通过时间稳定的SHAP实现老年人护理中的可解释跌倒检测
Explainable Fall Detection for Elderly Care via Temporally Stable SHAP in Skeleton-Based Human Activity Recognition
- Department of Computer Engineering, University of Science and Culture（科学与文化大学计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种轻量级框架，结合高效LSTM模型与T-SHAP，通过时间窗口稳定SHAP特征归因，提升跌倒检测的解释可靠性，实测准确率达94.3%，满足实时性要求。
AI中文摘要：
老年人护理中的跌倒检测需要准确分类和可靠的解释。现有事后解释方法在逐帧处理时产生时间不稳定归因图，无法被临床人员信赖。为此，本文提出一种结合高效LSTM模型与T-SHAP的框架，T-SHAP通过线性平滑操作减少高频率方差，保留Shapley值的理论保证。在NTU RGB+D数据集上实验表明，该框架在25毫秒内实现94.3%的分类准确率，满足中端硬件的实时需求。定量评估显示，T-SHAP相比标准SHAP和Grad-CAM在解释可靠性上有所提升，归因结果一致突出生物力学相关的运动模式，如下肢不稳定和脊柱对齐变化，符合临床对跌倒动态的观察，支持其在长期护理环境中的应用。
英文摘要：
Fall detection in elderly care requires not only accurate classification but also reliable explanations that clinicians can trust. However, existing post-hoc explainability methods, when applied frame-by-frame to sequential data, produce temporally unstable attribution maps that clinicians cannot reliably act upon. To address this issue, we propose a lightweight and explainable framework for skeleton-based fall detection that combines an efficient LSTM model with T-SHAP, a temporally aware post-hoc aggregation strategy that stabilizes SHAP-based feature attributions over contiguous time windows. Unlike standard SHAP, which treats each frame independently, T-SHAP applies a linear smoothing operator to the attribution sequence, reducing high-frequency variance while preserving the theoretical guarantees of Shapley values, including local accuracy and consistency. Experiments on the NTU RGB+D Dataset demonstrate that the proposed framework achieves 94.3% classification accuracy with an end-to-end inference latency below 25 milliseconds, satisfying real-time constraints on mid-range hardware and indicating strong potential for deployment in clinical monitoring scenarios. Quantitative evaluation using perturbation-based faithfulness metrics shows that T-SHAP improves explanation reliability compared to standard SHAP (AUP: 0.89 vs. 0.91) and Grad-CAM (0.82), with consistent improvements observed across five-fold cross-validation, indicating enhanced explanation reliability. The resulting attributions consistently highlight biomechanically relevant motion patterns, including lower-limb instability and changes in spinal alignment, aligning with established clinical observations of fall dynamics and supporting their use as transparent decision aids in long-term care environments
