AED Hunter: Gamified AED Retrieval Training System
Investigating AED retrieval in real-world settings through gamified mobile interaction and sensing.
My main research area is ubiquitous computing, and my research goal is to improve people's well-being using information technologies. To achieve this goal, I am conducting research not only on individual- and group-centered behavior recognition, analysis, accumulation, and prediction technologies, but also on intervention-based behavior change promotion. Furthermore, I engage in interdisciplinary collaborations with researchers both domestically and internationally in application domains such as healthcare, sports, and education.
Investigating AED retrieval in real-world settings through gamified mobile interaction and sensing.
Individual-level precise UV exposure assessment using satellite signals and Earth observation data.
Detecting and predicting driving behavior of sharing bikes, scooters, and other mobility users using consumer devices to improve safety.
A silent speech interface using consumer earbuds with ultrasonic sensing to recognize silently spelled words, enabling hands-free and voice-free text input with user authentication.
Investigating and optimizing acceptable voice-based notification timings through earable devices to minimize user interruption.
Application of passive mobile and wearable sensing technologies to health tracking, including early detection of postpartum depression, disease treatment monitoring, symptom tracking, and medication support in collaboration with medical institutions.
Detecting and recognizing baby and childcare activities using off-the-shelf wearable devices and inertial sensors.
Data collection and reduction platform using smartphones and wearable devices to track athlete condition and performance, developed collaboratively with student-athletes.
Understanding city-scale traffic behavior and optimization of micro-mobility rearrangement while estimating greenhouse gas emissions.
Analysis of student behavior patterns and development of systems supporting student life using mobile passive sensing.
AWARE is an open-source sensing framework passively collecting sensor data from smartphones, used in over 200 academic papers. Responsible for iOS, macOS, and watchOS development.
Integrating deep learning with compressed sensing to efficiently compress and reconstruct smartphone sensor data, addressing storage challenges from diverse mobile sensors.
Platform enhancing team-level behavior change using lifelog information sharing among team members based on competition and collaboration.
Robust detection of preventive behaviors (mask-wearing, hand-washing, disinfection) using commercially available wearable devices.
Platform embedding sensor data into video frames using animated 2D barcodes via real-time video processing. Supports iOS, Android, macOS, and web.
Self-tracking application for recording daily activities including visited places, mobility range, and duration using location sensors.
Wearable motion sensor worn on elbow to detect inappropriate throwing form in baseball players, preventing shoulder and elbow injuries.