Explainable Gait Abnormality Detection Using Dual-Dataset CNN-LSTM Models
This advances explainable gait analysis for clinical and biometric domains, but it is incremental as it combines existing methods.
The paper tackled the problem of detecting gait abnormalities with a lack of interpretability and reliance on single datasets by proposing a dual-branch CNN-LSTM framework, achieving 98.6% accuracy on held-out sets.
Gait is a key indicator in diagnosing movement disorders, but most models lack interpretability and rely on single datasets. We propose a dual-branch CNN-LSTM framework a 1D branch on joint-based features from GAVD and a 3D branch on silhouettes from OU-MVLP. Interpretability is provided by SHAP (temporal attributions) and Grad-CAM (spatial localization).On held-out sets, the system achieves 98.6% accuracy with strong recall and F1. This approach advances explainable gait analysis across both clinical and biometric domains.