Open access
Jul 2026
Hybrid Spatial-Temporal Deep Learning Architectures for FMCW Radar-Based Human Activity Recognition
A hybrid spatial–temporal deep learning framework for FMCW radar-based HAR using micro-Doppler spectrograms is proposed, which outperform conventional CNN and standalone LSTM approaches in accuracy, robustness, and generalisation.
Daffa Ahmadhan Khusumah, F. Suratman, Hesty Susanti
· ARMADA : Jurnal Penelitian M... · 0 citations