GTSNet: Flexible Architecture Under Budget Constraint for Real-Time Human Activity Recognition from Wearable Sensor
Published in Engineering Applications of Artificial Intelligence, 2023
Authors: Jaegyun Park, Wonseon Lim, Dae-Won Kim, Jaesung Lee
GTSNet is a flexible neural network architecture that adapts to a target compute budget, enabling real-time human activity recognition on wearable sensors with stringent latency requirements.
Recommended citation: J. Park, W. Lim, D. Kim, J. Lee. (2023). "GTSNet: Flexible Architecture Under Budget Constraint for Real-Time Human Activity Recognition from Wearable Sensor." Engineering Applications of Artificial Intelligence.
Download Paper