Yiqiao Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yiqiao Cai has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Hui Tian
Huaqiao University
10 shared publications Shunkai Fu
College of Computer Science and Technology, Huaqiao University, Xiamen, China
6 shared publicationsWei Luo
Huaqiao University
5 shared publicationsYonghong Chen
College of Computer Science and Technology, Huaqiao University, Xiamen, 361021, China
5 shared publicationsChi Shao
College of Computer Science and Technology, Huaqiao University, Xiamen, 361021, China
4 shared publicationsTian Wang
College of Computer Science and Technology, Huaqiao University, Xiamen, China
4 shared publications
Latest Publications
- Open Access
- 1 February 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 31  (1) , 59-83
Scale-Adaptive Subspace-Based Multiform Optimization for Large-Scale Optimization Problems
With the increasing size of optimization problems in various scientific and engineering fields, finding promising solutions for these large-scale optimization problems has become increasingly challenging. Dimension reduction-based evolutionary algorithms have emerged as one of the most efficient approaches to tackle these challenges. However, they still face difficulties in constructing appropriate subspaces and preserving the global optimum within those subspaces. To overcome these challenges, a multiform optimization framework with scale-adaptive subspace, called MFO-SAS, is proposed for large-scale optimization by taking full advantage of the subspace-assisted and multitasking mechanisms. To address the first challenge, a scale-adaptive switch strategy is designed to switch the subspaces with different scales at different optimization stages, enabling efficient assistance of the optimization processes for the original problem with appropriate subspaces. To tackle the second challenge, a multiform optimization paradigm is adopted to conduct the simultaneous search over both the original problem space and the constructed subspaces in a multitasking scenario, thus facilitating the utilization of the search experiences from different problem spaces. Consequently, the MFO-SAS framework effectively leverages valuable knowledge obtained from different spaces to guide the search and dynamically balances the representation accuracy of the subspace with the computational cost of subspace search. Experimental results on the large-scale benchmark problems demonstrate the superiority of MFO-SAS over several state-of-the-art algorithms.
- 1 February 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 31  (1) , 59-83
Open AccessScale-Adaptive Subspace-Based Multiform Optimization for Large-Scale Optimization Problems
With the increasing size of optimization problems in various scientific and engineering fields, finding promising solutions for these large-scale optimization problems has become increasingly challenging. Dimension reduction-based evolutionary algorithms have emerged as one of the most efficient approaches to tackle these challenges. However, they still face difficulties in constructing appropriate subspaces and preserving the global optimum within those subspaces. To overcome these challenges, a multiform optimization framework with scale-adaptive subspace, called MFO-SAS, is proposed for large-scale optimization by taking full advantage of the subspace-assisted and multitasking mechanisms. To address the first challenge, a scale-adaptive switch strategy is designed to switch the subspaces with different scales at different optimization stages, enabling efficient assistance of the optimization processes for the original problem with appropriate subspaces. To tackle the second challenge, a multiform optimization paradigm is adopted to conduct the simultaneous search over both the original problem space and the constructed subspaces in a multitasking scenario, thus facilitating the utilization of the search experiences from different problem spaces. Consequently, the MFO-SAS framework effectively leverages valuable knowledge obtained from different spaces to guide the search and dynamically balances the representation accuracy of the subspace with the computational cost of subspace search. Experimental results on the large-scale benchmark problems demonstrate the superiority of MFO-SAS over several state-of-the-art algorithms.
- Open Access
- 3 March 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11  (4) , 1-32
A local search with chain search path strategy for real-world many-objective vehicle routing problem
- 3 March 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11  (4) , 1-32
Open AccessA local search with chain search path strategy for real-world many-objective vehicle routing problem
- Open Access
Multi-Task Multi-Objective Evolutionary Search Based on Deep Reinforcement Learning for Multi-Objective Vehicle Routing Problems with Time Windows
The vehicle routing problem with time windows (VRPTW) is a widely studied combinatorial optimization problem in supply chains and logistics within the last decade. Recent research has explored the potential of deep reinforcement learning (DRL) as a promising solution for the VRPTW. However, the challenge of addressing the VRPTW with many conflicting objectives (MOVRPTW) still remains for DRL. The MOVRPTW considers five conflicting objectives simultaneously: minimizing the number of vehicles required, the total travel distance, the travel time of the longest route, the total waiting time for early arrivals, and the total delay time for late arrivals. To tackle the MOVRPTW, this study introduces the MTMO/DRP-AT, a multi-task multi-objective evolutionary search algorithm, by making full use of both DRL and the multitasking mechanism. In the MTMO/DRL-AT, a two-objective MOVRPTW is constructed as an assisted task, with the objectives being to minimize the total travel distance and the travel time of the longest route. Both the main task and the assisted task are simultaneously solved in a multitasking scenario. Each task is decomposed into scalar optimization subproblems, which are then solved by an attention model trained using DRL. The outputs of these trained models serve as the initial solutions for the MTMO/DRL-AT. Subsequently, the proposed algorithm incorporates knowledge transfer and multiple local search operators to further enhance the quality of these promising solutions. The simulation results on real-world benchmarks highlight the superior performance of the MTMO/DRL-AT compared to several other algorithms in solving the MOVRPTW.
Open AccessMulti-Task Multi-Objective Evolutionary Search Based on Deep Reinforcement Learning for Multi-Objective Vehicle Routing Problems with Time Windows
The vehicle routing problem with time windows (VRPTW) is a widely studied combinatorial optimization problem in supply chains and logistics within the last decade. Recent research has explored the potential of deep reinforcement learning (DRL) as a promising solution for the VRPTW. However, the challenge of addressing the VRPTW with many conflicting objectives (MOVRPTW) still remains for DRL. The MOVRPTW considers five conflicting objectives simultaneously: minimizing the number of vehicles required, the total travel distance, the travel time of the longest route, the total waiting time for early arrivals, and the total delay time for late arrivals. To tackle the MOVRPTW, this study introduces the MTMO/DRP-AT, a multi-task multi-objective evolutionary search algorithm, by making full use of both DRL and the multitasking mechanism. In the MTMO/DRL-AT, a two-objective MOVRPTW is constructed as an assisted task, with the objectives being to minimize the total travel distance and the travel time of the longest route. Both the main task and the assisted task are simultaneously solved in a multitasking scenario. Each task is decomposed into scalar optimization subproblems, which are then solved by an attention model trained using DRL. The outputs of these trained models serve as the initial solutions for the MTMO/DRL-AT. Subsequently, the proposed algorithm incorporates knowledge transfer and multiple local search operators to further enhance the quality of these promising solutions. The simulation results on real-world benchmarks highlight the superior performance of the MTMO/DRL-AT compared to several other algorithms in solving the MOVRPTW.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 128-132
A Knowledge Transfer Mechanism Based on Population Distribution Information for Multifactorial Differential Evolution
Evolutionary multi-task optimization (EMTO) is a novel optimization paradigm that improves the performance of each task by transferring valuable knowledge across related tasks. At present, a significant challenge and research direction in EMTO is to select useful knowledge to reduce the negative transfer phenomenon. In most EMTO algorithms, however, population distribution information of different tasks has not been effectively used in designing the mechanism for transferring useful knowledge. Based on this consideration, we propose a novel knowledge transfer mechanism based on population distribution information to alleviate the problem of negative transfer. Further, to evaluate the effectiveness of the proposed mechanism, an improved multifactorial differential evolution (MFDE) with this mechanism is presented, leading to a new EMTO variant, termed PDI-MDE. The experimental results on a suite of single-objective multitasking benchmark problems have demonstrated the competitive performance of PDI-MDE.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 128-132
A Knowledge Transfer Mechanism Based on Population Distribution Information for Multifactorial Differential Evolution
Evolutionary multi-task optimization (EMTO) is a novel optimization paradigm that improves the performance of each task by transferring valuable knowledge across related tasks. At present, a significant challenge and research direction in EMTO is to select useful knowledge to reduce the negative transfer phenomenon. In most EMTO algorithms, however, population distribution information of different tasks has not been effectively used in designing the mechanism for transferring useful knowledge. Based on this consideration, we propose a novel knowledge transfer mechanism based on population distribution information to alleviate the problem of negative transfer. Further, to evaluate the effectiveness of the proposed mechanism, an improved multifactorial differential evolution (MFDE) with this mechanism is presented, leading to a new EMTO variant, termed PDI-MDE. The experimental results on a suite of single-objective multitasking benchmark problems have demonstrated the competitive performance of PDI-MDE.
- 19 January 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 51  (8) , 5873-5897
Self-regulated differential evolution for real parameter optimization
- 19 January 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 51  (8) , 5873-5897
Self-regulated differential evolution for real parameter optimization
- Open Access
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 226557-226578
Enhancing Differential Evolution on Continuous Optimization Problems by Detecting Promising Leaders
Due to that the performance of differential evolution (DE) significantly depends on offspring generation strategies, various DE variants have been reported with the improved mutation operators. However, on the one hand, the mutation operators in most DE variants are guided by the elites in terms of the fitness value, without considering their distribution information in the fitness landscape. It may lead to the population be evolving towards the unpromising areas more frequently if these elites are clustered in a locally optimal region. On the other hand, in most DE variants, the evolutionary information of the potential trial vectors is not fully utilized to guide the search, which will hamper the local exploitation in the promising regions that they are located in. To overcome these weaknesses, this article proposes an enhanced DE framework (DELDG) with a leaders-detection-and-guidance mechanism that consists of an adaptive leaders detection (ALD) and a neighborhood-based tournament selection (NTS). With these two novel operators, DELDG can not only guide the mutation process of each individual with multiple promising leaders detected by ALD, but also accelerate the convergence speed with the competition among the potential trial vectors by NTS. Therefore, DELDG is characterized by the explicit detection of the promising leaders according to their fitness values and distribution information and the effective use of the potential trial vectors in the neighborhood of each leader. Compared with 36 excellent DE variants and evolutionary algorithms (EAs), the experimental results on 28 IEEE CEC2013 real-parameter functions and 17 IEEE CEC2011 real-world problems have demonstrated the competitive performance of DELDG.
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 226557-226578
Open AccessEnhancing Differential Evolution on Continuous Optimization Problems by Detecting Promising Leaders
Due to that the performance of differential evolution (DE) significantly depends on offspring generation strategies, various DE variants have been reported with the improved mutation operators. However, on the one hand, the mutation operators in most DE variants are guided by the elites in terms of the fitness value, without considering their distribution information in the fitness landscape. It may lead to the population be evolving towards the unpromising areas more frequently if these elites are clustered in a locally optimal region. On the other hand, in most DE variants, the evolutionary information of the potential trial vectors is not fully utilized to guide the search, which will hamper the local exploitation in the promising regions that they are located in. To overcome these weaknesses, this article proposes an enhanced DE framework (DELDG) with a leaders-detection-and-guidance mechanism that consists of an adaptive leaders detection (ALD) and a neighborhood-based tournament selection (NTS). With these two novel operators, DELDG can not only guide the mutation process of each individual with multiple promising leaders detected by ALD, but also accelerate the convergence speed with the competition among the potential trial vectors by NTS. Therefore, DELDG is characterized by the explicit detection of the promising leaders according to their fitness values and distribution information and the effective use of the potential trial vectors in the neighborhood of each leader. Compared with 36 excellent DE variants and evolutionary algorithms (EAs), the experimental results on 28 IEEE CEC2013 real-parameter functions and 17 IEEE CEC2011 real-world problems have demonstrated the competitive performance of DELDG.
- 2 April 2020
- Published by Springer Nature
- p. 15-26
Experimental Analysis of Selective Imitation for Multifactorial Differential Evolution
- 2 April 2020
- Published by Springer Nature
- p. 15-26
Experimental Analysis of Selective Imitation for Multifactorial Differential Evolution
- Open Access
- 21 March 2020
- Published by MDPI AG in Electronics
- Vol. 9  (3) , 522
Steganalysis of Adaptive Multi-Rate Speech Based on Extreme Gradient Boosting
Steganalysis of adaptive multi-rate (AMR) speech is a hot topic for controlling cybercrimes grounded in steganography in related speech streams. In this paper, we first present a novel AMR steganalysis model, which utilizes extreme gradient boosting (XGBoost) as the classifier, instead of support vector machines (SVM) adopted in the previous schemes. Compared with the SVM-based model, this new model can facilitate the excavation of potential information from the high-dimensional features and can avoid overfitting. Moreover, to further strengthen the preceding features based on the statistical characteristics of pulse pairs, we present the convergence feature based on the Markov chain to reflect the global characterization of pulse pairs, which is essentially the final state of the Markov transition matrix. Combining the convergence feature with the preceding features, we propose an XGBoost-based steganalysis scheme for AMR speech streams. Finally, we conducted a series of experiments to assess our presented scheme and compared it with previous schemes. The experimental results demonstrate that the proposed scheme is feasible, and can provide better performance in terms of detecting the existing steganography methods based on AMR speech streams.
- 21 March 2020
- Published by MDPI AG in Electronics
- Vol. 9  (3) , 522
Open AccessSteganalysis of Adaptive Multi-Rate Speech Based on Extreme Gradient Boosting
Steganalysis of adaptive multi-rate (AMR) speech is a hot topic for controlling cybercrimes grounded in steganography in related speech streams. In this paper, we first present a novel AMR steganalysis model, which utilizes extreme gradient boosting (XGBoost) as the classifier, instead of support vector machines (SVM) adopted in the previous schemes. Compared with the SVM-based model, this new model can facilitate the excavation of potential information from the high-dimensional features and can avoid overfitting. Moreover, to further strengthen the preceding features based on the statistical characteristics of pulse pairs, we present the convergence feature based on the Markov chain to reflect the global characterization of pulse pairs, which is essentially the final state of the Markov transition matrix. Combining the convergence feature with the preceding features, we propose an XGBoost-based steganalysis scheme for AMR speech streams. Finally, we conducted a series of experiments to assess our presented scheme and compared it with previous schemes. The experimental results demonstrate that the proposed scheme is feasible, and can provide better performance in terms of detecting the existing steganography methods based on AMR speech streams.
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 14  (4) , 5253-5264
A Decomposition-Based Local Search for Large-Scale Many-Objective Vehicle Routing Problems With Simultaneous Delivery and Pickup and Time Windows
Vehicle routing problem with simultaneous delivery and pickup and time windows (VRPSDPTW) is an important logistics problem in supply chain network optimization. However, at present, existing approaches are only applied to solve small-scale many-objective VRPSDPTW. For the large-scale problem, to obtain high-quality solutions (effectively) and solve the problem in a short running time (efficiently), we focus on two issues: 1) how to handle many-objective property and 2) how to tackle large-scale property of the problem. For the first issue, to enhance the convergence property, a novel local search algorithm utilizing seven neighborhood operators is proposed. Meanwhile, to maintain the diversity property, the concept of decomposition is adopted. The problem is first decomposed into multiple single-objective problems, then local search is utilized to optimize these subproblems. For the second issue, since optimizing a subproblem by local search is time consuming for large-scale problems, the key point is how to allocate the computational resources and balance the convergence and diversity. To handle this problem, a weight space partition strategy is introduced. Finally, a decomposition-based local search algorithm is proposed for many-objective VRPSDPTW. Experimental results on the large-scale instances provided by Chinese logistic company show the effectiveness of the proposed algorithm.
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 14  (4) , 5253-5264
A Decomposition-Based Local Search for Large-Scale Many-Objective Vehicle Routing Problems With Simultaneous Delivery and Pickup and Time Windows
Vehicle routing problem with simultaneous delivery and pickup and time windows (VRPSDPTW) is an important logistics problem in supply chain network optimization. However, at present, existing approaches are only applied to solve small-scale many-objective VRPSDPTW. For the large-scale problem, to obtain high-quality solutions (effectively) and solve the problem in a short running time (efficiently), we focus on two issues: 1) how to handle many-objective property and 2) how to tackle large-scale property of the problem. For the first issue, to enhance the convergence property, a novel local search algorithm utilizing seven neighborhood operators is proposed. Meanwhile, to maintain the diversity property, the concept of decomposition is adopted. The problem is first decomposed into multiple single-objective problems, then local search is utilized to optimize these subproblems. For the second issue, since optimizing a subproblem by local search is time consuming for large-scale problems, the key point is how to allocate the computational resources and balance the convergence and diversity. To handle this problem, a weight space partition strategy is introduced. Finally, a decomposition-based local search algorithm is proposed for many-objective VRPSDPTW. Experimental results on the large-scale instances provided by Chinese logistic company show the effectiveness of the proposed algorithm.
- Open Access
- 24 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 6117-6129
Detecting Steganography in Inactive Voice-Over-IP Frames Based on Statistic Characteristics of Fundamental Frequency
Steganography in inactive Voice-over-IP frames is a new technique of information hiding, which can achieve large steganographic capacity while maintaining excellent imperceptibility. To prevent the illegitimate use of this technique, the entropy-based and poker test-based steganalysis methods have been presented. However, the detection performance of these two methods is not so good for the cases of having small quantity of inactive frames or low embedding rates. Thus, we present a new steganalysis method based on statistic characteristics of fundamental frequency. Specifically, we employ the statistics for zero-crossing count (ZCC), including the average ZCC of inactive frames, the ratio between the average ZCC of inactive frames and that of all frames, and the difference between the average ZCC of inactive frames and their calibrated versions, to characterize the frame-level dynamic characteristic of speech signals; we utilize the average values of Mel-frequency cepstral coefficients (MFCCs) to represent the invariant characteristic of inactive frames; further, using the feature set consisting of the zero-crossing statistics and average MFCCs, we propose a support-vector-machine based steganalysis for inactive speech frames. The proposed steganalysis method is evaluated with a large number of ITU-T G.723.1 encoded speech samples, and compared with the existing methods. The experimental results demonstrate that the proposed method significantly outperforms the previous ones on detection accuracy, false positive rate and false negative rate for any given embedding rates or using the same number of inactive frames. Particularly, the proposed method can provide accurate detecting results for the existing steganographic methods only using very small quantity of inactive frames, and thereby be employed to detecting potential inactive-frame steganography behaviors in real-time speech streams.
- 24 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 6117-6129
Open AccessDetecting Steganography in Inactive Voice-Over-IP Frames Based on Statistic Characteristics of Fundamental Frequency
Steganography in inactive Voice-over-IP frames is a new technique of information hiding, which can achieve large steganographic capacity while maintaining excellent imperceptibility. To prevent the illegitimate use of this technique, the entropy-based and poker test-based steganalysis methods have been presented. However, the detection performance of these two methods is not so good for the cases of having small quantity of inactive frames or low embedding rates. Thus, we present a new steganalysis method based on statistic characteristics of fundamental frequency. Specifically, we employ the statistics for zero-crossing count (ZCC), including the average ZCC of inactive frames, the ratio between the average ZCC of inactive frames and that of all frames, and the difference between the average ZCC of inactive frames and their calibrated versions, to characterize the frame-level dynamic characteristic of speech signals; we utilize the average values of Mel-frequency cepstral coefficients (MFCCs) to represent the invariant characteristic of inactive frames; further, using the feature set consisting of the zero-crossing statistics and average MFCCs, we propose a support-vector-machine based steganalysis for inactive speech frames. The proposed steganalysis method is evaluated with a large number of ITU-T G.723.1 encoded speech samples, and compared with the existing methods. The experimental results demonstrate that the proposed method significantly outperforms the previous ones on detection accuracy, false positive rate and false negative rate for any given embedding rates or using the same number of inactive frames. Particularly, the proposed method can provide accurate detecting results for the existing steganographic methods only using very small quantity of inactive frames, and thereby be employed to detecting potential inactive-frame steganography behaviors in real-time speech streams.