用双数据集模型实现可解释的步态异常检测，准确率达98.6%。
Explainable Gait Abnormality Detection Using Dual-Dataset CNN-LSTM Models
- 融合关节特征与轮廓图像的双分支CNN-LSTM架构
- 在独立测试集上达到98.6%准确率，召回率与F1值优异
- 结合SHAP与Grad-CAM提供时间与空间可解释性，适合临床与生物识别场景
步态是诊断运动障碍的关键指标，但现有模型多缺乏可解释性且依赖单一数据集。本文提出一种双分支CNN-LSTM框架：一维分支使用来自GAVD数据集的关节特征，三维分支使用来自OU-MVLP数据集的轮廓图像。通过SHAP（时间归因）和Grad-CAM（空间定位）实现可解释性。在独立测试集上，系统达到98.6%的准确率，同时具备高召回率与F1值。该方法推动了临床与生物识别领域中可解释步态分析的发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。