Performance assessment of sequential Bayesian processors based on probably approximately correct computation and information theory

Abstract

A novel method to characterise the efficacy and efficiency of different sequential Bayesian processor implementations is proposed. This method is based on concepts of probably approximately correct computation and information theory measures. The proposed approach is used to compare the performance of three different Bayesian estimation algorithms (particle filter, unscented Kalman filter (UKF), and UKF with outer feedback correction loops) in the context of lithium-ion battery state-of-charge monitoring.