Title: A new particle filter for high-dimensional state-space models based on intensive and extensive proposal distribution

Authors: Viet Phuong Nguyen, Takashi Washio, Tomoyuki Higuchi

Addresses: The Institute for Scientific and Industrial Research, Osaka University, 8-1, Mihogaoka, Ibaraki-shi, Osaka 567-0047, Japan. ' The Institute for Scientific and Industrial Research, Osaka University, 8-1, Mihogaoka, Ibaraki-shi, Osaka 567-0047, Japan. ' The Institute of Statistical Mathematics, 10-3, Midori-cho, Tachikawa, Tokyo 190-8562, Japan

Abstract: This paper proposes novel principles and techniques of a particle filter to estimate dynamic system states under an observed time series data and a state-space model which are possibly non-linear and have the dimensions more than several hundreds. First, we point out two crucial curses of dimensionality and propose three key ideas to overcome them. Second, we propose the novel particle filters implementing these ideas and analyse their mathematical characteristics. Our experimental evaluation demonstrates their significant accuracy, robustness and efficiency for both artificial and real-world problems having large scales.

Keywords: dynamic systems; state-space modelling; state estimation; particle filters; high-dimensional state space; curses of dimensionality; distribution approximation; intensive proposal distribution; extensive proposal distribution; non-parametric smoothings.

DOI: 10.1504/IJKESDP.2010.037492

International Journal of Knowledge Engineering and Soft Data Paradigms, 2010 Vol.2 No.4, pp.284 - 311

Published online: 14 Dec 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article