What question did this study set out to answer?

This research aims to improve gait phase detection by utilizing deep learning models for automatic phase recognition.

April 17, 2026PLoS ONEOpen Access

Deep learning-based gait phase detection using shank-mounted IMU data: Classification approach

View Full Paper

Ask AI

Bookmark

Authors

Gait phase detection utilizes deep learning models for enhanced accuracy in assessing mobility, indicating practical applications.

This research aims to improve gait phase detection by utilizing deep learning models for automatic phase recognition.
Used an end-to-end supervised classification learning approach with a Transformer model.
Trained models on the NONAN GaitPrint dataset with time-series recordings from 35 healthy young adults.
Evaluated various models, including a CNN, Hybrid LSTM+GRU, and a Transformer.
The Transformer model achieved an F1-score of approximately 92.99%.
The CNN and Hybrid LSTM+GRU models showed comparable performance with no substantial differences.

Choi et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark