Open access
Sep 2026
Deployment-Oriented Evaluation of Lightweight IMU-Based Human Activity Recognition: On-Device Efficiency and Streaming Feasibility
Lightweight Human Activity Recognition (L-HAR), a controlled comparison of Baseline and Lightweight Temporal Convolutional Network, Transformer, and Long Short-Term Memory models using data sampled at 100Hz from three inertial measurement units (IMUs) worn by one participant is presented.
Inho Gil, Seongmin Ha, Jihwan Oh et al.
· Italian National Conference... · 0 citations