TY - GEN
T1 - Comparative Study of ML, DL and Temporal Models in Plantar Gait Classification
AU - Zhang, Guiyu
AU - Wang, Jun
AU - Tao, Zanyuan
AU - Yu, Hao
AU - Zou, Wulin
AU - Li, Shilei
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - This study classifies seven gait patterns (squatting, squat-to-stand, walking, going upstairs, going downstairs, standing, sitting) using plantar pressure time-series data. Following detailed data preprocessing (segmentation, window construction, feature engineering), we evaluated traditional machine learning (Random Forest, Gradient Boosting), fundamental deep learning (CNN, LSTM, Transformer, hybrid models), and advanced deep learning methods (contrastive learning, MiniRocket, ST-GCN variants). Results show: Gradient Boosting and ensemble models (ML) achieved 95.3% accuracy; hybrid models (DL) reached 94.9%; bilateral-fusion Transformer exceeded 95%; ST-GCN variants underperformed. Temporal feature-based deep learning methods demonstrated superior accuracy and generalization in gait classification, providing empirical support for model selection in gait recognition.
AB - This study classifies seven gait patterns (squatting, squat-to-stand, walking, going upstairs, going downstairs, standing, sitting) using plantar pressure time-series data. Following detailed data preprocessing (segmentation, window construction, feature engineering), we evaluated traditional machine learning (Random Forest, Gradient Boosting), fundamental deep learning (CNN, LSTM, Transformer, hybrid models), and advanced deep learning methods (contrastive learning, MiniRocket, ST-GCN variants). Results show: Gradient Boosting and ensemble models (ML) achieved 95.3% accuracy; hybrid models (DL) reached 94.9%; bilateral-fusion Transformer exceeded 95%; ST-GCN variants underperformed. Temporal feature-based deep learning methods demonstrated superior accuracy and generalization in gait classification, providing empirical support for model selection in gait recognition.
KW - deep learning
KW - gait classification
KW - machine learning
UR - https://www.scopus.com/pages/publications/105042797150
U2 - 10.1007/978-981-95-8435-2_18
DO - 10.1007/978-981-95-8435-2_18
M3 - Conference contribution
AN - SCOPUS:105042797150
SN - 9789819584345
T3 - Lecture Notes in Electrical Engineering
SP - 214
EP - 226
BT - Proceedings of 2025 9th Chinese Conference on Swarm Intelligence and Cooperative Control - Swarm Control Technologies
A2 - Wang, Qing
A2 - Dong, Xiwang
A2 - Song, Peng
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2025
Y2 - 31 October 2025 through 3 November 2025
ER -