A Dynamic-Varying Parameter Enhanced ZNN Model for Solving Time-Varying Complex-Valued Tensor Inversion With Its Application to Image Encryption

被引：8

作者：

Xiao, Lin ^{[1
,2
]}

Li, Xiaopeng ^{[1
,2
]}

Cao, Pengling ^{[1
,2
]}

He, Yongjun ^{[1
,2
]}

Tang, Wensheng ^{[1
,2
]}

Li, Jichun ^{[3
]}

Wang, Yaonan ^{[4
]}

机构：

[1] Hunan Normal Univ, Hunan Prov Key Lab Intelligent Comp & Language Inf, Changsha 410081, Peoples R China

[2] Hunan Normal Univ, MOE LCSM, Changsha 410081, Peoples R China

[3] Newcastle Univ, Sch Comp, Newcastle Upon Tyne NE1 7RU, England

[4] Hunan Univ, Coll Elect & Informat Technol, Changsha 410082, Hunan, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2024年 / 35卷 / 10期

基金：

中国国家自然科学基金;

关键词：

Dynamic parameter; image encryption; robustness; time-varying complex valued tensor inverse (TCVTI); zero-ing neural network (ZNN); RECURRENT NEURAL-NETWORK; MATRIX; CONVERGENCE; ALGORITHM; EQUATION; PRODUCT; DESIGN; SYSTEM; ROBUST;

D O I：

10.1109/TNNLS.2023.3270563

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Time-varying complex-valued tensor inverse (TVCTI) is a public problem worthy of being studied, while numerical solutions for the TVCTI are not effective enough. This work aims to find the accurate solution to the TVCTI using zeroing neural network (ZNN), which is an effective tool in terms of solving time-varying problems and is improved in this article to solve the TVCTI problem for the first time. Based on the design idea of ZNN, an error-adaptive dynamic parameter and a new enhanced segmented signum exponential activation function (ESS-EAF) are first designed and applied to the ZNN. Then a dynamic-varying parameter-enhanced ZNN (DVPEZNN) model is proposed to solve the TVCTI problem. The convergence and robustness of the DVPEZNN model are theoretically analyzed and discussed. In order to highlight better convergence and robustness of the DVPEZNN model, it is compared with four varying-parameter ZNN models in the illustrative example. The results show that the DVPEZNN model has better convergence and robustness than the other four ZNN models in different situations. In addition, the state solution sequence generated by the DVPEZNN model in the process of solving the TVCTI cooperates with the chaotic system and deoxyribonucleic acid (DNA) coding rules to obtain the chaotic-ZNN-DNA (CZD) image encryption algorithm, which can encrypt and decrypt images with good performance.

引用

页码：13681 / 13690

页数：10