Multiple model estimation represented by Bayesian networks

Multiple Model Estimation (MME) in hybrid systems, as a powerful approach to adaptive estimation, has been widely applied in a great deal of attention due to its unique power to handle problems with both structural and parametric uncertainties. In this paper, multiple well-known methods in MME are represented in the form of Bayesian Networks (BN), which is widely used in artificial intelligence. The discussion implies that MME may be a special case of BN.

[1]  M.J. Larkin,et al.  Sensor fusion and classification of acoustic signals using Bayesian networks , 1998, Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284).

[2]  X. Rong Li,et al.  Hybrid Estimation Techniques , 1996 .

[3]  David M. Auslander,et al.  Control and dynamic systems , 1970 .

[4]  Geoffrey Zweig,et al.  Speech Recognition with Dynamic Bayesian Networks , 1998, AAAI/IAAI.

[5]  Jukka Saarinen,et al.  Target identification with Bayesian networks , 2000, SPIE Defense + Commercial Sensing.

[6]  Youmin Zhang,et al.  Detection and diagnosis of sensor and actuator failures using IMM estimator , 1998 .

[7]  Antonio A. F. Oliveira,et al.  An image processing and belief network approach to face detection , 1999, XII Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00481).