H∞ Filtering for Discrete-Time Neural Networks System with Time- Varying Delay and Sensor Nonlinearities

摘要

The H∞ filtering problem for a class of discrete stochastic neural networks systems with time-varying delay andnonlinear sensor is investigated. By employing the Lyapunov stability theory and linear matrix inequality optimizationapproach, sufficient conditions to guarantee the filtering error systems asymptotically stable are provided. By setting onthe lower and upper bounds of the discrete time-varying delays, an acceptable state-space realization of the H∞ and anacceptable H∞ performance index are obtained in terms of linear matrix inequality (LMI). Numerical examples andsimulations are provided to illustrate the effectiveness of the proposed methods.