Jiahao Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiahao Fan has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Yanan Sun
College of Computer Science, Sichuan University, Chengdu, China
7 shared publications - Tan Wang
Space Technology (Jilin) Limited Company, Jilin, China
6 shared publications - Ying Li
College of Computer Science and Technology, Jilin University, Changchun, People’s Republic of China
5 shared publications Ying Li
Affiliations College of Computer Science and Technology, Jilin University, Changchun, China, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
3 shared publications- Jiancheng Lv
Sichuan University
2 shared publications - Jiyuan Liu
State Key Laboratory of Oral Diseases, the National Center for Stomatology, the National Clinical Research Center for Oral Diseases, the Sichuan Provincial Engineering Research Center of Smart Diagnosis and Treatment for Oral Diseases, and the Department of Oral Surgery, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, China
2 shared publications
Latest Publications
- 29 October 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A two-stage evolutionary algorithm with subregion-aware selection for constrained multi-objective optimization
- 29 October 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 204
A two-stage evolutionary algorithm with subregion-aware selection for constrained multi-objective optimization
- Open Access
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
A Two-Stage Evolutionary Algorithm with Subregion- Aware Selection for Constrained Multi-objective Optimization
Balancing convergence, diversity, and feasibility is a critical challenge in constrained multi-objective optimization, particularly when dealing with discontinuous or degenerate Pareto fronts (PFs). Constrained multi-objective evolutionary algorithms (CMOEAs) are commonly employed to tackle such problems, yet most of them prioritize convergence and feasibility while overlooking diversity. To address this gap, we propose a novel two-stage hybrid tri-population CMOEA (TS-HC3) that enhances both exploration and exploitation to achieve well-converged, diverse, and feasible solutions. In the first stage, a dual-population exploration mechanism is presented to promotes broad exploration and accelerate the discovery of promising feasible regions. In the second stage, a tri-population exploitation mechanism is introduced, incorporating a novel subregion-aware environmental selection strategy that adaptively preserves solution distribution and uniformity across the PF. A two-level multi-armed bandit strategy is proposed to dynamically select the most suitable parent population and variation operator based on real-time evolutionary feedback. Finally, a differential evolution based flexible genetic operator is designed to enhance exploration in sparse feasible regions. Extensive experiments on widely used benchmarks demonstrate that TS-HC3 significantly outperforms state-of-the-art CMOEAs, particularly on problems with discontinuous or degenerate PFs. The effectiveness of TS-HC3 is further validated on a multi-unmanned surface vehicle collaborative path planning problem, highlighting its practical applicability in complex real-world scenarios. Moreover, an ablation study is conducted to validate the contribution of each individual component within TS-HC3.
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Two-Stage Evolutionary Algorithm with Subregion- Aware Selection for Constrained Multi-objective Optimization
Balancing convergence, diversity, and feasibility is a critical challenge in constrained multi-objective optimization, particularly when dealing with discontinuous or degenerate Pareto fronts (PFs). Constrained multi-objective evolutionary algorithms (CMOEAs) are commonly employed to tackle such problems, yet most of them prioritize convergence and feasibility while overlooking diversity. To address this gap, we propose a novel two-stage hybrid tri-population CMOEA (TS-HC3) that enhances both exploration and exploitation to achieve well-converged, diverse, and feasible solutions. In the first stage, a dual-population exploration mechanism is presented to promotes broad exploration and accelerate the discovery of promising feasible regions. In the second stage, a tri-population exploitation mechanism is introduced, incorporating a novel subregion-aware environmental selection strategy that adaptively preserves solution distribution and uniformity across the PF. A two-level multi-armed bandit strategy is proposed to dynamically select the most suitable parent population and variation operator based on real-time evolutionary feedback. Finally, a differential evolution based flexible genetic operator is designed to enhance exploration in sparse feasible regions. Extensive experiments on widely used benchmarks demonstrate that TS-HC3 significantly outperforms state-of-the-art CMOEAs, particularly on problems with discontinuous or degenerate PFs. The effectiveness of TS-HC3 is further validated on a multi-unmanned surface vehicle collaborative path planning problem, highlighting its practical applicability in complex real-world scenarios. Moreover, an ablation study is conducted to validate the contribution of each individual component within TS-HC3.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (5) , 2583-2596
A Multiagent Transformer-Based Algorithm for Multitask Dynamic Scheduling With Constrained Machines
Modern manufacturers often require handling multiple tasks simultaneously under dynamic environments by sharing constrained machines. Existing multitask scheduling algorithms typically focus on transferring knowledge among multiple tasks. However, these algorithms overlook the need for collaborative multitasking efforts required to share constrained machines. To overcome this limitation, we propose a multiagent transformer (MAT)-based algorithm to solve multitask dynamic scheduling with constrained machines. Specifically, we first formulate the multitask scheduling problem as a sequential multiagent decision-making process, enabling agents to make collaborative decisions by accessing the actions of others. Furthermore, a joint policy network is developed to support the agents in adaptively selecting the appropriate heuristic for each task. It improves the decision-making quality by enabling agents to leverage common and task-specific knowledge. In addition, a comprehensive reward function is designed to guide the learning of a joint policy network for collaborative decision-making across tasks. This ensures that agents holistically consider the objectives of all tasks during the learning process. With these designs, the proposed algorithm can effectively address multiple tasks through collaborative machine sharing. The proposed algorithm is evaluated against 14 state-of-the-art competitors on 270 instances with varying scales. The results confirm that the proposed algorithm outperforms all competitors on each instance. In addition, the ablation study demonstrates the effectiveness of distinct reward mechanisms, revealing that the joint policy network makes more informed decisions by leveraging both individual and common knowledge.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (5) , 2583-2596
A Multiagent Transformer-Based Algorithm for Multitask Dynamic Scheduling With Constrained Machines
Modern manufacturers often require handling multiple tasks simultaneously under dynamic environments by sharing constrained machines. Existing multitask scheduling algorithms typically focus on transferring knowledge among multiple tasks. However, these algorithms overlook the need for collaborative multitasking efforts required to share constrained machines. To overcome this limitation, we propose a multiagent transformer (MAT)-based algorithm to solve multitask dynamic scheduling with constrained machines. Specifically, we first formulate the multitask scheduling problem as a sequential multiagent decision-making process, enabling agents to make collaborative decisions by accessing the actions of others. Furthermore, a joint policy network is developed to support the agents in adaptively selecting the appropriate heuristic for each task. It improves the decision-making quality by enabling agents to leverage common and task-specific knowledge. In addition, a comprehensive reward function is designed to guide the learning of a joint policy network for collaborative decision-making across tasks. This ensures that agents holistically consider the objectives of all tasks during the learning process. With these designs, the proposed algorithm can effectively address multiple tasks through collaborative machine sharing. The proposed algorithm is evaluated against 14 state-of-the-art competitors on 270 instances with varying scales. The results confirm that the proposed algorithm outperforms all competitors on each instance. In addition, the ablation study demonstrates the effectiveness of distinct reward mechanisms, revealing that the joint policy network makes more informed decisions by leveraging both individual and common knowledge.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9143-9153
OT-SAN: One Timestep Spiking Actor Network With Mask-Adaptive Global Connection and Dynamic Thresholds
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 9143-9153
OT-SAN: One Timestep Spiking Actor Network With Mask-Adaptive Global Connection and Dynamic Thresholds
- 8 November 2025
- Published by Elsevier in Swarm and Evolutionary Computation
- Vol. 99
A two-stage ensemble evolutionary algorithm for constrained multi-objective optimization
- 8 November 2025
- Published by Elsevier in Swarm and Evolutionary Computation
- Vol. 99
A two-stage ensemble evolutionary algorithm for constrained multi-objective optimization
- 23 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
A gradient-based lightweight network automated design method for facial expression recognition
- 23 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
A gradient-based lightweight network automated design method for facial expression recognition
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 30 (1) , 106-120
Evolutionary Multiobjective Spiking Neural Architecture Search for Image Classification
Spiking neural networks (SNNs) have the merit of energy efficiency, and have been widely used for various real-world applications. Similar to other types of neural networks, the performance of SNN is also significantly decided by its architecture. In this paper, we propose an Evolutionary Multi-objective Spiking Neural Architecture Search (EMO-SNAS) method that completely enables the automatic design of SNN architectures with both high performance and low power consumption. To achieve this, we first design a variable-length encoding strategy for SNNs, addressing the issue that traditional encoding strategies need to manually set the depth in advance. Furthermore, we propose an exploitation operator focusing on the local search for the variable-length encoding, as well as an exploration operator focusing on the global search based on the temporal expansion. Based on NSGA-II, EMO-SNAS can greatly balance the performance and power consumption during the architecture design. Experiments on three widely used image classification datasets show that EMO-SNAS can achieve the best among the state-of-the-art methods. Specifically, EMO-SNAS gains 0.45%, 0.26%, and 7.52% in terms of classification accuracy, yet significantly contributes to 33%, 29%, and 12% fewer spike numbers on CIFAR10, CIFAR100, and TinyImageNet datasets. Ablation studies show that the temporal expansion can improve the performance of EMO-SNAS. Moreover, the measurement of power consumption and theoretical convergence of EMO-SNAS are also discussed to justify its component design. In addition, with EMO-SNAS, the impact of initial channels for SNNs is also systemically investigated, based on which a conclusion against existing consensus is achieved. The source code is available at https://github.com/songxt3/EMO-SNAS.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 30 (1) , 106-120
Evolutionary Multiobjective Spiking Neural Architecture Search for Image Classification
Spiking neural networks (SNNs) have the merit of energy efficiency, and have been widely used for various real-world applications. Similar to other types of neural networks, the performance of SNN is also significantly decided by its architecture. In this paper, we propose an Evolutionary Multi-objective Spiking Neural Architecture Search (EMO-SNAS) method that completely enables the automatic design of SNN architectures with both high performance and low power consumption. To achieve this, we first design a variable-length encoding strategy for SNNs, addressing the issue that traditional encoding strategies need to manually set the depth in advance. Furthermore, we propose an exploitation operator focusing on the local search for the variable-length encoding, as well as an exploration operator focusing on the global search based on the temporal expansion. Based on NSGA-II, EMO-SNAS can greatly balance the performance and power consumption during the architecture design. Experiments on three widely used image classification datasets show that EMO-SNAS can achieve the best among the state-of-the-art methods. Specifically, EMO-SNAS gains 0.45%, 0.26%, and 7.52% in terms of classification accuracy, yet significantly contributes to 33%, 29%, and 12% fewer spike numbers on CIFAR10, CIFAR100, and TinyImageNet datasets. Ablation studies show that the temporal expansion can improve the performance of EMO-SNAS. Moreover, the measurement of power consumption and theoretical convergence of EMO-SNAS are also discussed to justify its component design. In addition, with EMO-SNAS, the impact of initial channels for SNNs is also systemically investigated, based on which a conclusion against existing consensus is achieved. The source code is available at https://github.com/songxt3/EMO-SNAS.
- 22 November 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 264
Classification of sewer pipe defects based on an automatically designed convolutional neural network
- 22 November 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 264
Classification of sewer pipe defects based on an automatically designed convolutional neural network
- Open Access
- 27 December 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (12) , e0279438
A novel Q-learning algorithm based on improved whale optimization algorithm for path planning
Q-learning is a classical reinforcement learning algorithm and one of the most important methods of mobile robot path planning without a prior environmental model. Nevertheless, Q-learning is too simple when initializing Q-table and wastes too much time in the exploration process, causing a slow convergence speed. This paper proposes a new Q-learning algorithm called the Paired Whale Optimization Q-learning Algorithm (PWOQLA) which includes four improvements. Firstly, to accelerate the convergence speed of Q-learning, a whale optimization algorithm is used to initialize the values of a Q-table. Before the exploration process, a Q-table which contains previous experience is learned to improve algorithm efficiency. Secondly, to improve the local exploitation capability of the whale optimization algorithm, a paired whale optimization algorithm is proposed in combination with a pairing strategy to speed up the search for prey. Thirdly, to improve the exploration efficiency of Q-learning and reduce the number of useless explorations, a new selective exploration strategy is introduced which considers the relationship between current position and target position. Fourthly, in order to balance the exploration and exploitation capabilities of Q-learning so that it focuses on exploration in the early stage and on exploitation in the later stage, a nonlinear function is designed which changes the value of ε in ε-greedy Q-learning dynamically based on the number of iterations. Comparing the performance of PWOQLA with other path planning algorithms, experimental results demonstrate that PWOQLA achieves a higher level of accuracy and a faster convergence speed than existing counterparts in mobile robot path planning. The code will be released at https://github.com/wanghanyu0526/improveQL.git.
- 27 December 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (12) , e0279438
Open AccessA novel Q-learning algorithm based on improved whale optimization algorithm for path planning
Q-learning is a classical reinforcement learning algorithm and one of the most important methods of mobile robot path planning without a prior environmental model. Nevertheless, Q-learning is too simple when initializing Q-table and wastes too much time in the exploration process, causing a slow convergence speed. This paper proposes a new Q-learning algorithm called the Paired Whale Optimization Q-learning Algorithm (PWOQLA) which includes four improvements. Firstly, to accelerate the convergence speed of Q-learning, a whale optimization algorithm is used to initialize the values of a Q-table. Before the exploration process, a Q-table which contains previous experience is learned to improve algorithm efficiency. Secondly, to improve the local exploitation capability of the whale optimization algorithm, a paired whale optimization algorithm is proposed in combination with a pairing strategy to speed up the search for prey. Thirdly, to improve the exploration efficiency of Q-learning and reduce the number of useless explorations, a new selective exploration strategy is introduced which considers the relationship between current position and target position. Fourthly, in order to balance the exploration and exploitation capabilities of Q-learning so that it focuses on exploration in the early stage and on exploitation in the later stage, a nonlinear function is designed which changes the value of ε in ε-greedy Q-learning dynamically based on the number of iterations. Comparing the performance of PWOQLA with other path planning algorithms, experimental results demonstrate that PWOQLA achieves a higher level of accuracy and a faster convergence speed than existing counterparts in mobile robot path planning. The code will be released at https://github.com/wanghanyu0526/improveQL.git.
- 13 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (17) , 18754-18776
Global chaotic bat algorithm for feature selection
- 13 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (17) , 18754-18776
Global chaotic bat algorithm for feature selection