Webinar 2/11/16

View Google event page here

You can view the webinar above or on our Google Plus Event page. Please feel free to ask questions prior to or during the webinar using Google’s Question and Answer feature or via Twitter using #HDEwebinar. In order to use the Question and Answer feature on Google Plus, you must be logged into a Google Plus account. To navigate to the Question and Answer feature 1) go to the webinar Google Plus event page, 2) click on the video box, 3) select the application icon (9-squar grid) in the top right corner), 4) select Q&A from the drop-down menu, 5) ask questions using the Q&A panel to the right.

Inter-individual differences such as age, gender, genetic variations, and personality can substantially impact the optimal time of day for performing cognitively demanding tasks i.e., the circadian rhythm of cognitive performance. Such differences can also affect individuals’ abilities to physiologically and cognitively cope with sleep deprivation and irregular sleep, which have negative impacts on cognitive performance as well. In this work, we are exploring the opportunity of personal data to better understand, unobtrusively model, and reliably predict individual characteristics and patterns related to circadian variables, cognitive performance, and sleep. More specifically, we are conducting the following activities: 1) Capturing smartphone interaction patterns, web usage behaviors, and online content to develop novel user-modeling techniques capable of handling this array of big data reliably and at scale; 2) conducting a 3 week study that incorporates well-established objective and subjective measurements in order to robustly evaluate our approach to passively sense an individual’s sleep and cognitive performance, factoring in biological rhythms and external factors such as caffeine; 3) advancing our understanding of the value of personal data streams in modeling health-related characteristics and behaviors by reflecting upon the daily trends in performance that our data and approach are able to effectively model as well as our failure points; and 4) delivering contributions relevant to diverse stakeholders for instance by providing insights to behavioral scientists interested in better understanding the interplay between technology usage and health behaviors or by providing recommendations for circadian-aware behavioral intervention systems that can be pursued by designers and system builders and eventually adopted by real users.

Julie A. Kientz  is an Associate Professor in the department of Human Centered Design & Engineering at the University of Washington. She directs the Computing for Healthy Living and Learning Lab, is active in the Design, Use, Build (dub) alliance, and has adjunct appointments in The Information School and Computer Science & Engineering. Dr. Kientz’s primary research areas are in the fields of Human-Computer Interaction, Ubiquitous Computing, and Health Informatics. Her research focuses on understanding and reducing the user burdens of interactive technologies for health and education through the design of future applications. She has designed, developed, and evaluated mobile, sensor, and social applications for helping individuals with sleep problems, parents of young children tracking developmental progress, individuals with visual impairments, people who want to quit smoking, and special education teachers working with children with autism. Her primary research methods involve human-centered design, technology development, and a mix of qualitative and quantitative methods. Dr. Kientz received her Ph.D. in Computer Science from the Georgia Institute of Technology in 2008. She was awarded a National Science Foundation CAREER Award in 2009, named an MIT Technology Review Innovator Under 35 in 2013, and was given the UW College of Engineering Faculty Research Innovator award in 2014.

Tanzeem Choudhury is an Associate Professor in Information Science at Cornell University, working with graduate students in both the Information Science and Computer Science departments as field faculty. She directs the People-Aware Computing group, which works on developing machine learning techniques for systems that can reason about human activities, interactions, and social networks in everyday environments.