On-Line Bayesian Classifier Design for Measurement Fusion

Abstract

A neural-network-based classifier design for adaptive Kalman filtering is introduced to fuse the measurements extracted from multiple sensors to improve tracking accuracy. The proposed method consists of a group of parallel Kalman filters and a classifier based on Radial Basis Function Network (RBFN). By incorporating Markov chain into Bayesian estimation scheme, a RBFN is used as a probabilistic neural network for classification. Based upon data compression technique and on-line classification algorithm, an adaptive estimator to measurement fusion is developed that can handle the switching plant in the multi-sensor environment. The simulation results are presented which demonstrate the effectiveness of the proposed method.