Network-based H_∞ state estimation for neural networks using limited measurement

This chapter is concerned with the network-based H_∞ state estimation problem for neural networks. Because of network constraints, we consider that transmitted measurements suffer from the sampling effect, external disturbance, network-induced delay, and packet dropout, simultaneously. The external disturbance, network-induced delay, and packet dropout affect the measurements at only the sampling instants owing to the sampling effect. In addition, when packet dropout occurs, the last received data are used. To overcome the difficulty in estimating original signals from the limited signals, a compensator is designed. By aid of the compensator, a state estimator designed which guarantees desired H_∞ performance. A numerical example is given to illustrate the validity of the proposed methods.