Reliable H∞ filtering for Markovian jump neural networks with time delays and sensor failures

This paper is concerned with the problem of reliable H
_∞
filtering for Markovian jump neural networks in the presence of time-varying delays and sensor failures. The aim is the design of a reliable filter ensuring stochastic stability and a prescribed H
_∞
performance level for the resulting filtering error system. A sufficient condition for the existence of such a filter is obtained. When this condition is feasible, a design procedure of the desired filter is developed. Finally, a numerical example is provided to illustrate the effectiveness of the proposed filter design scheme.