Various real-world multiobjective optimization problems are dynamic, requiring evolutionary algorithms (EAs) to be able to rapidly track the moving Pareto front of an optimization problem once an environmental change occurs. To this end, several methods have been developed to predict the new location of the moving Pareto set (PS) so that the population can be reinitialized around the predicted location. In this paper, we present a multidirectional prediction strategy to enhance the performance of EAs in solving a dynamic multiobjective optimization problem (DMOP). To more accurately predict the moving location of the PS, the population is clustered into a number of representative groups by a proposed classification strategy, where the number of clusters is adapted according to the intensity of the environmental change. To examine the performance of the developed algorithm, the proposed prediction strategy is compared with four state-of-the-art prediction methods under the framework of particle swarm optimization as well as five popular EAs for dynamic multiobjective optimization. Our experimental results demonstrate that the proposed algorithm can effectively tackle DMOPs.
27 June 2019 in IEEE Transactions on Evolutionary Computation
A large number of prediction strategies are specific to a dynamic multi-objective optimization problem (DMOP) with only one type of the Pareto set (PS) change. However, a continuous DMOP with more than one type of the unknown PS change has been seldom investigated. We present a multi-model prediction approach (MMP) realized in the framework of evolutionary algorithms (EAs) to tackle the problem. In this paper, we first detect the type of the PS change, followed by the selection of an appropriate prediction model to provide an initial population for the subsequent evolution. To observe the influence of MMP on EAs, optimal solutions obtained by three classical dynamic multi-objective EAs with and without MMP are investigated. Furthermore, to investigate the performance of MMP, three state-of-the-art prediction strategies are compared on a large number of dynamic test instances under the same particle swarm optimizer. Experimental results demonstrate that the proposed approach outperforms its counterparts under comparison on most optimization problems.
Feature selection has been an important research area in data mining, which chooses a subset of relevant features for use in model building. This paper aims to provide an overview of feature selection methods for big data mining. It first discusses the current challenges and difficulties faced when mining valuable information from big data. A comprehensive review of existing feature selection methods in big data is then presented. Herein, we approach the review from two aspects: methods specific to a particular kind of big data with certain characteristics and applications of methods in classification analysis, which are significantly different to the existing review work. The paper also highlights the current issues of feature selection in big data and suggests the future research directions.
16 January 2017 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Dynamic multi-objective optimization problems (DMOPs) not only involve multiple conflicting objectives, but these objectives may also vary with time, raising a challenge for researchers to solve them. This paper presents a cooperative co-evolutionary strategy based on environment sensitivities for solving DMOPs. In this strategy, a new method that groups decision variables is first proposed, in which all the decision variables are partitioned into two subcomponents according to their interrelation with environment. Adopting two populations to cooperatively optimize the two subcomponents, two prediction methods, i.e., differential prediction and Cauchy mutation, are then employed respectively to speed up their responses on the change of the environment. Furthermore, two improved dynamic multi-objective optimization algorithms, i.e., DNSGAII-CO and DMOPSO-CO, are proposed by incorporating the above strategy into NSGA-II and multi-objective particle swarm optimization, respectively. The proposed algorithms are compared with three state-of-the-art algorithms by applying to seven benchmark DMOPs. Experimental results reveal that the proposed algorithms significantly outperform the compared algorithms in terms of convergence and distribution on most DMOPs.
24 June 2024 in IEEE Transactions on Evolutionary Computation
Dynamic multi-objective evolutionary algorithms (DMOEAs) have gained great popularity in dealing with dynamic multi-objective optimization problems (DMOPs). However, existing studies have difficulties in tackling DMOPs subject to (dynamic) constraints. In this paper, we propose a prediction and weak coevolutionary multi-objective optimization algorithm (PWDCMO) to handle dynamic constrained multi-objective optimization problems (DCMOPs), where a prediction strategy is employed to forecast potential optimal regions under the new environment, with a weak coevolutionary constrained multi-objective optimization (CCMO) as the optimizer aiming at balancing exploration and convergence. The proposed method is compared with four popular dynamic constrained multi-objective evolutionary algorithms (DCMOEAs) on six test instances from two various test suites with their convergence and the overall performance being discussed. Furthermore, the performance of the proposed prediction strategy is also investigated to observe its impact on the final results. Additionally, the PWDCMO is employed in the optimization of an integrated coal mine energy system (ICMES) to validate the proficiency in addressing real world problems. Experimental results demonstrate the superiority of PWDCMO.