PBVI for Optimal Photoplethysmography Noise Filter Selection Using Human Activity Recognition Observations for Improved Heart Rate Estimation on Multi-Sensor Systems

Abstract This work details the Point Based Value Iteration (PBVI) algorithm for use in multi-sensor systems. Specifically a sensor system capable of heart rate (HR) estimation. An end-to-end embedded Human Activity Recognition (HAR) System was developed to represent the observation uncertainty, and two motion artifact filters (MA) reducing filters are proposed as actions. PBVI allows optimal action decision-making based on an uncertain observation, effectively balancing correct action choice and sensor system cost. Two central systems are proposed to accompany these algorithms, one for unlimited observation access and one for limited observation access. Through simulation, it can be shown that the limited observation system performs optimally when sensor cost is negligible, while limited observation access performs optimally when sensor cost is considered. The final general framework for POMDP and PBVI that was applied to a specific HR estimation example in this work can be expanded on and used as a basis for future work on any similar multi-sensor system.