<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This article examines the problem of estimating the states of Markovian jumping competitive neural networks, where the estimation is done using stochastic sampled-data control with time-varying delay. Instead of continuously measuring the states, the network relies on sampled measurements, and a sampled-data estimator is proposed. The estimator uses probabilistic sampling during two sampling periods, following a Bernoulli distribution. The article also takes into account the possibility of actuator failure in real systems. To ensure the exponentially mean-square stability of the delayed neural networks, the article constructs a Lyapunov-Krasovskii functional (LKF) that includes information about the bounds of the delay. The sufficient conditions for stability are derived in the form of linear matrix inequalities (LMIs) by employing modified free matrix-based integral inequalities. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed method.</p>
</abstract>

This article examines the problem of estimating the states of Markovian jumping competitive neural networks, where the estimation is done using stochastic sampled-data control with time-varying delay. Instead of continuously measuring the states, the network relies on sampled measurements, and a sampled-data estimator is proposed. The estimator uses probabilistic sampling during two sampling periods, following a Bernoulli distribution. The article also takes into account the possibility of actuator failure in real systems. To ensure the exponentially mean-square stability of the delayed neural networks, the article constructs a Lyapunov-Krasovskii functional (LKF) that includes information about the bounds of the delay. The sufficient conditions for stability are derived in the form of linear matrix inequalities (LMIs) by employing modified free matrix-based integral inequalities. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed method.

Exponential State Estimation for Delayed Competitive Neural Network Via Stochastic Sampled-Data Control with Markov Jump Parameters Under Actuator Failure

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This article examines the problem of estimating the states of Markovian jumping competitive neural networks, where the estimation is done using stochastic...

Exponential State Estimation for Delayed Competitive Neural Network Via Stochastic Sampled-Data Control with Markov Jump Parameters Under Actuator Failure

Published Online: Jul 29, 2024

Page range: 373 - 385

Received: May 23, 2024

Accepted: Jul 15, 2024

DOI: https://doi.org/10.2478/jaiscr-2024-0020

Keywords
stochastic sampled-data control, competitive neural networks, state estimation, Markov jump, actuator failure

© 2024 Yang Cao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Exponential State Estimation for Delayed Competitive Neural Network Via Stochastic Sampled-Data Control with Markov Jump Parameters Under Actuator Failure

Published Online: Jul 29, 2024

Page range: 373 - 385

Received: May 23, 2024

Accepted: Jul 15, 2024

DOI: https://doi.org/10.2478/jaiscr-2024-0020

Keywordsstochastic sampled-data control, competitive neural networks, state estimation, Markov jump, actuator failure

© 2024 Yang Cao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Keywords
stochastic sampled-data control, competitive neural networks, state estimation, Markov jump, actuator failure