TabletStone
Role-aware, rotation-robust feedback on a curling stone. An on-stone interface explores how throwers and sweepers can read movement information during training.
Read the researchPh.D. candidate / Takegawa Lab
Guanyu
Chen.
Future University HakodateHakodate, Japan
I study how sensing and lightweight AI can make movement easier to understand. My research brings together sports informatics, wearable motion sensing, and interactive systems—with a focus on curling and animal behavior.
RESEARCH FIELDNOTES01 / MOTION
From motion
to understanding.
MODELING
INTERACTION
Sports informatics+Wearable sensing+Edge AI+Human–computer interaction
01 / RESEARCH
Making movement
meaningful.
01
Sports informatics
Understanding curling through motion measurement, trajectory prediction, and feedback during training.
View research02Motion sensing
Using inertial sensors and machine learning to recognize movement and behavior in everyday settings.
View research03Intelligence at the edge
Designing lightweight inference and secure IoT systems for devices with limited computing resources.
View research02 / SELECTED PROJECTS
Research in practice.
From the curling rink
to everyday movement.
Predicting the next move
Lightweight trajectory prediction for curling. Attention-enhanced sequence models connect motion measurements to real-time forecasts on resource-constrained devices.
Read the researchSensing animal behavior
IMU-based motion recognition for cats and dogs. Wearable sensing and compact models support animal–computer interaction, alongside research into secure data exchange.
Read the research03 / PUBLICATIONS
Selected writing.
2026Journal
TabletStone: Role-Aware, Rotation-Robust On-Stone Visualization for Curling Training
Applied Sciences · 16(9), 4181
2026Journal
Attention-Enhanced LSTM for Real-Time Curling Stone Trajectory Prediction on Resource-Constrained Devices
Applied Sciences · 16(5), 2612
2026Journal
Lightweight Authentication and Dynamic Key Generation for IMU-Based Canine Motion Recognition IoT Systems
Future Internet · 18(2), 111
2025Journal
Canine-centric interactive systems: Wavelet-based IMU motion recognition in edge AI scenarios
Entertainment Computing · 55, 100971
2025Journal
Cat and Dog Behavior Recognition Method Using Deep Learning Approach Based on Inertial Measurement Unit Sensor Data
Sensors and Materials · 37(3), 1073–1098
04 / BACKGROUND
A path through
research.
2025–present
Ph.D. candidate
Future University Hakodate
2023–2025
Master’s degree
Future University Hakodate
2022–2023
Research student
Future University Hakodate
2018–2022
Bachelor’s degree
Communication University of China, Nanjing
AWARDS & HONORS
Recognition.
Best Paper Award
icSPORTS 2024
CONTACT
Let’s exchange
ideas.
Takegawa Lab · Future University Hakodate
Hakodate, Japan