What question did this study set out to answer?

The study aims to evaluate the effectiveness of different classifiers for assessing sit-to-stand movements in post-stroke rehabilitation across datasets.

March 16, 2026Open Access

Cross-Dataset Evaluation of Sit-to-Stand Movement Classifiers for Post-Stroke Rehabilitation

Key Points

The study aims to evaluate the effectiveness of different classifiers for assessing sit-to-stand movements in post-stroke rehabilitation across datasets.
Evaluated rule-based and Random Forest classifiers using XSense IMU data.
Conducted zero-shot evaluation on the CeTI-Locomotion dataset.
Performed one-shot calibration to improve Random Forest accuracy.
Rule-based classifiers achieved 71.3% accuracy in zero-shot evaluation.
Random Forest classifiers showed initial accuracy of 17.8%, improved to 58.2% with calibration.
Findings suggest biomechanically grounded strategies enhance generalizability.

Abstract

Automated assessment could support at-home post-stroke rehabilitation, yet ensuring cross-dataset generalizability is critical for real-world adoption. This study evaluates rule-based and Random Forest classifiers, trained on XSense IMU data, against the independent CeTI-Locomotion dataset. Zero-shot evaluation demonstrated the robustness of the rule-based approach (71.3% accuracy) compared to Random Forest (17.8%), which significantly improved to 58.2% with one-shot calibration. These findings indicate that generalizability is achievable through biomechanically grounded or adaptive strategies, marking a key step toward robust, clinically deployable rehabilitation systems.

Bookmark

View Full Paper

Bookmark

View Full Paper

Cross-Dataset Evaluation of Sit-to-Stand Movement Classifiers for Post-Stroke Rehabilitation

Key Points

Abstract

Cite This Study