Zicheng Wang

Zicheng Wang

Auto-generated profile, based on publicly available information

Zicheng Wang

School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 September 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
JSJunwei Sun
Junwei Sun
CLChuangchuang Li
Chuangchuang Li
ZWZicheng Wang
Zicheng Wang
YWYanfeng Wang
Yanfeng Wang
With the continuous development of computers, communication technology, and regional medical collaboration services, the security and confidentiality of information are becoming more and more important. In order to prevent the illegal leakage of sensitive patient information, it is of great significance to study medical image encryption. In this article, a flux-controlled hyperbolic memristor model with locally active characteristics is proposed, which has rich nonlinear characteristics. The memristor parameters affect the local activity of the memristor, which is explained by mathematical analysis. Based on the traditional hopfield neural network (HNN), a memristive fully connect neural network (MFNN) containing four neurons is constructed with more complex coupling relationships between individual neurons. The memristor can be used to characterize the effect of external electromagnetic radiation on neurons. The complex dynamical behaviors of MFNN are found by numerical simulations. An equivalent circuit for the neural network is constructed to verify the accuracy of the numerical simulation. In addition, a medical image encryption scheme based on MFNN is proposed. The encryption scheme performs a bit-level permutation of the original image using a chaotic sequence randomly generated by the chaotic system. Fibonacci $Q$ -matrix and central diffusion algorithm are used to diffuse the permutation image. Through numerical analysis, the maximum entropy of this encryption algorithm reaches 7.99, and the correlation is close to zero, which proves the resistance of the algorithm to statistical attacks. The algorithm takes only 3.9 s to encrypt an 8-bit medical image of 320 × 320 size on Windows 10 operating system. Experimental results show that the proposed encryption scheme is very secure and has good applications in medical image encryption.

22 April 2025 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YWYanfeng Wang
Yanfeng Wang
KTKefan Tao
Kefan Tao
ZWZicheng Wang
Zicheng Wang
JSJunwei Sun
Junwei Sun
Current memristive circuits for biological decision-making only consider simple situations and do not take into account how the organisms themselves learn these behaviors. In this article, a memristor-based generalized fuzzy min–max (GFMM) neural network circuit of biology with multiobjective decision is designed, imprinting learning is taken into account. The designed circuit is mainly composed of imprinting learning module, generalization and differentiation learning module, multimodal learning module, behavioral decision module, graded response and feedback module. Behavioral signals are converted into high-intensity and low-intensity learning signals by imprinting learning module, which are output to multimodal learning module for multiple processes. The generalization and differentiation learning module is designed to better analyze the learning signals. Multiple factors are processed by behavior decision module, different behaviors are output based on GFMM neural network. The feasibility of the circuit is verified by PSpice, which provides a reference for biomimetic robots in learning, decision-making, and industrial firefighting.

18 December 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
YWYanfeng Wang
Yanfeng Wang
PSPengke Su
Pengke Su
ZWZicheng Wang
Zicheng Wang
JSJunwei Sun
Junwei Sun
With the rapid development of intelligent information technology, it is significant to construct neural network models that conform to biological characteristics. In this paper, a memoristor model with tunable multistable properties is proposed. By changing the memory parameters, the number of multistable states can be adjusted. Based on the memoristor, an asymmetric memristive FN-HNN neural network (MFNHNN) containing five neurons is constructed. The fundamental dynamical theories, such as equilibrium points, bifurcation diagrams and Lyapunov exponents, are used to reveal the complex dynamic behaviours of MFNHNN. The different dynamic behaviors with coupling intensity control, the tunable coexistence of infinite chaotic attractors and the coexistence of initially controlled chaos and periodic attractors are observed. Furthermore, the equivalent circuit of MFNHNN is implemented. On the basis of random chaotic sequences, an image encryption scheme combining Arnold mapping and diagonal diffusion algorithm is proposed. The findings indicate that the proposed scheme exhibits superior encryption performance, rendering it suitable for application in remote sensing information security.

26 August 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
JSJunwei Sun
Junwei Sun
KTKefan Tao
Kefan Tao
Shiping WenShiping Wen
Shiping Wen
ZWZicheng Wang
Zicheng Wang
YWYanfeng Wang
Yanfeng Wang
Current biological behavior models only take the external environment information as the basis for decision-making, ignoring the internal emotional state information. A memristor-based cerebellar model articulation controller (CMAC) neural network circuit of artificial fish behavioral decision is designed, and fuzzy emotion is taken into account. The designed circuit is mainly composed of voltage selection modules, fuzzy processing modules, synaptic neuron modules, eigen quantity modules and feedback modules. CMAC neural network is used as learning criteria and the learning subspace voltage with emotional generalization properties outputs to synaptic neural module. By utilizing the nonvolatility and thresholding properties of the memristor, the weights in the neural network are changed to enable the artificial fish to perform primary and secondary learning under specific emotional voltages. The feasibility of the above circuit is verified by PSpice simulation software. The artificial life and biological intelligence behavior are integrated by the memristor-based CMAC neural network circuit. It provides a reliable theory and basis for the emotional behavior of bionic robots.

25 September 2025 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
JSJunwei Sun
Junwei Sun
YCYu Chen
Yu Chen
ZWZicheng Wang
Zicheng Wang
YWYanfeng Wang
Yanfeng Wang
By boosting reactions to stimuli, sensitization helps organisms adapt both physically and mentally. It is a crucial mechanism for dealing with environmental shifts and dangers. Although most memristor-based neural networks only consider the processes of habituation and dehabituation. However, the phenomenon of sensitization corresponding to habituation tends to be neglected. A memristor-based context-dependent sensitization and system desensitization neural network circuit is designed in this article. The circuit consists of sensitization module, sensitization generalization module, context-dependent module, and system desensitization module. First, when stronger stimuli appear repeatedly, the sensitization function of increasing the intensity of individual responses is realized through the sensitization module. Second, when new stimuli that are similar to the original stimuli appear, sensitization also occur. In addition, when the context changes, the effects on sensitization and biological responses are achieved through context-dependent modules. Finally, reduction of anxiety responses associated with specific stimuli is achieved through systematic desensitization of organisms using the principle of reciprocal inhibition. The simulation results of PSPICE verify the above functions. The circuit provides a reference for bionic emotional robots in neural computing and industrial applications.