TY - JOUR
T1 - Mixed H-Infinity and Passive Filtering for Discrete Fuzzy Neural Networks With Stochastic Jumps and Time Delays
AU - Shi, Peng
AU - Zhang, Yingqi
AU - Chadli, Mohammed
AU - Agarwal, Ramesh K.
N1 - Funding Information:
This work was supported in part by the 111 Project under Grant B12018, in part by the National Natural Science Foundation of China under Grant 61174058, in part by the Australian Research Council under Grant DP140102180 and Grant LP140100471, in part by the Natural Science Foundation of Henan Province, China, under Grant 132300410013, and in part by the Plan of Nature Science Fundamental Research in Henan University of Technology under Grant 2012JCYJ13.
Publisher Copyright:
© 2015 IEEE.
PY - 2016/4
Y1 - 2016/4
N2 - In this brief, the problems of the mixed H-infinity and passivity performance analysis and design are investigated for discrete time-delay neural networks with Markovian jump parameters represented by Takagi-Sugeno fuzzy model. The main purpose of this brief is to design a filter to guarantee that the augmented Markovian jump fuzzy neural networks are stable in mean-square sense and satisfy a prescribed passivity performance index by employing the Lyapunov method and the stochastic analysis technique. Applying the matrix decomposition techniques, sufficient conditions are provided for the solvability of the problems, which can be formulated in terms of linear matrix inequalities. A numerical example is also presented to illustrate the effectiveness of the proposed techniques.
AB - In this brief, the problems of the mixed H-infinity and passivity performance analysis and design are investigated for discrete time-delay neural networks with Markovian jump parameters represented by Takagi-Sugeno fuzzy model. The main purpose of this brief is to design a filter to guarantee that the augmented Markovian jump fuzzy neural networks are stable in mean-square sense and satisfy a prescribed passivity performance index by employing the Lyapunov method and the stochastic analysis technique. Applying the matrix decomposition techniques, sufficient conditions are provided for the solvability of the problems, which can be formulated in terms of linear matrix inequalities. A numerical example is also presented to illustrate the effectiveness of the proposed techniques.
KW - Fuzzy neural networks
KW - Markovian jump parameters
KW - mixed H-infinity and passivity performance
UR - http://www.scopus.com/inward/record.url?scp=84929208294&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2015.2425962
DO - 10.1109/TNNLS.2015.2425962
M3 - Article
AN - SCOPUS:84929208294
SN - 2162-237X
VL - 27
SP - 903
EP - 909
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 4
M1 - 7105419
ER -