Partial-neurons-based state estimation for artificial neural networks under constrained bit rate: The finite-time case

• Published in: Neurocomputing (Amsterdam) Vol. 488; pp. 144 - 153
• Main Authors: Wang, Licheng, Zhao, Di, Wang, Yu-Ang, Ding, Derui, Liu, Hongjian
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2022
• Subjects: Artificial neural networks; Bit-rate constraints; Encoding–decoding mechanism; Finite-time state estimation; Partial-nodes-based state estimation; Encoding–decoding mechanism; Partial-nodes-based state estimation; Finite-time state estimation; Bit-rate constraints; Artificial neural networks
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2022.03.001

This paper is concerned with the partial-neuron-based finite-time state estimation problem for a class of artificial neural networks with time-varying delays. Measurements information from only a small fractional of the artificial neurons are applied to the state estimation process. The data transmission from the sensor to estimator is implemented via a bit-rate constrained communication channel, and a data encoding–decoding scheme is developed to convert the original analog sensor measurements into certain digital codewords with fewer occupations of the network bandwidth. With the help of the Lyapunov stability theory, sufficient conditions are presented to guarantee the finite-time boundedness of the estimation error and the estimator gain matrix is parameterized in terms of the solution to certain matrix inequalities. Finally, a numerical example is provided to further confirm the effectiveness of the proposed state estimation scheme.