XAI-BayesHAR: A novel Framework for Human Activity Recognition with Integrated Uncertainty and Shapely Values

TL;DR

XAI-BayesHAR is a Bayesian framework for human activity recognition that enhances accuracy, provides uncertainty estimates, detects out-of-distribution data, and uses Shapley values for interpretability and model compression.

Contribution

It introduces an integrated Bayesian approach with Kalman filtering and Shapley values for improved accuracy, uncertainty quantification, and interpretability in IMU-based HAR systems.

Findings

Improved activity classification accuracy with Bayesian filtering.

Effective detection of out-of-distribution inputs using predictive uncertainty.

Shapley values help identify important features for model compression.

Abstract

Human activity recognition (HAR) using IMU sensors, namely accelerometer and gyroscope, has several applications in smart homes, healthcare and human-machine interface systems. In practice, the IMU-based HAR system is expected to encounter variations in measurement due to sensor degradation, alien environment or sensor noise and will be subjected to unknown activities. In view of practical deployment of the solution, analysis of statistical confidence over the activity class score are important metrics. In this paper, we therefore propose XAI-BayesHAR, an integrated Bayesian framework, that improves the overall activity classification accuracy of IMU-based HAR solutions by recursively tracking the feature embedding vector and its associated uncertainty via Kalman filter. Additionally, XAI-BayesHAR acts as an out of data distribution (OOD) detector using the predictive uncertainty which help to evaluate and detect alien input data distribution. Furthermore, Shapley value-based performance of the proposed framework is also evaluated to understand the importance of the feature embedding vector and accordingly used for model compression