Title: State estimation for neural networks with time-varying delays in the leakage terms

Authors: Chong Jiang; Dexin Zou

Addresses: Sport Education Department, Nanjing Sport Institute, Nanjing, Jiangsu Province 210014, China; Department of Sport Information and Technology, Shenyang Sport University, Shenyang, Liaoning Province 110102, China ' Sport Education Department, Nanjing Sport Institute, Nanjing, Jiangsu Province 210014, China; Economics Development Center, Shenyang Sport University, Shenyang, Liaoning Province 110102, China

Abstract: The paper is concerned with state estimation for neural networks with time-varying delay in the leakage terms. By constructing an appropriate Lyapunov-Krasovskii functional with double integral terms, and using free-weighting matrix technique and Jensen's inequality approach, new globally asymptotic stability criteria are established. The stability criteria depend on the upper bounds of the transmission discrete time-varying delay, leakage delay as well as their derivation. The presented results can be efficiently solved by resorting to Matlab LMI Toolbox. An example is included to show the effectiveness of the proposed criteria.

Keywords: neural networks; leakage delay; state estimation; time-varying delay; LMI; linear matrix inequality.

DOI: 10.1504/IJSCIP.2018.097175

International Journal of System Control and Information Processing, 2018 Vol.2 No.4, pp.305 - 316

Received: 12 Oct 2017
Accepted: 20 Aug 2018

Published online: 23 Dec 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article