Manchun Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Manchun Tan has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Desheng Xu
8 shared publicationsJianglian Xiang
College of Information Science and Technology Jinan University Guangzhou China
5 shared publications- Qiu Peng
Department of Mathematics Jinan University Guangzhou China
4 shared publications Yunfeng Liu
College of Information Science and Technology Jinan University Guangzhou China
4 shared publicationsZhiqiang Song
College of Information Science and Technology, Jinan University, Guangzhou 510632, China
4 shared publications- Jianglian Xiang
Department of Mathematics and Artificial Intelligence, Chongqing University of Arts and Sciences, Chongqing 402100, China
3 shared publications
Latest Publications
- 1 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
Synchronization of neutral-type Clifford-valued inertial neural networks with mixed delays by non-reduced-order and non-separation approaches
- 1 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
Synchronization of neutral-type Clifford-valued inertial neural networks with mixed delays by non-reduced-order and non-separation approaches
- 10 August 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114 (15) , 1022
Complex-valued recurrent neural networks with multiple-discontinuity activation functions and time delays: multistability analysis and estimation of attraction domains
- 10 August 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114 (15) , 1022
Complex-valued recurrent neural networks with multiple-discontinuity activation functions and time delays: multistability analysis and estimation of attraction domains
- Open Access
- 3 June 2026
- Published by Universal Wiser Publisher Pte. Ltd in Contemporary Mathematics
- p. 3881-3911
Almost Periodic Uniform Stability of Delayed Fractional-Order Quaternion-Valued Fuzzy Neural Networks with Stochastic Terms Via a Direct Method
Fractional-order neural networks are vital for modeling neuronal interactions in information processing, and exploring their existence and stability remains a key research challenge. This paper aims to achieve almost periodic uniform stability for fractional-order stochastic fuzzy neural networks in the quaternion field, which is crucial for ensuring reliable and sustained periodic performance in dynamic environments, essential for applications like simulating biological neural systems. We employ a direct method without decomposing quaternion-valued networks into real-valued counterparts, and by leveraging fixed point theorem, fundamental fractional calculus properties, and various inequality techniques, we establish the existence of a unique almost periodic solution under specific conditions. Additionally, by constructing an error system and applying uniform stability definitions with inequality methods, we derive conditions for almost periodic uniform stability. Finally, MATLAB simulations validate the feasibility and accuracy of our results.
- 3 June 2026
- Published by Universal Wiser Publisher Pte. Ltd in Contemporary Mathematics
- p. 3881-3911
Open AccessAlmost Periodic Uniform Stability of Delayed Fractional-Order Quaternion-Valued Fuzzy Neural Networks with Stochastic Terms Via a Direct Method
Fractional-order neural networks are vital for modeling neuronal interactions in information processing, and exploring their existence and stability remains a key research challenge. This paper aims to achieve almost periodic uniform stability for fractional-order stochastic fuzzy neural networks in the quaternion field, which is crucial for ensuring reliable and sustained periodic performance in dynamic environments, essential for applications like simulating biological neural systems. We employ a direct method without decomposing quaternion-valued networks into real-valued counterparts, and by leveraging fixed point theorem, fundamental fractional calculus properties, and various inequality techniques, we establish the existence of a unique almost periodic solution under specific conditions. Additionally, by constructing an error system and applying uniform stability definitions with inequality methods, we derive conditions for almost periodic uniform stability. Finally, MATLAB simulations validate the feasibility and accuracy of our results.
- 10 February 2026
- Published by Wiley in Mathematical Methods in the Applied Sciences
- Vol. 49 (10) , 10108-10132
Finite‐Time Intra‐Layer and Inter‐Layer Synchronization of Fractional‐Order Multi‐Layer Networks With Time‐Varying Delays
This paper focuses on the finite‐time intra‐layer synchronization (FTALS) and finite‐time inter‐layer synchronization (FTRLS) of fractional‐order multi‐layer networks (FOMLNs) with time‐varying delays. To begin, two forms of continuous control schemes with time‐varying delays are proposed: State feedback control and fractional‐order adaptive control. Following that, based on the finite‐time stability theory and utilizing fractional‐order differential inequalities and other inequality approaches, several new sufficient conditions for intra‐layer synchronization (ALS) and inter‐layer synchronization (RLS) of FOMLNs in finite time are given. Furthermore, the control gains here can be widely selected, and the upper bounds of the settling times for FTALS and FTRLS are explicitly derived in terms of the control gains and network parameters. Lastly, the viability of the theoretical results is demonstrated by two numerical examples.
- 10 February 2026
- Published by Wiley in Mathematical Methods in the Applied Sciences
- Vol. 49 (10) , 10108-10132
Finite‐Time Intra‐Layer and Inter‐Layer Synchronization of Fractional‐Order Multi‐Layer Networks With Time‐Varying Delays
This paper focuses on the finite‐time intra‐layer synchronization (FTALS) and finite‐time inter‐layer synchronization (FTRLS) of fractional‐order multi‐layer networks (FOMLNs) with time‐varying delays. To begin, two forms of continuous control schemes with time‐varying delays are proposed: State feedback control and fractional‐order adaptive control. Following that, based on the finite‐time stability theory and utilizing fractional‐order differential inequalities and other inequality approaches, several new sufficient conditions for intra‐layer synchronization (ALS) and inter‐layer synchronization (RLS) of FOMLNs in finite time are given. Furthermore, the control gains here can be widely selected, and the upper bounds of the settling times for FTALS and FTRLS are explicitly derived in terms of the control gains and network parameters. Lastly, the viability of the theoretical results is demonstrated by two numerical examples.
- Open Access
- 1 December 2025
- Published by Springer Nature in Neural Processing Letters
- Vol. 58 (1)
Design and Analysis of Quaternion-Valued Artificial Neural Networks for Image Encryption/Decryption
- 1 December 2025
- Published by Springer Nature in Neural Processing Letters
- Vol. 58 (1)
Open AccessDesign and Analysis of Quaternion-Valued Artificial Neural Networks for Image Encryption/Decryption
- 19 August 2025
- Published by Springer Nature
- p. 247-257
Multiple $\mu $-Stability of Delayed State-Dependent Switching Neural Networks With Discontinuous Activation Function- 19 August 2025
- Published by Springer Nature
- p. 247-257
Multiple $\mu $-Stability of Delayed State-Dependent Switching Neural Networks With Discontinuous Activation Function- Open Access
- 29 July 2025
- Published by Wiley
Finite-time cluster synchronization of multi-weighted fractional-order coupled two-layer neural networks
The finite-time cluster synchronization (FTCS) problem in multi-weighted fractional-order coupled two-layer neural networks (MFOCTLNNs) is investigated in this paper. It is worth noting that the considered model consists of two-layer networks with distinct topologies and dynamic behaviors, and there exist multiple connections between nodes within each layer. First, by applying fractional-order finite-time convergence lemmas and creating a state-feedback control scheme, we establish a FTCS criterion for the drive network. Subsequently, we compress the nodes in the same cluster of the drive network into a virtual node. In order to achieve the FTCS of MFOCTLNNs, we then design another new delayed controller to synchronize the response network with these virtual nodes. Finally, we provide an illustrative example to validate the effectiveness of the proposed results.
- 29 July 2025
- Published by Wiley
Open AccessFinite-time cluster synchronization of multi-weighted fractional-order coupled two-layer neural networks
The finite-time cluster synchronization (FTCS) problem in multi-weighted fractional-order coupled two-layer neural networks (MFOCTLNNs) is investigated in this paper. It is worth noting that the considered model consists of two-layer networks with distinct topologies and dynamic behaviors, and there exist multiple connections between nodes within each layer. First, by applying fractional-order finite-time convergence lemmas and creating a state-feedback control scheme, we establish a FTCS criterion for the drive network. Subsequently, we compress the nodes in the same cluster of the drive network into a virtual node. In order to achieve the FTCS of MFOCTLNNs, we then design another new delayed controller to synchronize the response network with these virtual nodes. Finally, we provide an illustrative example to validate the effectiveness of the proposed results.