8:30 AM to 9:00 AM: WetTouch: Touching Ground in the Wearable Detection of Hand-Washing Using Capacitive Sensing
Florian Wolling; Jonas Bilal; Philipp M Scholl; Benjamin Völker; Kristof Van Laerhoven
9:00 AM to 9:30 AM: Inferring User Height and Improving Impersonation Attacks in Mobile Payments using a Smartwatch
Jack Sturgess; Simon Eberz; Ivo Sluganovic; Ivan Martinovic
9:30 AM to 10:00 AM: Rail Lone Worker Safety Solution with Deep Learning
Lan Lin; Cristina Rodriguez Vera; Frédéric Bernaudin; Benoit Besson; Jun Fu
Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection
Yuang Shi; Varsha Suresh; Wei Tsang Ooi
Gait-based Authentication: Evaluation of Energy Consumption on Commercial Devices
Alessio Vecchio; Raffaele Nocerino; Guglielmo Cola
Impact of E-Scooters on Pedestrian Safety: A Field Study Using Pedestrian Crowd-Sensing
Anindya Maiti; Nisha Vinayaga-Sureshkanth; Murtuza Jadliwala; Raveen Wijewickrama; Greg Griffin
ROMeasure: A Practical Solution For Accurate Range Of Motion Analysis Using A Smartwatch
Vivek Chandel; Murali Poduval; Avik Ghose
The cold start problem and per-group personalization in real-life emotion recognition with wearables
Stanislaw Saganowski; Dominika Kunc; Bartosz Perz; Joanna Komoszyńska; Maciej Behnke; Przemysław Kazienko
Unobtrusive Monitoring of COPD Patients using Speech Collected from Smartwatches in the Wild
Tina Sedaghat; Salaar Liaqat; Daniyal Liaqat; Robert Wu; Andrea Gershon; Tatiana Son; Tiago Falk; Moshe Gabel; Alex Mariakakis; Eyal de Lara
Wearables in an Ecosystem of Smart Devices for Health Sensing by Dr. Mayank Goel (CMU)
Abstract: Personal wearable fitness devices (e.g., FitBit, Apple Watch) can go beyond providing information such as the number of steps taken, hours spent exercising, and a coarse measure of sleep quality. Though highly valued by the user, rough activity estimates fail to provide medically-actionable information. This talk will include approaches to detect a user’s behavior, their physiology, and how this information can be clinically relevant. Considering wearables are already sensor-laden, I will talk about machine learning models that leverage the onboard sensors and ensure immediate deployability and impact of our efforts. Moreover, given wearables are continually evolving, we are investigating what new form factors and capabilities can make them smarter and more clinically useful. Ultimately, we aim to develop a suite of technologies that adapts to the user's context and requirements, and holistically understand the user's behavior, physiology, and the relation between the two.
About the Speaker: Mayank Goel is an Associate Professor in ISR and HCII in the School of Computer Science at Carnegie Mellon University. He leads the Smart Sensing for Humans (Smash) Lab at CMU and focuses on designing new sensing systems using sensors and devices that are already present in a user's environment. The lab aims to solve hard problems in various domains, including health sensing, technologies for global development, and novel interactive systems. Some of his inventions are currently deployed in clinics around the world and are used by several thousand patients every month. Many of these technologies are currently going through regulatory approvals. Mayank has been awarded Google Faculty Research Fellowship and Microsoft Research PhD Fellowship. He received his Ph.D. in Computer Science and Engineering from the University of Washington in 2016.
4:00 PM to 4:15 PM: Closing remarks