Efficient Particle Filtering for Jump Markov Systems


C. Andrieu, M. Davy and A. Doucet

Technical report CUED/F-INFENG/TR427, University of Cambridge, February 2002

Abstract: In this paper we present an efficient particle filtering method to perform optimal estimation in Jump Markov (Nonlinear) Systems. This original method relies on the combination of techniques presented recently in the filtering literature, namely the Auxiliary Particle Filter [15] and the Unscented Transform [10]. This algorithm is applied to the complex problem of time-varying autoregressive estimation with an unknown time-varying model order. Simulations demonstrate the performance of our method compared to standard particle filtering techniques.