作者: V. Krishnamurthy , L. Johnston , A. Logothetis
DOI: 10.1109/ICASSP.1998.681627
关键词: Kalman filter 、 Mathematical optimization 、 Expectation–maximization algorithm 、 Bilinear interpolation 、 Maximum a posteriori estimation 、 Iterative method 、 Extended Kalman filter 、 Bilinear map 、 Algorithm 、 Sequential estimation 、 Mathematics
摘要: We present a finite dimensional iterative algorithm for optimal maximum posteriori (MAP) state estimation of bilinear systems. Bilinear models are appealing in their ability to represent or approximate broad class nonlinear show that several previously considered the literature special cases general model we propose. Our is based on expectation-maximization (EM) and outperforms widely used extended Kalman filter (EKF). Unlike EKF our an (in MAP sense) finite-dimensional solution sequence problem models.