TY - JOUR
T1 - Finite-Time Passivity-Based Stability Criteria for Delayed Discrete-Time Neural Networks via New Weighted Summation Inequalities
AU - Saravanakumar, Ramasamy
AU - Stojanovic, Sreten B.
AU - Radosavljevic, Damnjan D.
AU - Ahn, Choon Ki
AU - Karimi, Hamid Reza
N1 - Funding Information:
Manuscript received August 9, 2017; revised January 12, 2018 and March 27, 2018; accepted April 9, 2018. Date of publication May 22, 2018; date of current version December 19, 2018. This work was supported in part by the National Research Foundation of Korea through the Ministry of Science, ICT and Future Planning under Grant NRF-2017R1A1A1A05001325, in part by the Brain Korea 21 Plus Project in 2018, and in part by the Ministry of Science and Technology of Serbia under Grant ON174001. (Corresponding author: Choon Ki Ahn.) R. Saravanakumar is with the Department of Mathematics, Faculty of Science, Mahidol University, Bangkok 10400, Thailand, and also with the Research Center for Wind Energy Systems, Kunsan National University, Gunsan-si 54005, South Korea (e-mail: saravanamaths30@gmail.com).
Publisher Copyright:
© 2012 IEEE.
PY - 2019/1
Y1 - 2019/1
N2 - In this paper, we study the problem of finite-time stability and passivity criteria for discrete-time neural networks (DNNs) with variable delays. The main objective is how to effectively evaluate the finite-time passivity conditions for NNs. To achieve this, some new weighted summation inequalities are proposed for application to a finite-sum term appearing in the forward difference of a novel Lyapunov-Krasovskii functional, which helps to ensure that the considered delayed DNN is passive. The derived passivity criteria are presented in terms of linear matrix inequalities. A numerical example is given to illustrate the effectiveness of the proposed results.
AB - In this paper, we study the problem of finite-time stability and passivity criteria for discrete-time neural networks (DNNs) with variable delays. The main objective is how to effectively evaluate the finite-time passivity conditions for NNs. To achieve this, some new weighted summation inequalities are proposed for application to a finite-sum term appearing in the forward difference of a novel Lyapunov-Krasovskii functional, which helps to ensure that the considered delayed DNN is passive. The derived passivity criteria are presented in terms of linear matrix inequalities. A numerical example is given to illustrate the effectiveness of the proposed results.
KW - Discrete-time neural networks (DNNs)
KW - Lyapunov method
KW - finite-time passivity (FTP) analysis
KW - weighted summation inequality
UR - http://www.scopus.com/inward/record.url?scp=85047638906&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2018.2829149
DO - 10.1109/TNNLS.2018.2829149
M3 - Article
C2 - 29994321
AN - SCOPUS:85047638906
SN - 2162-237X
VL - 30
SP - 58
EP - 71
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 1
M1 - 8362787
ER -