Browsing by Author "Gong, Dunwei"

Now showing 1 - 11 of 11
  • Thumbnail Image
    ItemEmbargo
    A subspace-knowledge transfer based dynamic constrained multiobjective evolutionary algorithm
    (IEEE Press, 2023-12-12) Chen, Guoyu; Guo, Yinan; Jiang, Min; Yang, Shengxiang; Zhao, Xiaoxiao; Gong, Dunwei
    Dynamic constrained multiobjective optimization problems (DCMOPs) have gained increasing attention in the evolutionary computation field during the past years. Among the existing studies, it is a significant challenge to rationally utilize historical knowledge to track the changing Pareto optima in DCMOPs. To address this issue, a subspace-knowledge transfer based dynamic constrained multiobjective evolutionary algorithm is proposed in this article, termed SKTEA. Once a new environment appears, objective space is partitioned into a series of subspaces by a set of uniformly-distributed reference points. Following that, a subspace that has complete time series under certain number of historical environments is regarded as the feasible subspace by the subspace classification method. Otherwise, it is the infeasible one. Based on the classification results, a subspace-driven initialization strategy is designed. In each feasible subspace, Kalman filter is introduced to predict an individual in terms of historical solutions preserved in external storage. The predicted individuals of feasible neighbors are transferred into the infeasible subspace to generate the one, and then an initial population at the new time is formed by integrating predicted and transferred individuals. Intensive experiments on 10 test benchmarks verify that SKTEA outperforms several state-of-the-art DCMOEAs, achieving good performance in solving DCMOPs.
  • Thumbnail Image
    ItemOpen Access
    Cooperative co-evolutionary algorithm for multi-objective optimization problems with changing decision variables
    (Elsevier, 2022-06-07) Xu, Biao; Gong, Dunwei; Zhang, Yong; Yang, Shengxiang; Wang, Ling; Fan, Zhun; Zhang, Yonggang
    Multi-objective optimization problems (MOPs) with changing decision variables exist in the actual industrial production and daily life, which have changing Pareto sets and complex relations among decision variables and are difficult to solve. In this study, we present a cooperative co-evolutionary algorithm by dynamically grouping decision variables to effectively tackle MOPs with changing decision variables. In the presented algorithm, decision variables are grouped into a series of groups using maximum entropic epistasis (MEE) at first, with decision variables in different groups owning a weak dependency. Subsequently, a sub-population is generated to solve decision variables in each group with an existing multi-objective evolutionary algorithm (MOEA). Further, a complete solution including all the decision variables is achieved through the cooperation among sub-populations. Finally, when a decision variable is added or deleted from the existing problem, the grouping of decision variables is dynamically adjusted based on the correlation between the changed decision variable and existing groups. To verify the performance of the developed method, the presented method is compared with five popular methods by tackling eight benchmark optimization problems. The experimental results reveal that the presented method is superior in terms of diversity, convergence, and spread of solutions on most benchmark optimization problems.
  • Thumbnail Image
    ItemOpen Access
    An environment-driven hybrid evolutionary algorithm for dynamic multi-objective optimization problems
    (Springer, 2022-07-28) Chen, Meirong; Guo, Yinan; Jin, Yaochu; Yang, Shengxiang; Gong, Dunwei; Yu, Zekuan
    In dynamic multi-objective optimization problems, the environmental parameters may change over time, which makes the Pareto fronts shifting. To address the issue, a common idea is to track the moving Pareto front once an environmental change occurs. However, it might be hard to obtain the Pareto optimal solutions if the environment changes rapidly. Moreover, it may be costly to implement a new solution. By contrast, robust Pareto optimization over time provides a novel framework to find the robust solutions whose performance is acceptable for more than one environment, which not only saves the computational costs for tracking solutions, but also minimizes the cost for switching solutions. However, neither of the above two approaches can balance between the quality of the obtained non-dominated solutions and the computation cost. To address this issue, environment-driven hybrid dynamic multi-objective evolutionary optimization method is proposed, aiming to fully use strengths of TMO and RPOOT under various characteristics of environmental changes. Two indexes, i.e., the frequency and intensity of environmental changes, are first defined. Then, a criterion is presented based on the characteristics of dynamic environments and the switching cost of solutions, to select an appropriate optimization method in a given environment. The experimental results on a set of dynamic benchmark functions indicate that the proposed hybrid dynamic multi-objective evolutionary optimization method can choose the most rational method that meets the requirements of decision makers, and balance the convergence and robustness of the obtained non-dominated solutions.
  • Thumbnail Image
    ItemOpen Access
    Evolutionary dynamic constrained multiobjective optimization: Test suite and algorithm
    (IEEE Press, 2023-09-11) Chen, Guoyu; Guo, Yinan; Wang, Yong; Liang, Jing; Gong, Dunwei; Yang, Shengxiang
    Dynamic constrained multiobjective optimization problems (DCMOPs) abound in real-world applications and gain increasing attention in the evolutionary computation community. To evaluate the capability of an algorithm in solving DCMOPs, artificial test problems play a fundamental role. Nevertheless, some characteristics of real-world scenarios are not fully considered in the previous test suites, such as time-varying size, location and shape of feasible regions, the controllable change severity, as well as small feasible regions. Therefore, we develop the generators of objective functions and constraints to facilitate the systematic design of DCMOPs, and then a novel test suite consisting of nine benchmarks, termed as DCP, is put forward. To solve these problems, a dynamic constrained multiobjective evolutionary algorithm with a two-stage diversity compensation strategy (TDCEA) is proposed. Some initial individuals are randomly generated to replace historical ones in the first stage, improving the global diversity. In the second stage, the increment between center points of Pareto sets in the past two environments is calculated and employed to adaptively disturb solutions, forming an initial population with good diversity for the new environment. Intensive experiments show that the proposed test problems enable a good understanding of strengths and weaknesses of algorithms, and TDCEA outperforms other state-of-the-art comparative ones, achieving promising performance in tackling DCMOPs.
  • Thumbnail Image
    ItemOpen Access
    An infeasible solutions diversity maintenance epsilon constraint handling method for evolutionary constrained multiobjective optimization
    (Springer, 2021-05-25) Zhou, Jinlong; Zou, Juan; Zheng, Jinhua; Yang, Shengxiang; Gong, Dunwei; Pei, Tingrui
    It is well known that it is very difficult to solve constrained multiobjective optimization problems. Such problems not only need to optimize the objective function but also need to consider the constraints. The epsilon constraint handling method is commonly used, which releases the degree of constraint violations by defining a gradually decayed epsilon. However, for the solutions whose overall constraint violations degree is greater than epsilon, the original epsilon constraint handling method cannot guarantee the diversity of solutions and only constraint violations are considered. To solve this issue, this paper proposed an infeasible solutions diversity maintenance strategy for solutions whose constraint violations degree is greater than epsilon. The experimental results show that our proposed algorithm is very competitive with other state-of-the-art algorithms for constrained multiobjective optimization problems.
  • Thumbnail Image
    ItemOpen Access
    Manifold clustering-based prediction for dynamic multiobjective optimization
    (Elsevier, 2023-01-28) Yan, Li; Qi, Wenlong; Qin, A. K.; Yang, Shengxiang; Gong, Dunwei; Qu, Boyang; Liang, Jing
    Prediction-based evolutionary algorithms have gained much attention in solving dynamic multiobjective optimization problems due to their impressive performance in tracking the changing Pareto set (PS). Current approaches focus on developing learning or estimation models to reveal the dynamic regularities from the correlations between the historical PSs. However, the underlying knowledge in the PS itself, such as the neighborhood distribution of the individuals and their local correlation in the decision space, is ignored which may affect prediction accuracy and the quality of the predicted population. Therefore, a manifold clustering-based predictor is proposed in this paper. A manifold learning method is introduced to preprocess the historical PSs to find and reserve the intrinsic neighborhood relationship of the individuals. As a result, a number of local linear manifolds are extracted from each historical PS, and the individuals in a population are divided into several clusters according to the different linear manifolds they attach to. The individuals belonging to one cluster can be regarded as linearly correlated and may have a similar moving trend. Thus, the subsequent prediction is conducted in units of the cluster and multiple prediction models are built to predict the new PS in a decomposition manner. Finally, an initial population with good diversity and distribution can be generated for the new environment. The proposed algorithm is tested on a variety of commonly-used benchmark problems and compared with eight state-of-the-art algorithms. Experimental results confirm the efficacy of the proposed algorithm, especially on the problems with nonlinear correlation between the decision variables.
  • Thumbnail Image
    ItemOpen Access
    Niche-based and angle-based selection strategies for many-objective evolutionary optimization
    (Elsevier, 2021-04-20) Zhou, Jinlong; Zou, Juan; Yang, Shengxiang; Zheng, Jinhua; Gong, Dunwei; Pei, Tingrui
    It is well known that balancing population diversity and convergence plays a crucial role in evolutionary many-objective optimization. However, most existing multiobjective evolutionary algorithms encounter difficulties in solving many-objective optimization problems. Thus, this paper suggests niche-based and angle-based selection strategies for many-objective evolutionary optimization. In the proposed algorithm, two strategies are included: niche-based density estimation strategy and angle-based selection strategy. Both strategies are employed in the environmental selection to eliminate the worst individual from the population in an iterative way. To be specific, the former estimates the diversity of each individual and finds the most crowded area in the population. The latter removes individuals with weak convergence in the same niche. Experimental studies on several well-known benchmark problems show that the proposed algorithm is competitive compared with six state-of-the-art many-objective algorithms. Moreover, the proposed algorithm has also been verified to be scalable to deal with constrained many-objective optimization problems.
  • Thumbnail Image
    ItemOpen Access
    A reconstruction method for cross-cut shredded documents based on the extreme learning machine algorithm
    (Springer, 2022-07-24) Zhang, Zhenghui; Zou, Juan; Yang, Shengxiang; Zheng, Jinhua; Gong, Dunwei; Pei, Tingrui
    Reconstruction of cross-cut shredded text documents (RCCSTD) has important applications for information security and judicial evidence collection. The traditional method of manual construction is a very time-consuming task, so the use of computer-assisted efficient reconstruction is a crucial research topic. Fragment consensus information extraction and fragment pair compatibility measurement are two fundamental processes in RCCSTD. Due to the limitations of the existing classical methods of these two steps, only documents with specific structures or characteristics can be spliced, and pairing error is larger when the cutting is more fine-grained. In order to reconstruct the fragments more effectively, this paper improves the extraction method for consensus information and constructs a new global pairwise compatibility measurement model based on the extreme learning machine algorithm. The purpose of the algorithm’s design is to exploit all available information and computationally suggest matches to increase the algorithm’s ability to discriminate between data in various complex situations, then find the best neighbor of each fragment for splicing according to pairwise compatibility. The overall performance of our approach in several practical experiments is illustrated. The results indicate that the matching accuracy of the proposed algorithm is better than that of the previously published classical algorithms and still ensures a higher matching accuracy in the noisy datasets, which can provide a feasible method for RCCSTD intelligent systems in real scenarios.
  • Thumbnail Image
    ItemOpen Access
    Reduced-space multistream classification based on multi-objective evolutionary optimization
    (IEEE, 2022-12-27) Jiao, Botao; Guo, Yinan; Yang, Shengxiang; Pu, Jiayang; Gong, Dunwei
    In traditional data stream mining, classification models are typically trained on labeled samples from a single source. However, in real-world scenarios, obtaining accurate labels is very hard and expensive, especially when multiple data streams are concurrently sampled from an environment or the same process. To address this issue, multistream classification is proposed, in which a data stream with biased labels (called the source stream) is leveraged to train a suitable model for prediction over another stream with unlabeled samples (called the target stream). Despite the growing research in this field, previous multistream classification methods are mostly designed for single source stream scenarios. However, various source streams contain diverse data distributions, providing more valuable information for building a more accurate model. In addition, previous works construct classification models in the original shared feature space, ignoring the effect of redundant or low-quality features on the classification performance. This may produce inefficient knowledge transfer across streams. In view of this, a reduced-space multistream classification based on multi-objective evolutionary optimization is proposed in this paper. First, a multi-objective evolutionary optimization is employed to seek the most valuable feature subset shared in the source and target domains, with the purpose of narrowing the distribution difference between source and target streams. Following that, a Gaussian Mixture Model-based weighting mechanism for source samples is presented. More especially, two drift adaptation methods are proposed to address asynchronous drift. Experimental results on benchmark datasets show that the proposed method outperforms other comparative methods on classification accuracy and G-mean.
  • Thumbnail Image
    ItemEmbargo
    Robust online active learning with cluster-based local drift detection for unbalanced imperfect data
    (Elsevier, 2024-08-05) Guo, Yinan; Zheng, Zhiji; Pu, Jiayang; Jiao, Botao; Gong, Dunwei; Yang, Shengxiang
    With the rapid development of data-driven technologies, a massive amount of actual data emerges from industrial systems, forming data stream. Their data distribution may change over time and outliers may be generated as unbalanced imperfect data due to time-varying working condition, aging equipment, etc. Previous methods struggle with the dual challenges of concept drift and unbalance, however, fail to efficiently distinguishing outliers from a drift under the limited labeling budget, causing the performance degradation. To address the issue, robust online active learning with cluster-based local drift detection is proposed to classify unbalanced imperfect data stream with the above characteristics. The cluster-based local drift detection is first designed to capture a new concept and recognize the corresponding drifted regions. Following that, an improved active learning mechanism is presented to distinguish outliers from a drift, and select most valuable instances for labeling and updating ensemble classifier. Experimental results for eight synthetic and four real-world data streams show that the proposed method outperforms seven comparative methods on classification accuracy and robustness.
  • Thumbnail Image
    ItemOpen Access
    A similarity-based cooperative co-evolutionary algorithm for dynamic interval multi-objective optimization problems
    (IEEE Press, 2019-04-19) Gong, Dunwei; Xu, Biao; Zhang, Yong; Guo, Yinan; Yang, Shengxiang
    Dynamic interval multi-objective optimization problems (DI-MOPs) are very common in real-world applications. However, there are few evolutionary algorithms that are suitable for tackling DI-MOPs up to date. A framework of dynamic interval multi-objective cooperative co-evolutionary optimization based on the interval similarity is presented in this paper to handle DI-MOPs. In the framework, a strategy for decomposing decision variables is first proposed, through which all the decision variables are divided into two groups according to the interval similarity between each decision variable and interval parameters. Following that, two sub-populations are utilized to cooperatively optimize decision variables in the two groups. Furthermore, two response strategies, rgb0.00,0.00,0.00i.e., a strategy based on the change intensity and a random mutation strategy, are employed to rapidly track the changing Pareto front of the optimization problem. The proposed algorithm is applied to eight benchmark optimization instances rgb0.00,0.00,0.00as well as a multi-period portfolio selection problem and compared with five state-of-the-art evolutionary algorithms. The experimental results reveal that the proposed algorithm is very competitive on most optimization instances.