Yanming Fu
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
Yanming Fu has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Chiwen Qu
School of Public Health and Management, Youjiang Medical University for Nationalities, China
4 shared publications - Baohua Huang
School of Computer and Electronic Information, Guangxi University, Nanning 530004, China
2 shared publications - Zhuohang Li
School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
2 shared publications - Bocheng Huang
School of Computer Electronics and Information, Guangxi University, Nanning, China
1 shared publication Danyang Chen
Guangxi Minzu University
1 shared publicationHaiqiang Chen
Computer and Electronic Information College
1 shared publication
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (18) , 43028-43040
MS-MLSIR: A Multiscale Multilevel Approach for Spatiotemporal Data Inference in Sparse Mobile CrowdSensing
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (18) , 43028-43040
MS-MLSIR: A Multiscale Multilevel Approach for Spatiotemporal Data Inference in Sparse Mobile CrowdSensing
- Open Access
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 149203-149215
Reliability-Driven Label Enhancement in Crowdsourcing: Integrating Confidence Filtering and Collaborative Correction
Crowdsourcing has been widely used for labeling data in artificial intelligence and machine learning due to its cost-saving benefits. However, inconsistencies in worker-provided labels degrade the quality of the integrated labels. Most noise correction methods proposed by researchers in recent years focus on training a corrector using subsets of data that are filtered to be clean. These methods depend on limited data to train the corrector model, which inevitably compromises the corrector’s reliability. To address this problem, this paper aims to enhance the reliability of integrated labels by applying a novel noise correction method that uses correctors trained on both clean and noisy subsets. This method comprises two stages: confidence filtering and an improved co-teaching+ algorithm. In the first stage, this method calculates the confidence levels of the integrated labels for each instance in the crowdsourced dataset, and then divides the dataset into clean and noisy subsets according to the confidence level. In the second stage, our method initially trains a corrector, denoted as Cclean, on the clean dataset. Subsequently, Cclean guides the co-teaching+ algorithm to adaptively train two correctors on the complete crowdsourced dataset, which includes both clean and noisy subsets. Finally, the instances in the crowdsourced dataset are corrected by these three correctors. Within this study, comparative experiments have been carried out on fifteen simulated datasets and four real-world datasets. The proposed noise correction method attains the best outcomes on the majority of the datasets evaluated.
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 149203-149215
Open AccessReliability-Driven Label Enhancement in Crowdsourcing: Integrating Confidence Filtering and Collaborative Correction
Crowdsourcing has been widely used for labeling data in artificial intelligence and machine learning due to its cost-saving benefits. However, inconsistencies in worker-provided labels degrade the quality of the integrated labels. Most noise correction methods proposed by researchers in recent years focus on training a corrector using subsets of data that are filtered to be clean. These methods depend on limited data to train the corrector model, which inevitably compromises the corrector’s reliability. To address this problem, this paper aims to enhance the reliability of integrated labels by applying a novel noise correction method that uses correctors trained on both clean and noisy subsets. This method comprises two stages: confidence filtering and an improved co-teaching+ algorithm. In the first stage, this method calculates the confidence levels of the integrated labels for each instance in the crowdsourced dataset, and then divides the dataset into clean and noisy subsets according to the confidence level. In the second stage, our method initially trains a corrector, denoted as Cclean, on the clean dataset. Subsequently, Cclean guides the co-teaching+ algorithm to adaptively train two correctors on the complete crowdsourced dataset, which includes both clean and noisy subsets. Finally, the instances in the crowdsourced dataset are corrected by these three correctors. Within this study, comparative experiments have been carried out on fifteen simulated datasets and four real-world datasets. The proposed noise correction method attains the best outcomes on the majority of the datasets evaluated.
- 8 February 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (2) , 1001-1019
Socially-aware and privacy-preserving multi-objective worker recruitment in mobile crowd sensing
- 8 February 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (2) , 1001-1019
Socially-aware and privacy-preserving multi-objective worker recruitment in mobile crowd sensing
- 24 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (10) , 10735-10748
Hybrid Recruitment Scheme Based on Deep Learning in Vehicular Crowdsensing
Vehicular Crowdsensing (VCS) aims to collect sensing data over a range of areas using a large number of on-board sensors and resources in intelligent vehicles. The mobility of vehicles allows for large-scale mobile sensing data, but it remains a challenging problem to recruit the right participating vehicles and to actively maximize the sensing benefits. In this paper, we formulate the vehicle recruitment problem as the maximizing completion rate with limited budget problem (MCRLB) and prove that it is NP-complete. A hybrid recruitment scheme based on deep learning in vehicular crowdsensing (HR-DLVCS) is proposed in this paper, which consists of two phases: an opportunistic vehicle recruitment phase and a participatory vehicle recruitment phase. In the first phase, a deep learning-based opportunistic vehicle recruitment algorithm (DL-OVR) is proposed to maximize the sensing task completion rate within a limited budget. It aims to recruit the most suitable vehicles to collect sensing data according to their daily movement patterns. In the second phase, a sensing task density-based participatory vehicle recruitment algorithm (STD-PVR) is proposed to reduce the computational complexity of matching vehicles with uncompleted sensing tasks. It is designed to recruit vehicles to arrive at designated locations to complete the sensing tasks within a given budget. Extensive evaluations based on a real-world dataset show that HR-DLVCS achieves higher sensing task completion rate than other baseline approaches in a variety of settings.
- 24 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (10) , 10735-10748
Hybrid Recruitment Scheme Based on Deep Learning in Vehicular Crowdsensing
Vehicular Crowdsensing (VCS) aims to collect sensing data over a range of areas using a large number of on-board sensors and resources in intelligent vehicles. The mobility of vehicles allows for large-scale mobile sensing data, but it remains a challenging problem to recruit the right participating vehicles and to actively maximize the sensing benefits. In this paper, we formulate the vehicle recruitment problem as the maximizing completion rate with limited budget problem (MCRLB) and prove that it is NP-complete. A hybrid recruitment scheme based on deep learning in vehicular crowdsensing (HR-DLVCS) is proposed in this paper, which consists of two phases: an opportunistic vehicle recruitment phase and a participatory vehicle recruitment phase. In the first phase, a deep learning-based opportunistic vehicle recruitment algorithm (DL-OVR) is proposed to maximize the sensing task completion rate within a limited budget. It aims to recruit the most suitable vehicles to collect sensing data according to their daily movement patterns. In the second phase, a sensing task density-based participatory vehicle recruitment algorithm (STD-PVR) is proposed to reduce the computational complexity of matching vehicles with uncompleted sensing tasks. It is designed to recruit vehicles to arrive at designated locations to complete the sensing tasks within a given budget. Extensive evaluations based on a real-world dataset show that HR-DLVCS achieves higher sensing task completion rate than other baseline approaches in a variety of settings.
- Open Access
The RapidIO Routing Strategy Based on the Double-Antibody Group Multi-Objective Artificial Immunity Algorithm
The RapidIO standard is a packet-switching interconnection technology similar to the Internet Protocol (IP) conceptually. It realizes the high-speed transmission of RapidIO packets at the transport layer, but this greatly increases the probability of network blocking. Therefore, it is of great significance to optimize the RapidIO routing strategy. For this problem, this paper proposes a Double-Antibody Group Multi-Objective Artificial Immune Algorithm (DAG-MOAIA), which improves the local search and global search ability of the population by adaptive crossover and adaptive mutation of the double-antibody groups, and uses co-competition of multi-antibody groups to increase the diversity of population. Through DAG-MOAIA, an optimal transmission path from the source node to multiple destination nodes can be selected to solve the Quality Of Service (QoS) problem during data transmission and ensure the QoS of the RapidIO network. Simulation results show that DAG-MOAIA could obtain high-quality solutions to select better routing transmission paths, and exhibit better comprehensive performance in all simulated test networks, which plays a certain role in solving the problem of the RapidIO routing strategy.
Open AccessThe RapidIO Routing Strategy Based on the Double-Antibody Group Multi-Objective Artificial Immunity Algorithm
The RapidIO standard is a packet-switching interconnection technology similar to the Internet Protocol (IP) conceptually. It realizes the high-speed transmission of RapidIO packets at the transport layer, but this greatly increases the probability of network blocking. Therefore, it is of great significance to optimize the RapidIO routing strategy. For this problem, this paper proposes a Double-Antibody Group Multi-Objective Artificial Immune Algorithm (DAG-MOAIA), which improves the local search and global search ability of the population by adaptive crossover and adaptive mutation of the double-antibody groups, and uses co-competition of multi-antibody groups to increase the diversity of population. Through DAG-MOAIA, an optimal transmission path from the source node to multiple destination nodes can be selected to solve the Quality Of Service (QoS) problem during data transmission and ensure the QoS of the RapidIO network. Simulation results show that DAG-MOAIA could obtain high-quality solutions to select better routing transmission paths, and exhibit better comprehensive performance in all simulated test networks, which plays a certain role in solving the problem of the RapidIO routing strategy.
- Open Access
- 7 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 88527-88546
A Discrete Multi-Objective Rider Optimization Algorithm for Hybrid Flowshop Scheduling Problem Considering Makespan, Noise and Dust Pollution
Many optimization algorithms have been proposed to solve hybrid flowshop scheduling problem (HFSP). However, with the development of industry and society, labor right and labor safety have become important problem to consider in production scheduling. So the green HFSP considering makespan, noise and dust pollution becomes an urgent problem to be solved. In this paper, the rider optimization algorithm (ROA) is modified into the multi-objective rider optimization algorithm (MOROA) using Pareto archive and neighborhood sorting techniques. The Pareto archive and neighborhood sorting technology make the Pareto optimal solution set of MOROA have higher coverage and more solutions. Then MOROA is discretized into discrete MOROA (DMOROA) to solve the HFSP considering makespan, noise and dust pollution. DMOROA is tested on 10, 30 and 50 jobs HFSP considering makespan, noise and dust pollution. The test results are compared with two multi-objective algorithms to verify the performance of DMOROA. And the test results verify that the DMOROA is superior to the comparison algorithms in search accuracy, number of non-dominated solutions, diversity of solution set and stability. Therefore, DMOROA is effective in solving multi-objective HFSP considering makespan, noise and dust pollution.
- 7 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 88527-88546
Open AccessA Discrete Multi-Objective Rider Optimization Algorithm for Hybrid Flowshop Scheduling Problem Considering Makespan, Noise and Dust Pollution
Many optimization algorithms have been proposed to solve hybrid flowshop scheduling problem (HFSP). However, with the development of industry and society, labor right and labor safety have become important problem to consider in production scheduling. So the green HFSP considering makespan, noise and dust pollution becomes an urgent problem to be solved. In this paper, the rider optimization algorithm (ROA) is modified into the multi-objective rider optimization algorithm (MOROA) using Pareto archive and neighborhood sorting techniques. The Pareto archive and neighborhood sorting technology make the Pareto optimal solution set of MOROA have higher coverage and more solutions. Then MOROA is discretized into discrete MOROA (DMOROA) to solve the HFSP considering makespan, noise and dust pollution. DMOROA is tested on 10, 30 and 50 jobs HFSP considering makespan, noise and dust pollution. The test results are compared with two multi-objective algorithms to verify the performance of DMOROA. And the test results verify that the DMOROA is superior to the comparison algorithms in search accuracy, number of non-dominated solutions, diversity of solution set and stability. Therefore, DMOROA is effective in solving multi-objective HFSP considering makespan, noise and dust pollution.
- Open Access
- 15 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 19657-19678
Optimal Foraging Algorithm Based on Differential Evolution
The optimal foraging algorithm (OFA) was proposed by summarizing the rules of the animal foraging behavior in a group. Therefore OFA also has the defects of the swarm intelligence algorithm, such as easy to trap into local optimum and low convergence accuracy. In order to overcome these defects, an optimal foraging algorithm based on differential evolution (DEOFA) is proposed. The differential evolution mechanism contains mutation and crossover operators. The mutation and crossover operators are used to accelerate the convergence speed and global search capability of the OFA. The mutation operator is adopted to perform mutation operations centered on the optimal individual of each iteration to raise the convergence accuracy of the OFA. The test results of 30 benchmark functions show that the performance of DEOFA is better than nine compared algorithms in search accuracy, convergence speed and robustness. In order to verify the effectiveness of the DEOFA in solving practical problems, DEOFA is applied to solve the 0-1 knapsack problem. The test results in the six examples of 0-1 knapsack problems indicate that the DEOFA achieves better performance in accuracy, stability and high dimension.
- 15 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 19657-19678
Open AccessOptimal Foraging Algorithm Based on Differential Evolution
The optimal foraging algorithm (OFA) was proposed by summarizing the rules of the animal foraging behavior in a group. Therefore OFA also has the defects of the swarm intelligence algorithm, such as easy to trap into local optimum and low convergence accuracy. In order to overcome these defects, an optimal foraging algorithm based on differential evolution (DEOFA) is proposed. The differential evolution mechanism contains mutation and crossover operators. The mutation and crossover operators are used to accelerate the convergence speed and global search capability of the OFA. The mutation operator is adopted to perform mutation operations centered on the optimal individual of each iteration to raise the convergence accuracy of the OFA. The test results of 30 benchmark functions show that the performance of DEOFA is better than nine compared algorithms in search accuracy, convergence speed and robustness. In order to verify the effectiveness of the DEOFA in solving practical problems, DEOFA is applied to solve the 0-1 knapsack problem. The test results in the six examples of 0-1 knapsack problems indicate that the DEOFA achieves better performance in accuracy, stability and high dimension.
- Open Access
- 14 January 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-22
Modified Atom Search Optimization Based on Immunologic Mechanism and Reinforcement Learning
Atom search optimization algorithm has good searching ability and has been successfully applied to calculate hydrogeological parameters and groundwater dispersion coefficient. Since the atom search optimization algorithm is only based on the atom force motion model in molecular dynamics, it has some shortcomings such as slow search speed and low precision during the later stage of iteration. A modified atom search optimization based on the immunologic mechanism and reinforcement learning is proposed to overcome the abovementioned shortcomings in this paper. The proposed algorithm introduces a vaccine operator to better utilize the dominant position in the current atom population so that the speed, accuracy, and domain search ability of the atom search optimization algorithm can be strengthened. The reinforcement learning operator is applied to dynamically adjust the vaccination probability to balance the global exploration ability and local exploitation ability. The test results of 21 benchmark functions confirm that the performance of the proposed algorithm is superior to seven contrast algorithms in search accuracy, convergence speed, and robustness. The proposed algorithm is used to optimize the permutation flow shop scheduling problem. The experimental results indicate that the proposed algorithm can achieve better optimization results than the seven comparative algorithms, so the proposed algorithm has good practical application value.
- 14 January 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-22
Open AccessModified Atom Search Optimization Based on Immunologic Mechanism and Reinforcement Learning
Atom search optimization algorithm has good searching ability and has been successfully applied to calculate hydrogeological parameters and groundwater dispersion coefficient. Since the atom search optimization algorithm is only based on the atom force motion model in molecular dynamics, it has some shortcomings such as slow search speed and low precision during the later stage of iteration. A modified atom search optimization based on the immunologic mechanism and reinforcement learning is proposed to overcome the abovementioned shortcomings in this paper. The proposed algorithm introduces a vaccine operator to better utilize the dominant position in the current atom population so that the speed, accuracy, and domain search ability of the atom search optimization algorithm can be strengthened. The reinforcement learning operator is applied to dynamically adjust the vaccination probability to balance the global exploration ability and local exploitation ability. The test results of 21 benchmark functions confirm that the performance of the proposed algorithm is superior to seven contrast algorithms in search accuracy, convergence speed, and robustness. The proposed algorithm is used to optimize the permutation flow shop scheduling problem. The experimental results indicate that the proposed algorithm can achieve better optimization results than the seven comparative algorithms, so the proposed algorithm has good practical application value.
- Open Access
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Chicken Swarm Optimization Based on Elite Opposition‐Based Learning
Chicken swarm optimization is a new intelligent bionic algorithm, simulating the chicken swarm searching for food in nature. Basic algorithm is likely to fall into a local optimum and has a slow convergence rate. Aiming at these deficiencies, an improved chicken swarm optimization algorithm based on elite opposition‐based learning is proposed. In cock swarm, random search based on adaptive t distribution is adopted to replace that based on Gaussian distribution so as to balance the global exploitation ability and local development ability of the algorithm. In hen swarm, elite opposition‐based learning is introduced to promote the population diversity. Dimension‐by‐dimension greedy search mode is used to do local search for individual of optimal chicken swarm in order to improve optimization precision. According to the test results of 18 standard test functions and 2 engineering structure optimization problems, this algorithm has better effect on optimization precision and speed compared with basic chicken algorithm and other intelligent optimization algorithms.
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Open AccessChicken Swarm Optimization Based on Elite Opposition‐Based Learning
Chicken swarm optimization is a new intelligent bionic algorithm, simulating the chicken swarm searching for food in nature. Basic algorithm is likely to fall into a local optimum and has a slow convergence rate. Aiming at these deficiencies, an improved chicken swarm optimization algorithm based on elite opposition‐based learning is proposed. In cock swarm, random search based on adaptive t distribution is adopted to replace that based on Gaussian distribution so as to balance the global exploitation ability and local development ability of the algorithm. In hen swarm, elite opposition‐based learning is introduced to promote the population diversity. Dimension‐by‐dimension greedy search mode is used to do local search for individual of optimal chicken swarm in order to improve optimization precision. According to the test results of 18 standard test functions and 2 engineering structure optimization problems, this algorithm has better effect on optimization precision and speed compared with basic chicken algorithm and other intelligent optimization algorithms.
- Open Access
- 1 December 2010
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 3 (sup01) , 43-60
Chaotic Time Series Prediction Using Immune Optimization Theory
To solve chaotic time series prediction problem, a novel Prediction approach for chaotic time series based on Immune Optimization Theory (PIOT) is proposed. In PIOT, the concepts and formal definitions of antigen, antibody and affinity being used for time series prediction are given, and the mathematical models of immune optimization operators being used for establishing time series prediction model are exhibited. Chaotic time series is analyzed and corresponding sample space is reconstructed by phase space reconstruction method; then, the prediction model of chaotic time series is constructed by immune optimization theory; finally, using this prediction model to forecast chaotic time series. To demonstrate the effectiveness of PIOT, the three typical chaotic nonlinear time series are generated by nonlinear dynamics systems that are Lorenz, Mackey–Glass and Henon, respectively, and are used for simulating prediction. The simulation results show that PIOT is a feasible and effective prediction method, and meanwhile provides a novel prediction approach for chaotic time series.
- 1 December 2010
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 3 (sup01) , 43-60
Open AccessChaotic Time Series Prediction Using Immune Optimization Theory
To solve chaotic time series prediction problem, a novel Prediction approach for chaotic time series based on Immune Optimization Theory (PIOT) is proposed. In PIOT, the concepts and formal definitions of antigen, antibody and affinity being used for time series prediction are given, and the mathematical models of immune optimization operators being used for establishing time series prediction model are exhibited. Chaotic time series is analyzed and corresponding sample space is reconstructed by phase space reconstruction method; then, the prediction model of chaotic time series is constructed by immune optimization theory; finally, using this prediction model to forecast chaotic time series. To demonstrate the effectiveness of PIOT, the three typical chaotic nonlinear time series are generated by nonlinear dynamics systems that are Lorenz, Mackey–Glass and Henon, respectively, and are used for simulating prediction. The simulation results show that PIOT is a feasible and effective prediction method, and meanwhile provides a novel prediction approach for chaotic time series.