Independent component analysis for nonminimum phase systems using stable dynamic model inversion
Shuichi Fukunaga, Kenji Fujimoto · 2007
This paper proposes an independent component analysis method using stable dynamic model inversion for nonminimum phase systems. First, a stable inverse filter is constructed based on a Kalman filter in order to estimate the input sequence of the given plant. Second, the learning algorithm is derived by minimizing the Kullback-Leibler divergence. Furthermore, a numerical simulation demonstrates the effectiveness of the proposed method.