 76.6% participants reported that they experienced reduced stress after playing the game. We present findings of this study and observations that could lead to some design improvements.
Authors: Gauri Deshpande (TCS Research; University of augsburg Germany), Sachin Patel (Tata Consultancy Service), Sushovan Chanda (TCS Research), Priti Patil (TCS Research), Vasundhara Agrawal (TCS Research), Bjorn Schuller (EIHW, University of Augsburg Germany; GLAM, Imperial College London UK),
Hide Authors & Abstract

Show Authors & Abstract
14:00 - 14:05
Multimodal fusion of IMUs and EPS body-worn sensors for scratch recognition

In order to develop and evaluate the extent to which itching affects a person’s daily life, it is useful to develop automated means to recognise the action of scratching. We present an investigation of sensors and algorithms to realise a wearable scratch detection device. We collected a dataset, where each user wore 4 inertial measurement unit (IMU) sensors and one electric potential sensor (EPS). Data were collected from nine users, where each user followed a 40-min protocol, which involved scratching different parts of head, shoulder, and leg, as well as other activities such as walking, drinking water, brushing teeth, and typing to a computer. The dataset contained 813 scratching instances and 5 h 15 min of recorded data. We investigated the trade-offs between the number of devices worn (comfort) and accuracy. We trained the k-NN and random forest algorithms by using between 1 and 5 features per channel. We concluded that a scratch could be detected with 80.7% accuracy by using the random forest algorithm on hand coordinates, which required four devices. However, an f1 score of 70% could be achieved with k-NN with IMU and EPS data, which only required one device. Moreover, the fusion of IMU data with EPS data improved the accuracy and reduced the deviation between the folds. This expanded the state-of-the-art method by opening up new trade-offs between accuracy and comfort for future research.
Authors: Zygimantas Jocys (University of Sussex), Arash Pouryazdan (University of Sussex), Daniel Roggen (University of Sussex),
Hide Authors & Abstract

Show Authors & Abstract
14:05 - 14:10
SleepApp: Providing Contextualized and Actionable SleepFeedback

Most commercial sleep sensors typically rely on population-leveldata and focus on recommendations based on objective metricssuch as sleep duration or sleep efficiency. However, there is inter-individual trait-variability to sleep and people’s sleep habits areindividualized. To prompt users to adopt habits that improve sleephealth, meaningful sleep feedback must not only provide evidenceof how users’ behaviors affect their sleep quality, as objectifiedby some of the metrics, but also show how carry-over effects ofsleep affect daytime cognitive function. In this paper, we proposeand validate an approach that combines both subjective and ob-jective measures of sleep, accounting for a person’s lifestyle andties it to meaningful and measurable carryover effects such as day-time alertness and working memory. Our approach is based on themedical community’s Ru-SATED framework, which characterizessleep through six dimensions: Regularity, Satisfaction, Alertness,Timing,Efficiency and Duration. Using data collected by a smartphone app: SleepApp, with a suite of ecological momentary assess-ment tests from 9 participants over 14 days, we demonstrate howsleep health can be contextualized to the individual lifestyle andactionable feedback can be generated. In a follow up survey with 57respondents, we show how the actionable feedback generated bySleepApp can encourage in users the intent to make adjustments totheir sleep habits that may impact their daytime cognitive function.
Authors: Ruth Ravichandran (University of Washington), Shwetak Patel (University of Washignton), Julie Kientz (University of Washington),
Hide Authors & Abstract

Show Authors & Abstract
14:10 - 14:15
Understanding Participant Needs for Engagement and Attitudes towards Passive Sensing in Remote Digital Health Studies

Digital psychiatry is a rapidly growing area of research. Mobile assessment, including passive sensing, could improve research into human behavior and may afford opportunities for rapid treatment delivery. However, retention is poor in remote studies of depressed populations in which frequent assessment and passive monitoring are required. To improve engagement and understanding participant needs overall, we conducted semi-structured interviews with 20 people representative of a depressed population in a major metropolitan area. These interviews elicited feedback on strategies for long-term remote research engagement and attitudes towards passive data collection. Our results found participants were uncomfortable sharing vocal samples, need researchers to take a more active role in supporting their understanding of passive data collection, and wanted more transparency on how data were to be used in research. Despite these findings, participants trusted researchers with the collection of passive data. They further indicated that long term study retention could be improved with feedback and return of information based on the collected data. We suggest that researchers consider a more educational consent process, giving participants a choice about the types of data they share in the design of digital health apps, and consider supporting feedback in the design to improve engagement.
Authors: Samantha Kolovson (University of Washington), Abhishek Pratap (Sage Bionetworks), Jaden Duffy (University of Washington), Ryan Allred (University of Washington), Sean Munson (University of Washington), Patricia Areán (University of Washington),
Hide Authors & Abstract

Show Authors & Abstract

Information Needs 14:30 - 16:00

Four full presentations presenting information needs related to technologies and online communities
14:30 - 14:50
Designing Everyday Conversational Agents for Managing Health and Wellness: A Study of Alexa Skills Reviews

Conversational agents have been developed for supporting a wide array of areas, including autonomous vehicles, decision making, and health behavior change. In the last few years, conversational agents increasingly became available as everyday technologies. This phenomenon enables opportunities for finding novel ways to support health and wellness in everyday contexts. By conducting a content analysis of 433 user reviews of Amazon Alexa’s Skills, the goal of this study is two-fold: (1) Extract users’ perceived strengths of conversational agents in everyday health and wellness management, (2) develop design heuristics for developing conversational agents for health and wellness. We found that the role of trustworthy content providers is critical during the adoption. The Skills enabled people to overcome logistical barriers to improving daily health and wellness routines. The findings also revealed the importance of transparency in the limitations of the Skill and how to better design command dialogues. We present the design heuristics of conversational agents, building on Nielsen’s Usability Heuristics, and discuss implications for designing conversational agents that support health and wellness.
Authors: Ji Youn Shin (Michigan State University),
Hide Authors & Abstract

Show Authors & Abstract
14:50 - 15:10
Adherence to Personal Health Devices: A Case Study in Diabetes Management

Personal health devices can enable continuous monitoring of health parameters. However, the benefit of these devices is often directly related to the frequency of use. Therefore, adherence to personal health devices is critical. This paper takes a data mining approach to study continuous glucose monitor use in diabetes management. We evaluate two independent datasets from a total of 44 subjects for 60 - 270 days. Our results show that: 1) missed target goals (i.e. suboptimal outcomes) is a factor that is associated with wearing behavior of personal health devices, and 2) longer duration of non-adherence, identified through missing data or data gaps, is significantly associated with poorer outcomes. More specifically, we found that up to 33% of data gaps occurred when users were in abnormal blood glucose categories. The longest data gaps occurred in the most severe (i.e. 'very low / very high') glucose categories. Additionally, subjects with poorly-controlled diabetes had longer average data gap duration than subjects with well-controlled diabetes. This work contributes to the literature on the design of context-aware systems that can leverage data-driven approaches to understand factors that influence non-wearing behavior. The results can also support targeted interventions to improve health outcomes.
Authors: Sudip Vhaduri (Fordham University), Temiloluwa Prioleau (Dartmouth College),
Hide Authors & Abstract

Show Authors & Abstract
15:10 - 15:30
Connections and Disconnections between Online Health Information Seeking and Offline Consequences

Online Health Information Seeking (HIS) has become pervasive with critical impacts on consumers' health. Yet, little is known about the connections between consumers' online HIS process and subsequent offline behaviors. To fill this gap, we conducted semi-structured interviews by adopting the Critical Incident Technique to understand the real-world search experiences from 24 consumers. We characterized the online HIS around source selection behaviors, information needs, and search starting-point, then further analyzed their impacts on offline emotion change and decision-making. Specifically, we identified that self-diagnosis is a common need for online HIS, where search engines are dominantly used as the starting point. More surprisingly, although mostly being viewed as helpful, online HIS might lead to consumers' extremely negative emotions and decisions. These findings deepen the understanding of consumer-centered health information seeking behaviors and provide insights for designing better interactive technologies to facilitate desirable online-offline transitions and thus promoting the outcomes of healthcare.
Authors: Yu Chi (University of Pittsburgh), Daqing He (University of Pittsburgh), Fanghui Xiao (University of Pittsburgh), Ning Zou (University of Pittsburgh),
Hide Authors & Abstract

Show Authors & Abstract
15:30 - 15:50
What to Expect When You are No Longer Expecting: Information Needs of Women who Experienced a Miscarriage

Even though miscarriages are a common experience, there remains a discrepancy between the information needed after a pregnancy is lost and the information received. We explored the reasons for this gap as part of an eight-week online study with 42 participants who experienced a miscarriage. Common online sources of information were forums, blogs, and Facebook. Participants were interested in general information about miscarriage, counselling resources, others’ experiences, and information from health care providers. Barriers to information access were both external (e.g., difficulty locating resources) and internal (e.g., self-blame or stigma). We map these information needs and barriers to a generalized miscarriage timeline crafted from participants’ individual experiences and discuss implications for the design of sociotechnical systems to support people through miscarriage and beyond.
Authors: K. Cassie Kresnye (Indiana University), Mona Alqassim (University of Edinburgh), Briana Hollins (Indiana University), Lucia Guerra-Reyes (Indiana University), Maria Wolters (University of Edinburgh), Katie Siek (Indiana University),
Hide Authors & Abstract

Show Authors & Abstract
Day 2 07/10/2020
Room #1

Unconference time 10:00 - 10:45

Please see email or Slack for information about drop-in sessions

Behavior change & messages 10:45 - 11:35

Three full presentations exploring behavior change and messaging in the context of physical activity and eating
10:45 - 11:00
Gym Usage Behavior & Desired Digital Interventions: An Empirical Study

Understanding individual’s exercise motives, participation patterns and reasons for dropout are essential for designing strategies to help gym-goers with long-term exercise adherence. In this work, we derive insights on various exercise-related behaviors of gym-goers, including evidence of a significant number of individuals exhibiting early dropout and also describing their attitudes towards digital technologies for sustained gym participation. By utilizing gym visitation data logs of 6513 individuals over a period of 16 months in a campus gym, we show the retention & dropout rates of gym-goers. Our data indicates that 32% of the people quit their gym activity after initial 1-2 visits and about 65% of the users have less than 10 visits during the study period. We also observed that people attending gym in a group have a lower chance of ceasing gym activity. Further by surveying 615 individuals of varying demographics, we uncover the key reasons for dropout to be "lack of knowledge in using gym equipment" & “lack of access to a personal trainer", besides the notable reason of “lack of time". Our survey also indicates the propensity of individuals towards using digital technologies to track their gym activity. Somewhat surprisingly, our survey reveals a disinclination among individuals to use obtrusive wearable-based solutions in a gym, with 60% of them preferring a less-invasive and more convenient approach of machine-attached sensors for automated tracking of gym exercises.
Authors: Meeralakshmi Radhakrishnan (Singapore Management University), Archan Misra (Singapore Management University), Rajesh Balan (Singapore Management University), Youngki Lee (Seoul National University, Korea),
Hide Authors & Abstract

Show Authors & Abstract
11:00 - 11:15
Design to Eat Smart! A Design Framework for Pervasive Interventions of Eating Habits

Seemingly trivial eating habits, such as eating too fast, has been,linked to diverse and rather serious health issues. While some technology-mediated interventions have promoted healthy dietary habits, designing successful pervasive interventions remains challenging. This paper contributes to the design of eating interventions in three ways: 1) a comprehensive review of 62 studies which focused on interventions targeting eating habits; 2) a generative design framework with multiple design parameters; 3) and, an exploration of the potential efficacy of the developed framework. These contributions will improve designers’ comprehension and ability to apply current trends and state of art technologies in the design space. The work presented here aims to validate the generative nature of our design framework presented in this paper and further propose new exploratory directions.
Authors: Zuoyi Zhang (University of Manitoba), Teng Han (Institute of Software, Chinese Academy of Sciences), John Swystun (University of Manitoba), Yumiko Sakamoto (University of Manitoba), Pourang Irani (University of Manitoba),
Hide Authors & Abstract

Show Authors & Abstract
11:15 - 11:35
"Enter Your Dinner Now!”: Uncovering Persuasive Message Attributes in Tracking Reminders that Motivate Logging

Continuous tracking of information is critical for meaningful self-reflection and self-monitoring, but people often forget to log their information in tracking devices. Research indicates that tracking reminders can successfully remind people to log their information, yet, little is known about what make reminders (in)effective. We extend prior work by identifying message attributes in tracking reminders that people find most effective in motivating them to log. To address this overarching research goal, we conducted two online studies where participants evaluated and designed tracking reminders. In Study 1, participants (N = 135) evaluated a set of tracking reminders for different behaviors (e.g., breakfast, weight) from popular fitness tracking apps on several dimensions such as the persuasiveness of each reminder. We found that participants liked reminders that were straightforward, encouraging, goal specific, and positive. In Study 2, participants (N = 100) designed a reminder for different behaviors (i.e., breakfast, lunch, dinner, weight, and exercise) that would successfully motivate them to log. Through thematic analysis of participants’ self-created reminders, we again found prominent message attributes that had emerged in Study 1 and also uncovered novel message attributes, including personalization, humor, and friend-like. Design implications are discussed in light of our findings.
Authors: Jin Kang (Pennsylvania State University), Lewen Wei (Pennsylvania State University),
Hide Authors & Abstract

Show Authors & Abstract

Poster Session 11:35 - 12:55

Please see Slack or Email for Drop-in Groups

Clinicians & Patients 12:55 - 13:50

Three full presentations consider providers and their interactions with patients
12:55 - 13:10
Design and Care for Discordant Chronic Comorbidities: A Comparison of Healthcare Providers’ Perspectives

Care and support of discordant chronic comorbidities (DCCs) are challenges not only for patients but also for their healthcare providers. DCCs are health conditions in which patients have multiple, often unrelated, chronic illnesses that may need to be addressed concurrently but may also be associated with conflicting treatment instructions. Previous studies show that patients with DCCs reported multiple challenges. Here, we conducted interviews (N = 8) and focus groups (N = 7) with healthcare providers to obtain providers’ perspectives. We compare the challenges and views reported by patients and healthcare providers. We suggest design guidelines and technology-mediated ways to address convergent and divergent issues between patients and providers. We recommend future exploration of strategies to simplify and better understand how treatment choices for one condition may impact another and how that exacerbates DCCs care costs.
Authors: Katherine Connelly (Indiana University), Tom Ongwere (University of Dayton), Gabrielle Cantor (Indiana University), Jame Clawson (Indiana University), Patrick Shih (Indiana University Bloomington),
Hide Authors & Abstract

Show Authors & Abstract
13:10 - 13:30
Assessing Clinicians’ Reliance on Computational Aids for Acute Stroke Diagnosis

The rapid rise of computational aids for stroke diagnosis have led to important concerns about clinicians developing an over-dependence on technology. Other studies have assessed reliance on clinical decision support systems in fields like diabetes, but no such study exists for stroke diagnosis. In this work, we developed a high-fidelity user interface for a computational aid designed to support acute ischemic stroke diagnosis. Engaging with stroke practitioners at the UCSD Stroke Center, we conducted an experiment to determine how technology for identifying stroke symptoms may affect their diagnostic decision-making processes. By assessing how clinicians changed their video-based diagnosis of stroke when provided with data visualizations and predictions from a machine learning tool, we observed that such computational aids do in fact affect clinicians' decisions but only in cases when the aid directly supports or contradicts their prior beliefs. Future computational aids for stroke diagnosis should focus on helping clinicians solidify their decisions rather than only providing them with overly quantitative information that may impede or confuse their judgement.
Authors: Vishwajith Ramesh (University of California, San Diego), Andrew Nguyen (University of California, San Diego), Kunal Agrawal (University of California, San Diego), Brett Meyer (University of California, San Diego), Gert Cauwenberghs (University of California, San Diego), Nadir Weibel (University of California, San Diego),
Hide Authors & Abstract

Show Authors & Abstract
13:30 - 13:50
"Oh, I didn’t do a good job": How objective data affects physiotherapist–patient conversations for arthritis patients

A physically active lifestyle consisting of moderate-to-vigorous physical activity and non-sedentary behaviour can significantly improve mobility and the quality of life for people with arthritis. During consultations with patients, physiotherapists rely on patients’ subjective feedback to understand their existing physical activity levels and physical ability. We developed a web application called FitViz, which allows physiotherapists and patients to use the physical activity data collected from Fitbit fitness trackers during consultations. We conducted a four-week study with 20 patients(inflammatory and knee osteoarthritis arthritis) and seven physio-therapists to evaluate the feasibility of FitViz, and understand the experiences of the physiotherapists and the patients. We used semi-structured interviews to understand how physiotherapists used FitViz, and if and how it changed the nature of their consultation. We found that the use of objective data allowed the physiotherapist–patient conversations to be patient-driven, and allowed goals to be realistic and data-driven. However, the use of objective data also caused the patients to feel guilty, which has implications on the useof pervasive healthcare technology in clinical settings.
Authors: Ankit Gupta (Simon Fraser University), Tim Heng (Simon Fraser University), Chris Shaw (Simon Fraser University), Diane Gromala (Simon Fraser University), Jenny Leese (University of British Columbia), Linda Li (University of British Columbia),
Hide Authors & Abstract

Show Authors & Abstract

Pervasive health across generations 13:50 - 14:40

Three full presentations examining generational issues in pervasive health from youth to older adults, and intergenerational issues
13:50 - 14:05
Exploring the Use of Electronics to Customize Pervasive Health Technologies with Older Adult Crafters

As the worldwide population ages, HCI researchers are designing technologies to better support older adults. We investigated how older adult crafters would customize technologies using electronics by building on their crafting skills. This supported them to explore customizing devices for themselves and advance the design of pervasive health technologies for older adults. We first conducted a survey of 42 older adult crafters to learn more about their crafting habits and gauge interest in technology and health tracking. We then conducted a participatory design workshop with 10 older adult crafters, focused on mutual learning to support them in prototyping how they would customize technology with maker electronics. They brainstormed customized devices around health, games, and safety, as well as aesthetically enhanced artifacts integrating electronics. We discuss how promoting older adult crafters to design and build customized pervasive health technologies impacts future research, and we provide guidelines on how to do so.
Authors: Ben Jelen (Indiana University), Olivia Richards (University of Michigan), Samantha Whitman (Arizona State University), Tom Ongwere (University of Dayton), K. Kresnye (Indiana University), Katie Siek (Indiana University),
Hide Authors & Abstract

Show Authors & Abstract
14:05 - 14:40
Exploring Player Experience of an Augmented Puzzle and Wearables for Studying Interactions between Parents and Children with Down Syndrome

Directive behaviors enable parents to continually guide their children's activities. Conventional methods for studying such behaviors include in-situ observations, video analysis, and questionnaires. Methods for studying directive behaviors in parent-child interactions using sensor technology have been little explored. In this sense, it is unclear whether such methods can include on-body artifacts such as gloves and augmented objects in children with Down syndrome. In this work, we explore game experience in parent-child dyads through an augmented puzzle and gloves. We evaluated game experience using the Wizard-of-Oz technique. The results of this work can be used for the design of augmented artifacts used for studying directive behaviors of parents of children with disabilities.
Authors: Adrian Macias (Sonora Institute of Technology), Karina Caro (Autonomous University of Baja California (UABC)), Luis A. Castro (Sonora Institute of Technology), Jose-Fernando Parra (Sonora Institute of Technology (ITSON)),
Hide Authors & Abstract

Show Authors & Abstract

Sensing & Sensors 14:40 - 15:25

Three full presentations exploring the use of sensors to contribute understanding in various health domains
14:40 - 14:55
Visualization as Intermediate Representations (VLAIR) for Human Activity Recognition

Ambient, binary, event-driven sensor data is useful for many human activity recognition applications such as smart homes and ambient-assisted living. These sensors are privacy-preserving, unobtrusive, inexpensive and easy to deploy in scenarios that require detection of simple activities such as going to sleep, and leaving the house. However, classification performance is still a challenge, especially when multiple people share the same space or when different activities take place in the same areas. To improve classification performance we develop what we call a Visualization as Intermediate Representations (VLAIR) approach. The main idea is to re-represent the data as visualizations (generated pixel images) in a similar way as how visualizations are created for humans to analyze and communicate data. Then we can feed these images to a convolutional neural network whose strength resides in extracting effective visual features. We have tested five variants (mappings) of the VLAIR approach and compared them to a collection of classifiers commonly used in classic human activity recognition. The best of the VLAIR approaches outperforms the best baseline, with strong advantage in recognising less frequent activities and distinguishing users and activities in common areas. We conclude the paper with a discussion on why and how VLAIR can be useful in human activity recognition scenarios and beyond.
Authors: Ai Jiang (University of St Andrews), Miguel A. Nacenta (University of St Andrews), Kasim Kasim Terzic (University of St Andrews), Juan Ye (University of St Andrews),
Hide Authors & Abstract

Show Authors & Abstract
14:55 - 15:05
Understanding Heavy Drinking at Night through Smartphone Sensing and Active Human Engagement

Heavy alcohol consumption can lead to many severe consequences. In this paper, we study the phenomenon of heavy drinking at night (4+ drinks for women or 5+ for men on a single evening), using a smartphone sensing dataset depicting about nightlife and drinking behaviors for 240 young adult participants. Our work has three contributions. First, we segment nights into moving and static episodes as anchors to aggregate mobile sensing features. Second, we show that young adults tend to be more mobile, have more activities, and attend more crowded areas outside home on heavy drinking nights compared to other nights. Third, we develop a machine learning framework to classify a given weekend night as involving heavy or non-heavy drinking, comparing automatically captured sensor features versus manually contributed contextual cues and images provided over the course of the night. Results show that a fully automatic approach with phone sensors results in an accuracy of 71%. In contrast, manual input of context of drinking events results in an accuracy of 70%; and visual features of manually contributed images produce an accuracy of 72%. This suggests that automatic sensing is a competitive approach.
Authors: Thanh-Trung Phan (Idiap Research Institute and EPFL), Florian Labhart (Idiap Research Institute and La Trobe University), Skanda Muralidhar (Idiap Research Institute and EPFL), Daniel Gatica-Perez (Idiap Research Institute and EPFL),
Hide Authors & Abstract

Show Authors & Abstract
15:05 - 15:25
Open Speech Platform: Democratizing Hearing Aid Research

Hearing aids help overcome the challenges associated with hearing loss, and thus greatly benefit and improve the lives of those living with hearing-impairment. Unfortunately, there is a lack of adoption of hearing aids among those that can benefit from hearing aids. Hearing researchers and audiologists are trying to address this problem through their research. However, the current proprietary hearing aid market makes it difficult for academic researchers to translate their findings into commercial use. In order to abridge this gap and accelerate research in hearing health care, we present the design and implementation of the Open Speech Platform (OSP), which consists of a co-design of open-source hardware and software. The hardware meets the industry standards and enables researchers to conduct experiments in the field. The software is designed with a systematic and modular approach to standardize algorithm implementation and simplify user interface development. We evaluate the performance of OSP regarding both its hardware and software, as well as demonstrate its usefulness via a self-fitting study involving human participants.
Authors: Dhiman Sengupta (University of California, San Diego), Tamara Zubatiy (Georgia Institute of Technology), Sean Hamilton (University of California, San Diego), Arthur Boothroyd (San Diego State University), Cagri Yalcin (University of California, San Diego), Dezhi Hong (University of California, San Diego), Rajesh Gupta (University of California, San Diego), Harinath Garudadri (University of California, San Diego),
Hide Authors & Abstract

Show Authors & Abstract
Day 3 08/10/2020
Room #1

Pervasive Health Next Coach Workshop 14:30 - 18:00

14:30 CET - 9:30 EDT
Room #2

Poster Session 11:50 - 12:35

11:50 EDT
11:50 - 11:50
Measuring Self-Esteem with Passive Sensing

Self-esteem encompasses how an individual self-evaluates themselves and is an important contributor to their success. Like most other psychological wellbeing measures, self-esteem has been traditionally measured using survey-based methodologies. However, surveys suffer from limitations such as retrospective recall and reporting biases, leading to a need for more proactive measurement approaches. Our work uses smartphone sensors to predict self-esteem and is situated in a multimodal sensing study on college students over five weeks. We use theory-driven features, such as phone communications (calls and texts), and physical activity to predict three dimensions, performance, social, and appearance self-esteem. We adopt statistical modeling approaches including linear, ensemble, and neural network regression to measure self-esteem. Our best model predicts self-esteem with a high correlation (𝑟) of 0.60 and low SMAPE of 7.26%, indicating high predictive accuracy in performance. We inspect the top features finding theoretical alignment; for example, social interaction significantly contributes to performance and appearance-based self-esteem, whereas, and physical activity is the most significant contributor towards social self-esteem. Our work reveals the efficacy of passive sensors for predicting self-esteem, and we situate our observations with literature and discuss the implications of our work for tailored interventions and improving wellbeing.
Authors: Mehrab Bin Morshed (Georgia Tech), Koustuv Saha (Georgia Tech), Munmun De Choudhury (Georgia Tech), Gregory Abowd (Georgia Tech), Thomas Ploetz (Georgia Tech),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
A Design Research Into the Needs of a Sleep Diary for Children

We describe the process and results of a study into the needs of a sleep diary for children that are suffering of insomnia. Applying a methodology oriented on the user we have identified needs of patients and professionals, transcribed them into functional and non-functional requirements, and created a low fidelity prototype.
Authors: Tudor Vacaretu (Eindhoven University of Technology), Sigrid Pillen (Sleep Medicine Center Kempenhaeghe), Sebastiaan Overeem (Kempenhaeghe Sleep Medicine Research Centre), Thomas Visser (Philips Design), Panos Markopoulos (Eindhoven University of Technology),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Data-Driven Analysis of Parkinson's Disease and its Detection at an Early Stage

Parkinson's Disease (PD) is the neurological condition caused by the destruction and death of neurons. Nowadays, PD can not be cured and the number of the patients with the PD is continuously growing. In this work, we report a feasibility study involving 74 subjects to whom we proposed 15 exercises helping reveal the risk of PD at an early stage. In this study, we collected the data using wireless wearable sensors and perform the data analysis relying on machine learning techniques. Experimental results demonstrated that the proposed solution tested in real conditions is promising for more complex diagnostic workflow including the assessment of quality of PD therapy.
Authors: Aleksandr Talitckii (Skolkovo Institute of Science and Technology), Anna Anikina (Skolkov Institute of Science and Technology), Ekaterina Kovalenko (Skolkovo Institute of Science and Technology), Oscar Mayora (FBK), Venet Osmani (Fondazione Bruno Kessler), Olga Zimniakova (A.I.Burnazyan Federal Medical and Biophysical Center), Maxim Semenov (A.I.Burnazyan Federal Medical and Biophysical Center), Ekaterina Bril (A.I.Burnazyan Federal Medical and Biophysical Center), Dmitry Dylov (Skoltech), Andrey Somov (Autonomous Non-Profit Organization for Higher Education “Skolkovo Institute of Science and Technology”),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Design and Evaluation of Mobile Mental Health Resource App for First Responders

This project was completed in collaboration with a non- profit community mental health organization and first responders, to develop an app to better facilitate the process of navigating resources and finding the right ones at any time and location. To better understand the background, we carried out a literature review, heuristic evaluation, stakeholder interviews, and digital resource repository evaluations. This helped us identify four main domains to focus on: Resources, Around You, Information, and Programs. After this, a focus group discussion was conducted to understand how participants characterized mental health resources and evaluated the initial design. The design components have been explained in detail and future directions have been outlined in the article.
Authors: Courtney Crooks (Georgia Tech Research Institute), Kunal Dhodapkar (Georgia Institute of Technology), Rachel Feinberg (Georgia Institute of Technology), Sonam Singh (Georgia Institute of Technology), Talia Ayala-Feliciangeli (Georgia Institute of Technology), Rosa Arriaga (Georgia Institute of Technology),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Exploring the Challenges and Potential Alternatives of Insulin Pump Technologies

This paper examines the current technology of diabetes management devices, primarily insulin pumps. Insulin pumps are effective tools for the precise control of glucose levels, for type 1 diabetes (T1D) patients. Many design and usability challenges still exist with insulin pump technology. In this study, we investigated current shortcomings and limitations of insulin pumps through survey (N=103) and interview (N=7) data collection methods. Our findings revealed issues with current insulin pumps including: 1) wear-ability and accessibility in public; 2) operating devices while performing demanding tasks; 3) interruptions with social activities and interactions; 4) continuity of maintenance, and 5) interface operations. Our study aspires to inform the future design of novel insulin pumps that enable people with T1D to maintain better control of their glucose levels through consistent and steady interactions with these tools during their everyday activities.
Authors: Andrew Harper (Georgia Institute of Technology), Leila Aflatoony (Georgia Institute of Technology), Wendell Wilson (Georgia Institute of Technology), Wei Wang (Georgia Institute of Technology),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Foodbot: A Goal-Oriented Just-in-Time Healthy Eating Interventions Chatbot

Recent research has identified a few design flaws in popular mobile health (mHealth) applications for promoting healthy eating lifestyle, such as mobile food journals. These include tediousness of manual food logging, inadequate food database coverage, and a lack of healthy dietary goal setting. To address these issues, we present Foodbot, a chatbot-based mHealth application for goal-oriented just-in-time (JIT) healthy eating interventions. Powered by a large-scale food knowledge graph, Foodbot utilizes automatic speech recognition and mobile messaging interface to record food intake. Moreover, Foodbot allows users to set goals and guides their behavior toward the goals via JIT notification prompts, interactive dialogues, and personalized recommendation. Altogether, the Foodbot framework demonstrates the use of open-source data, tools, and platforms to build a practical mHealth solution for supporting healthy eating lifestyle in the general population.
Authors: Philips Kokoh Prasetyo (Singapore Management University), Palakorn Achananuparp (Singapore Management University), Ee-Peng Lim (Singapore Management University),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Challenges for the design of people-centered pharmaceutical packaging

Exploratory research, which seeks to investigate how people make use of pharmaceutical packaging and challenges to improve their design. In the United States alone, 62.9 million dispensing errors have been reported per year in hospitals and pharmacies (Hicks, 2008). In Colombia, there are no studies in this regard, and in general, the needs of people regarding packaging and how their design can contribute to a better user experience are unknown. This exploration was done with 5 people chosen at random, they were asked to perform a series of tasks regarding two packages while wearing eye tracker glasses. The findings show a good amount of mistakes easy to make during the use of medications: people did not easily find indications of how the medication should be consumed and storage properly, users have difficulty identifying expiration dates on the packaging, there is a feeling of that information is hidden, users mention as a necessary improvement a redesign of the contraindications section, the packaging does not provide information on how the product should be discarded. The upper right area of ​​these packages is relevant; it was observed in the eye-tracker that constant fixations were made in that area. The Conclusión is a question: how the design of pharmaceutical packaging could contribute to the reduction of errors during the phases of acquisition, intake, management, control of adverse effects, disposal and in the prevention of misuse?.
Authors: Monica Forero (Universidad Nacional de Colombia, Escuela de Diseño Gráfico, MG-Des, Profesor), Mauricio Román (Universidad Nacional de Colombia, Escuela de Diseño Gráfico, Estudiante), Brayan Sanchez (Universidad Nacional de Colombia, Escuela de Diseño Gráfico, Student), Miguel Buitrago (Universidad Nacional de Colombia, Escuela de Diseño Gráfico, Student),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Integrating voice-assisted technology with an in-home sensor system: Exploring the development of a participant-based design study

This paper describes the iterative process in which voice-assisted technology (VAT) has been integrated with an in-home sensor system to enable older adults to better manage their health. Through pilot research, a user interface was developed and is currently being deployed in older adults’ homes. This ongoing research has the ability to help older adults remain independent in their own homes and can assist informal caregivers in providing at-home supports.
Authors: Geunhye Park (School of Social Work, University of Missouri-Columbia), Erin Robinson (School of Social Work, University of Missouri-Columbia), Shradha Shalini (Electrical Engineering and Computer Science, University of Missouri-Columbia), Marjorie Skubic (Electrical Engineering and Computer Science, University of Missouri-Columbia), Brianna Markway (Center for Eldercare & Rehabilitation Tech, University of Missouri-Columbia), Amanda Hill (Center for Eldercare & Rehabilitation Tech, University of Missouri-Columbia), Kari Lane (Sinclair School of Nursing, University of Missouri-Columbia), Marilyn Rantz (Sinclair School of Nursing, University of Missouri-Columbia),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Machine Learning Approach for Motion Artifact Detection in Ballistocardiogram Signals

With the current increase in cardiovascular disease and the complexities they create, especially for aging seniors, we are working on in-home and non-invasive techniques to monitor vital signs for early detection of health conditions. Ballistocardiography has shown to be useful for long-term evaluation of myocardial strength. We have previously reported the successful utilization of our hydraulic bed sensor in the estimation of heart rate, sleep posture, and blood pressure. However, bed sensors used in naturalistic settings such as the home are known to be highly susceptible to motion artifacts. In this paper, the state of the art methods for motion artifact detection and reduction are reviewed, and a new sequential machine learning approach is proposed. The proposed method is based on 53 novel features extracted jointly from time and frequency domains for noise detection. Our experiments show detection accuracy and sensitivities as high as 99%. Data were collected in two separate IRB approved data collections, one with 16-minute sequences from 25 subjects in the lab and the other with 5 sets of overnight data collected at a sleep center.
Authors: Moein Enayati (Mayo Clinic), Nasibeh Zanjirani Farahani (Mayo Clinic), Marjorie Skubic (University of Missouri),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
MIND: A Tool for Mental Health Screening and Support of Therapy to Improve Clinical and Research Outcomes

Routine experiences of daily living invoke particular patterns that can be detected in online activities. Every time an individual carries out any activity on the internet some kind of metadata, reflecting the user's preference, is created and stored. The generated metadata, a latent bi-product of high volume user interactions, is rich, has the potential to be mined for understanding one's current mental state. For example, Google logs every search query made on Google Search, Maps, and YouTube. Closely monitoring these experiences and events, along with the history of online activities, can inform systems to provide early diagnosis and detection of depression, anxiety, and related problems. A growing body of research focuses on using social media for identifying signals associated to various mental health phenomena. However, interventions based on such sources tend to have high false positive rates and may lead to inaccurate diagnosis. In this work, we propose a framework, MIND, that can leverage large amount of passively sensed online engagements history to estimate mental health assessments on depression, anxiety, self-esteem, etc. MIND is designed to use these otherwise ignored data, with informed consent from the subject. We envision that MIND has the potential to be easily be integrated into applications in clinical and research settings to help caregivers make informed assessments about individuals during and in between appointments and other health sector contacts.
Authors: Anis Zaman, Henry Kautz (University of Rochester), Vincent Silenzio (Rutgers University),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Self-prediction of seizures in drug resistance epilepsy using digital phenotyping: a concept study

Drug-resistance is a prevalent condition in children and adult patients with epilepsy. The quality of life of these patients is profoundly affected by the unpredictability of seizure occurrence. Some of these patients are capable of reporting self-prediction of their seizures by observing their affectivity. Some patients report no signs of feeling premonitory symptoms, prodromes, or aura. In this paper, we propose a concept study that will provide objective information to self-predict seizures for both the patient groups. We will develop a model using digital phenotyping which takes both ecological momentary assessment and data from sensor technology into consideration. This method will be able to provide a feedback of their premonitory symptoms so that a pre-emptive therapy can be associated to reduce seizure frequency or eliminate seizure occurrence.
Authors: Sidratul Moontaha (Hasso-Plattner Institute, University of Potsdam), Nico Steckhan (Hasso-Plattner Institute), Arpita Kappattanavar (Hasso-Plattner Institute), Rainer Surges (University of Bonn Medical Center), Bert Arnrich (Hasso-Plattner-Institute, University of Potsdam),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Streamlining the Prosthesis Fabrication Process Using 3D Technologies

Existing plastering techniques for prosthesis fabrication cause sig- nificant inconvenience during the socket adjustment and replace- ment process for both prosthetists and patients. Due to limitations in the current process, plaster casts of the patient’s residual limb are destroyed during each step of the process, which prevents error correction or repetitions. This study employs a user-centered de- sign process to streamline the process of prosthesis fabrication by incorporating 3-Dimensional (3D) scanning, modeling and printing technologies, leveraging and evaluating the application of such technologies to enhance the method of prosthesis fabrication. Fea- sibility tests were conducted with 3D printed models of different thicknesses and structures, identifying their capabilities of with- standing heat and pressure during the procedure of processing. Using 3D technologies, prosthetists will be able to retain digital copies of geometry data of patients’ residual limbs while producing satisfactory outcomes, in order to add flexibility to consultation lo- cations and reduce effort for prosthetists, enhancing the experience of patient care.
Authors: Weijia Wang (The University of Melbourne), Chong Yan Chua (The University of Melbourne), Tilman Dingler (The University of Melbourne),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
TAMICA: Tailorable Autonomous Motivational Interviewing Conversational Agent

With the increased adoption of voice assistants in people’s homes such as Amazon Alexa and Google Home, conversational agents (CA) bring numerous opportunities to support health management in everyday settings. We present our ongoing effort on developing the Tailorable Autonomous Motivational Interviewing Conversational Agent (TAMICA). TAMICA incorporates Motivational Interviewing (MI) techniques to help parents strategize tailored healthy eating goals for their families. The system is accompanied by a tailoring interface designed for parents to tailor the MI script and the agent’s communicative behaviors. We are in the process of recruiting parents of children under the age of 18 to investigate the usability and feasibility of TAMICA. We present the system and the study protocol of this usability and feasibility testing.
Authors: Diva Smriti (Drexel University), Ji Youn Shin (Michigan State University), Munif Mujib (Drexel University), Meghan Colosimo (Drexel University), Tsui-Sui Kao (Michigan State University), Jake Williams (Drexel University), Jina Huh-Yoo (Drexel University),
Hide Authors & Abstract

Show Authors & Abstract
11:50 - 11:50
Will You Be My Quarantine: A Computer Vision and Inertial Sensor Based Home Exercise System

The quarantine situation inflicted by the COVID-19 pandemic has left many people around the world isolated at home. Despite the large variety of mobile device-based self exercise tools for training plans, activity recognition or repetition counts, it remains challenging for an inexperienced person to perform fitness workouts or learn a new sport with the correct movements at home. As a proof of concept, a home exercise system has been developed in this contribution. The system takes computer vision and inertial sensor data recorded for the same type of exercise as two independent inputs, and processes the data from both sources into the same representations on the levels of raw inertial measurement unit (IMU) data and 3D movement trajectories. Moreover, a Key Performance Indicator (KPI) dashboard was developed for data import and visualization. The usability of the system was investigated with an example use case where the learner equipped with IMUs performed a kick movement and was able to compare it to that from a coach in the video.
Authors: Justin Albert (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Lin Zhou (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Pawel Gloeckner (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Justin Trautmann (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Lisa Ihde (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Justus Eilers (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Mohammed Kamal (Digital Health Center, Hasso Plattner Institute, University of Potsdam), Bert Arnrich (Digital Health Center, Hasso Plattner Institute, University of Potsdam),
Hide Authors & Abstract

Show Authors & Abstract
Room #3

Doctoral Consortium 09:00 - 12:00

9:00 EST