Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l_{2}$ – $l_{\infty }$ Performances
Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l_{2}$ – $l_{\infty }$ Performances
复制标题
DOI：
10.1109/tcyb.2017.2655725
复制
发表时间：
2017-01
影响因子：
11.8
通讯作者：
H. Choi;C. Ahn;H. Karimi;M. Lim
中科院分区：
文献类型：
--
作者：
H. Choi;C. Ahn;H. Karimi;M. Lim
This paper studies delay-dependent exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ senses. The design of the desired exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.
This paper studies delay-dependent exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ senses. The design of the desired exponential dissipative and $\boldsymbol {l_{2}}$ – $\boldsymbol {l_{\infty }}$ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.