Abstract
This paper addresses the resilient H_{infty } state estimation problem under variance constraint for discrete uncertain time-varying recurrent neural networks with randomly varying nonlinearities and missing measurements. The phenomena of missing measurements and randomly varying nonlinearities are described by introducing some Bernoulli distributed random variables, in which the occurrence probabilities are known a priori. Besides, the multiplicative noise is employed to characterize the estimator gain perturbation. Our main purpose is to design a time-varying state estimator such that, for all missing measurements, randomly varying nonlinearities and estimator gain perturbation, both the estimation error variance constraint and the prescribed H_{infty } performance requirement are met simultaneously by providing some sufficient criteria. Finally, the feasibility of the proposed variance-constrained resilient H_{infty } state estimation method is verified by some simulations.
Highlights
In the past two decades, the popularization of the Internet has greatly changed our way of life through the rapid communication ways [1,2,3]
During the analysis and implementation of the methods related to recurrent neural networks (RNNs), it should be noticed that the neuron
4 Design of the estimator gain matrix a sufficient criterion is proposed to deal with the design problem of discrete time-varying state estimator, which can be solved by several recursive matrix inequalities
Summary
In the past two decades, the popularization of the Internet has greatly changed our way of life through the rapid communication ways [1,2,3]. It should be noted that the nonlinearities are commonly inherent characteristics between neurons, which affect the understanding and analysis of the neural networks (NNs). Some efficient methods have been given to analyze different NNs. For example, an effective finite-time synchronization criterion has been proposed in [7] for coupled stochastic NNs, where both the Markovian switching parameters and saturation have been addressed. Some useful state estimation algorithms have been given in [8] for delayed NNs to guarantee the H∞ as well as passivity and in [9] for bidirectional associative NNs subject to mixed time-delays. During the analysis and implementation of the methods related to RNNs, it should be noticed that the neuron
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
