Li Lv
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Li Lv has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Hui Wang
Nanchang Institute of Technology
5 shared publications - Ivan Lee
UniSA STEM, University of South Australia, Adelaide, SA, Australia
3 shared publications - Jeng-Shyang Pan
Shandong University of Science and Technology
3 shared publications Jia Zhao
Nanchang Institute of Technology
3 shared publicationsPing Kang
Nanchang Institute of Technology
3 shared publications- Renbin Xiao
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
3 shared publications
Latest Publications
- Open Access
- 10 March 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (5)
Constrained multi-objective wolf pack algorithm based on cooperative optimization and tiered hunting
In tackling constrained multi-objective optimization problems, conventional multi-objective wolf pack algorithm often exhibits poor feasibility and diversity, primarily due to the lack of explicit constraint-handling mechanisms and strong reliance on the leader wolf leading to population aggregation. To overcome these issues, this paper proposes a constrained multi-objective wolf pack algorithm based on cooperative optimization and tiered hunting (CTCMOWPA). The cooperative optimization technique is designed to balance exploration of the infeasible region and exploitation within the feasible region. It maintains two cooperative populations with distinct roles. The main population preserves feasibility by applying the CDP. The secondary population first explores the unconstrained Pareto Front and then employs an adaptive $$\varepsilon$$ constraint-handling method to guide the search toward feasible regions. Moreover, information exchange between these populations enhances adaptability to diverse constraints. Additionally, a tiered hunting strategy categorizes wolves into elite wolves characterized by lower fitness that besiege the leader wolf to inherit its information, and exploration wolves distinguished by higher fitness that are dually guided by the leader and elite wolves, thereby suppressing aggregation while maintaining diversity and convergence. Experimental comparisons with six advanced algorithms on three benchmark suites demonstrate that CTCMOWPA achieves the best IGD values on 19 out of 38 test problems and outperforms the comparison algorithms in feasibility and diversity.- 10 March 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (5)
Open AccessConstrained multi-objective wolf pack algorithm based on cooperative optimization and tiered hunting
In tackling constrained multi-objective optimization problems, conventional multi-objective wolf pack algorithm often exhibits poor feasibility and diversity, primarily due to the lack of explicit constraint-handling mechanisms and strong reliance on the leader wolf leading to population aggregation. To overcome these issues, this paper proposes a constrained multi-objective wolf pack algorithm based on cooperative optimization and tiered hunting (CTCMOWPA). The cooperative optimization technique is designed to balance exploration of the infeasible region and exploitation within the feasible region. It maintains two cooperative populations with distinct roles. The main population preserves feasibility by applying the CDP. The secondary population first explores the unconstrained Pareto Front and then employs an adaptive $$\varepsilon$$ constraint-handling method to guide the search toward feasible regions. Moreover, information exchange between these populations enhances adaptability to diverse constraints. Additionally, a tiered hunting strategy categorizes wolves into elite wolves characterized by lower fitness that besiege the leader wolf to inherit its information, and exploration wolves distinguished by higher fitness that are dually guided by the leader and elite wolves, thereby suppressing aggregation while maintaining diversity and convergence. Experimental comparisons with six advanced algorithms on three benchmark suites demonstrate that CTCMOWPA achieves the best IGD values on 19 out of 38 test problems and outperforms the comparison algorithms in feasibility and diversity. - 9 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-17
Density peaks clustering algorithm with neighborhood optimization and micro-cluster merging
- 9 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-17
Density peaks clustering algorithm with neighborhood optimization and micro-cluster merging
- 5 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Multi-modal multi-objective firefly algorithm with multi-stage niches and route planning application
- 5 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Multi-modal multi-objective firefly algorithm with multi-stage niches and route planning application
- 26 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (15) , 30005-30019
Decomposed Multiobjective Wolf Pack Algorithm for Resource Allocation and Task Scheduling in Computing Networks
In computing networks, resource allocation disorder and task scheduling imbalance can lead to problems such as long latency, high energy consumption, and high cost. To address these issues, a computing network model integrating non-orthogonal multiple access and wireless charging at base stations is constructed, and a decomposed multi-objective wolf pack algorithm is proposed to jointly optimize resource allocation and task scheduling. The uplink of the network uses non-orthogonal multiple access technology, which allows multiple users to share the same sub-channel and greatly improves the efficiency of spectrum utilization. The introduction of wireless charging technology at the base station ensures that users can complete their computing tasks without interruption and reduces maintenance costs. In the algorithm design, the decomposition strategy is introduced into the multi-objective wolf pack algorithm to screen the initial population by polynomial mutation operator and differential evolution operator to improve the diversity of the initial population. To help the algorithm escape from local optimum, the mutation operator is introduced to generate new elements, so that the population can explore a wider solution space. The experimental results show that when the number of users reaches 40, the algorithm achieves average improvements of over 22.47%, 27.82%, and 25.58% in computing delay, energy consumption, and cost, respectively. Compared with the other 10 algorithms, it significantly improves the user experience and resource utilization.
- 26 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (15) , 30005-30019
Decomposed Multiobjective Wolf Pack Algorithm for Resource Allocation and Task Scheduling in Computing Networks
In computing networks, resource allocation disorder and task scheduling imbalance can lead to problems such as long latency, high energy consumption, and high cost. To address these issues, a computing network model integrating non-orthogonal multiple access and wireless charging at base stations is constructed, and a decomposed multi-objective wolf pack algorithm is proposed to jointly optimize resource allocation and task scheduling. The uplink of the network uses non-orthogonal multiple access technology, which allows multiple users to share the same sub-channel and greatly improves the efficiency of spectrum utilization. The introduction of wireless charging technology at the base station ensures that users can complete their computing tasks without interruption and reduces maintenance costs. In the algorithm design, the decomposition strategy is introduced into the multi-objective wolf pack algorithm to screen the initial population by polynomial mutation operator and differential evolution operator to improve the diversity of the initial population. To help the algorithm escape from local optimum, the mutation operator is introduced to generate new elements, so that the population can explore a wider solution space. The experimental results show that when the number of users reaches 40, the algorithm achieves average improvements of over 22.47%, 27.82%, and 25.58% in computing delay, energy consumption, and cost, respectively. Compared with the other 10 algorithms, it significantly improves the user experience and resource utilization.
- 8 February 2025
- Published by Springer Nature
- p. 296-306
Feature Intracorrelation and Weighted Mahalanobis Distance for Fuzzy Support Vector Machine
- 8 February 2025
- Published by Springer Nature
- p. 296-306
Feature Intracorrelation and Weighted Mahalanobis Distance for Fuzzy Support Vector Machine
- 8 February 2025
- Published by Springer Nature
- p. 283-295
Dual-Population-Iterating and Preys-Gathering MPA for XGBoost Optimization
- 8 February 2025
- Published by Springer Nature
- p. 283-295
Dual-Population-Iterating and Preys-Gathering MPA for XGBoost Optimization
- 17 February 2024
- Published by Springer Nature in Cluster Computing
- Vol. 27 (5) , 5933-5951
A large-scale multi-objective firefly algorithm based on reward and punishment mechanisms and adaptive dimensional reorganization
- 17 February 2024
- Published by Springer Nature in Cluster Computing
- Vol. 27 (5) , 5933-5951
A large-scale multi-objective firefly algorithm based on reward and punishment mechanisms and adaptive dimensional reorganization
- 22 November 2023
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 36 (6)
Adaptive kernel density estimation weighted twin support vector machine and its sample screening method
Summary: In twin support vector machines (TSVM), noise blurs the boundary between positive and negative samples, increasing the probability of classification errors. In this article, we propose an adaptive kernel density estimation weighted twin support vector machine(AKWTSVM). AKWTSVM uses KDE based on K‐nearest neighbor estimation to calculate the probability density of samples. It automatically selects the optimal bandwidth based on the local density of the samples to improve the robustness of the algorithm. However, TSVM has high time complexity, to reduce the time costs, a sample screening method is proposed for AKWTSVM, named AKWTSVM‐SSM, which is based on the overall distance and local density, and reduces the time costs of the algorithm by reducing the sample size while ensuring the accuracy of the algorithm. The experiment with differently scaled noise environments of 0%, 5%, 10%, 15%, and 20% on 12 UCI datasets validate the accuracy and running time of AKWTSVM and AKWTSVM‐SSM. Experimental results prove the effectiveness and robustness of AKWTSVM, the robustness of AKWTSVM‐SSM, and its applicability to large‐scale datasets.
- 22 November 2023
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 36 (6)
Adaptive kernel density estimation weighted twin support vector machine and its sample screening method
Summary: In twin support vector machines (TSVM), noise blurs the boundary between positive and negative samples, increasing the probability of classification errors. In this article, we propose an adaptive kernel density estimation weighted twin support vector machine(AKWTSVM). AKWTSVM uses KDE based on K‐nearest neighbor estimation to calculate the probability density of samples. It automatically selects the optimal bandwidth based on the local density of the samples to improve the robustness of the algorithm. However, TSVM has high time complexity, to reduce the time costs, a sample screening method is proposed for AKWTSVM, named AKWTSVM‐SSM, which is based on the overall distance and local density, and reduces the time costs of the algorithm by reducing the sample size while ensuring the accuracy of the algorithm. The experiment with differently scaled noise environments of 0%, 5%, 10%, 15%, and 20% on 12 UCI datasets validate the accuracy and running time of AKWTSVM and AKWTSVM‐SSM. Experimental results prove the effectiveness and robustness of AKWTSVM, the robustness of AKWTSVM‐SSM, and its applicability to large‐scale datasets.
- Open Access
- 24 July 2023
- Published by Springer Nature in Research Square
A Large-scale multi-objective firefly algorithm based on Reward and punishment mechanisms and Adaptive dimensional reorganization
Multi-objective optimization problems with large-scale variables are the focus and difficulty of current research in the field of multi-objective evolutionary algorithms. In order to cope with the problem of "dimensional catastrophe", this paper proposes a large-scale multi-objective firefly algorithm based on reward and punishment mechanisms and adaptive dimensional reorganization. First, a reward and punishment mechanisms is proposed to make full use of the information of the solution itself, so that the population can break the constraint and rapidly approach the Pareto frontier, effectively improving the convergence of the population; then, an adaptive dimensional reorganization mechanism is proposed to select individuals with large differences according to different iteration periods to interact and learn from each other, effectively improving the diversity of the population. In the experimental part, to verify the effectiveness of the algorithm, the UF series and the variable expanded ZDT series, 15 test problems are selected for simulation experiments and compared with 8 advanced large-scale optimization algorithms, the results show that L-MOFA-RA has the advantages of fast convergence speed and high convergence accuracy, and the comprehensive experimental results show that compared with the comparison algorithm L-MOFA-RA has better optimization performance. The comprehensive experimental results show that L-MOFA-RA has better optimization performance compared to the comparison algorithm.
- 24 July 2023
- Published by Springer Nature in Research Square
Open AccessA Large-scale multi-objective firefly algorithm based on Reward and punishment mechanisms and Adaptive dimensional reorganization
Multi-objective optimization problems with large-scale variables are the focus and difficulty of current research in the field of multi-objective evolutionary algorithms. In order to cope with the problem of "dimensional catastrophe", this paper proposes a large-scale multi-objective firefly algorithm based on reward and punishment mechanisms and adaptive dimensional reorganization. First, a reward and punishment mechanisms is proposed to make full use of the information of the solution itself, so that the population can break the constraint and rapidly approach the Pareto frontier, effectively improving the convergence of the population; then, an adaptive dimensional reorganization mechanism is proposed to select individuals with large differences according to different iteration periods to interact and learn from each other, effectively improving the diversity of the population. In the experimental part, to verify the effectiveness of the algorithm, the UF series and the variable expanded ZDT series, 15 test problems are selected for simulation experiments and compared with 8 advanced large-scale optimization algorithms, the results show that L-MOFA-RA has the advantages of fast convergence speed and high convergence accuracy, and the comprehensive experimental results show that compared with the comparison algorithm L-MOFA-RA has better optimization performance. The comprehensive experimental results show that L-MOFA-RA has better optimization performance compared to the comparison algorithm.
- 20 July 2023
- Published by Springer Nature
- p. 385-395
Firefly Algorithm Based on Division of Labor for Solving Constrained Optimization Problems
- 20 July 2023
- Published by Springer Nature
- p. 385-395
Firefly Algorithm Based on Division of Labor for Solving Constrained Optimization Problems