Swarm and Evolutionary Computation最新文献_第7页

Learning-based memetic algorithm for bi-objective distributed heterogeneous permutation flow shop scheduling problem with flexible machine speeds 基于学习的模因算法求解柔性机器速度双目标分布式异构置换流水车间调度问题

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-03-01 Epub Date: 2026-03-16 DOI: 10.1016/j.swevo.2026.102354

Liangcai Xia , Shijun Chen , Xiangjing Lai

{"title":"Learning-based memetic algorithm for bi-objective distributed heterogeneous permutation flow shop scheduling problem with flexible machine speeds","authors":"Liangcai Xia , Shijun Chen , Xiangjing Lai","doi":"10.1016/j.swevo.2026.102354","DOIUrl":"10.1016/j.swevo.2026.102354","url":null,"abstract":"<div><div>This paper investigates the bi-objective distributed heterogeneous permutation flow shop scheduling problem with flexible machine speeds (DHPFSP-FMS), which has broad practical applications in various manufacturing domains. To address this problem, a learning-based memetic algorithm (LBMA) is proposed, which integrates several complementary components, including population initialization rules, an energy-efficient decoding scheme, a local search with a learning-based neighborhood selection strategy, and crossover operations based on precedence and uniform strategies. The algorithm analysis indicates that the learning-based neighborhood selection strategy effectively strengthens both the search capability and robustness of the algorithm, and that the energy-efficient decoding scheme is a critical factor in enhancing algorithm performance. Extensive computational experiments demonstrate that the proposed algorithm significantly outperforms existing state-of-the-art methods on a number of benchmark instances, achieving an average reduction of 1.36% in makespan and 6.18% in total energy consumption compared with the best results obtained by the competing methods.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"103 ","pages":"Article 102354"},"PeriodicalIF":8.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147543879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evolutionary algorithm with domain-specific operators for UAV path planning 基于特定域算子的无人机路径规划进化算法

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-01-08 DOI: 10.1016/j.swevo.2025.102267

Daison Darlan , Oladayo S. Ajani , Rammohan Mallipeddi

{"title":"Evolutionary algorithm with domain-specific operators for UAV path planning","authors":"Daison Darlan , Oladayo S. Ajani , Rammohan Mallipeddi","doi":"10.1016/j.swevo.2025.102267","DOIUrl":"10.1016/j.swevo.2025.102267","url":null,"abstract":"<div><div>Multi-objective UAV path planning is critical in practical applications such as surveillance, search-and-rescue missions, and environmental monitoring. However, the inherent complexity stemming from conflicting objectives, dynamic operational environments, and stringent mission constraints severely limits the efficacy of conventional evolutionary algorithms. Standard evolutionary operators typically fail to adequately respect domain-specific constraints, leading to infeasible or inefficient flight trajectories. Motivated by these limitations, this paper proposes specialized evolutionary operators tailored explicitly for multi-objective UAV path planning. We introduce a novel crossover operator that strategically employs the A* algorithm to generate feasible offspring paths between selected waypoints from parent solutions. Additionally, we present an adaptive polynomial mutation mechanism that dynamically controls exploration and exploitation by adjusting the mutation factor progressively across generations. Complementing this, we propose a secondary mutation operator utilizing A* to refine path segments effectively. Comprehensive ablation studies demonstrate the synergistic advantage of these innovations. Extensive evaluations on a realistic benchmark environment illustrate that our approach achieves significant enhancements, validated through substantial improvements in the hypervolume metric. Our findings confirm that embedding domain-specific intelligence into evolutionary operators markedly advances the state-of-the-art in multi-objective UAV path planning.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102267"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145915141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Move towards agile feedback: An adaptive Turing-enhanced multi-objective co-evolutionary algorithm for rescheduling optimization steelmaking-continuous casting under equipment failures 走向敏捷反馈：设备故障下炼钢连铸重调度优化的自适应图灵增强型多目标协同进化算法

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-02-09 DOI: 10.1016/j.swevo.2026.102314

Lin Guan, Yalin Wang, Chenliang Liu, Xujie Tan, Yujie Zhang

{"title":"Move towards agile feedback: An adaptive Turing-enhanced multi-objective co-evolutionary algorithm for rescheduling optimization steelmaking-continuous casting under equipment failures","authors":"Lin Guan, Yalin Wang, Chenliang Liu, Xujie Tan, Yujie Zhang","doi":"10.1016/j.swevo.2026.102314","DOIUrl":"10.1016/j.swevo.2026.102314","url":null,"abstract":"<div><div>Equipment failures often occur during industrial production, particularly in processes such as steelmaking and continuous casting (SCC), leading to highly dynamic and tightly constrained rescheduling optimization challenges. Existing optimization methods often fail to deliver reliable performance when confronted with abrupt equipment failures, resulting in reduced productivity and increased energy consumption. To address these challenges, this paper proposes an adaptive Turing-enhanced multi-objective evolutionary algorithm (ATE-MOEA) for SCC rescheduling optimization to improve optimization robustness and responsiveness. First, a novel multi-population co-evolution framework is designed to simplify the optimization problem by evolving auxiliary populations. Then, a bidirectional knowledge transfer mechanism based on encoding schemes is proposed to enhance collaboration between the original population and the auxiliary population. Furthermore, an adaptive Turing-pattern-driven mutation strategy is incorporated to balance global exploration and local exploitation during the multi-objective search process. Finally, comprehensive comparative experiments conducted on 16 real-world SCC scheduling scenarios demonstrate that ATE-MOEA consistently outperforms representative benchmark methods, achieving 95–99 % improvement in convergence metrics across most test cases, 90–93 % reduction in computational time, and consistently superior solution diversity as reflected by hypervolume improvements.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102314"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward intelligent acquisition policies: Reinforcement learning for causal multi-objective Bayesian optimization 迈向智能获取策略：因果多目标贝叶斯优化的强化学习

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-02-04 DOI: 10.1016/j.swevo.2026.102290

Shikun Chen, Yangguang Liu

{"title":"Toward intelligent acquisition policies: Reinforcement learning for causal multi-objective Bayesian optimization","authors":"Shikun Chen, Yangguang Liu","doi":"10.1016/j.swevo.2026.102290","DOIUrl":"10.1016/j.swevo.2026.102290","url":null,"abstract":"<div><div>Traditional Bayesian optimization relies on hand-crafted acquisition functions that treat variables uniformly, whereas multi-objective systems contain exploitable causal structure. Although recent advances established foundations for causal Bayesian optimization and multi-objective reinforcement learning independently, no existing approach combines these paradigms. Static acquisition policies cannot adapt to causal dependencies and competing objective trade-offs. Here, we present RL-CMBO (Reinforcement Learning for Causal Multi-Objective Bayesian Optimization), a reinforcement learning framework that learns intelligent acquisition policies through experience. Our approach shifts from hand-crafted functions to learned policies capable of discovering optimal intervention strategies. The framework integrates: (1) a meta-learning architecture adapting to task-specific causal structures, (2) state representation encoding Pareto front features and causal graph topology, and (3) constrained action space over Possibly-Optimal Minimal Intervention Sets (POMIS) ensuring causal identifiability. Our reward engineering balances hypervolume improvement, intervention costs, and Pareto front diversity–thus addressing competing objectives in causal systems. Experimental evaluation demonstrates that RL-CMBO outperforms existing methods across synthetic and real-world benchmarks, achieving improved sample efficiency while discovering intervention patterns that static acquisition functions fail to identify. This work establishes the first unified framework combining reinforcement learning, causal reasoning, and multi-objective optimization.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102290"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147398167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comprehensive review on deep learning for multi-objective optimization 面向多目标优化的深度学习研究综述

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-01-28 DOI: 10.1016/j.swevo.2026.102304

Haiping Ma, Jin Liu, Jiajun Li, Junhan Jia

{"title":"A comprehensive review on deep learning for multi-objective optimization","authors":"Haiping Ma, Jin Liu, Jiajun Li, Junhan Jia","doi":"10.1016/j.swevo.2026.102304","DOIUrl":"10.1016/j.swevo.2026.102304","url":null,"abstract":"<div><div>Over the past decades, multi-objective optimization has established itself as a fundamental and continuously evolving research area within computational intelligence. While traditional methods remain relevant, the integration of deep learning techniques has recently opened up new possibilities for solving complex optimization problems with multiple competing objectives. This trend has led to the development of numerous innovative approaches that leverage the powerful pattern recognition and representation learning capabilities of deep neural networks. This review systematically examines the current landscape of deep learning applications in multi-objective optimization, beginning with essential foundational concepts before progressing to a detailed analysis of how various deep learning architectures have been adapted for optimization tasks. Then the review categorizes these applications across different engineering domains and discusses their practical implementations. Finally, the paper outlines several promising research directions for advancing this rapidly evolving field, including the development of novel network architectures, deeper integration of deep learning with established multi-objective optimization frameworks, the creation of user-oriented interactive systems, the establishment of explainable theoretical foundations, and the reduction of computational costs.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102304"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive pattern learning particle swarm optimization for large-scale optimization 大规模优化的自适应模式学习粒子群算法

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-01-13 DOI: 10.1016/j.swevo.2025.102268

Zhi-Tao Lai , Zi-Jia Wang , Shuai Liu , Zong-Gan Chen , Zhi-Hui Zhan , Sam Kwong , Jun Zhang

{"title":"Adaptive pattern learning particle swarm optimization for large-scale optimization","authors":"Zhi-Tao Lai , Zi-Jia Wang , Shuai Liu , Zong-Gan Chen , Zhi-Hui Zhan , Sam Kwong , Jun Zhang","doi":"10.1016/j.swevo.2025.102268","DOIUrl":"10.1016/j.swevo.2025.102268","url":null,"abstract":"<div><div>Large scale optimization problems (LSOPs) are an important topic in the field of evolutionary computing (EC), and many researchers have designed various learning strategies to try to solve LSOPs more effectively. However, most of the learning strategies are with the fixed learning pattern during the whole evolution process and lack the adaptive adjustment mechanism according to individual property. In fact, different individuals are with different exploitation or exploration abilities, and are suitable for different learning patterns. Therefore, in this paper, we propose adaptive pattern learning particle swarm optimization (APLPSO) to solve LSOPs. In APLPSO, several learning patterns based on different numbers of learning exemplars are first generated to enrich the learning diversity of population. Then, each individual will evaluate the learning patterns and adaptively select its own appropriate learning pattern for updating. The experimental results on two widely used large-scale optimization test suites, CEC2010 and CEC2013, show that APLPSO significantly outperforms other state-of-the-art large-scale optimization algorithms, including the winners of the CEC2010 and CEC2012 competitions. Moreover, we apply APLPSO to a real-world large-scale portfolio optimization application to show its practical applicability.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102268"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reinforcement learning assisted sparse population coevolutionary algorithm for multi-component spectral feature selection 强化学习辅助稀疏种群协同进化多分量谱特征选择算法

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-02-09 DOI: 10.1016/j.swevo.2026.102292

Panpan Zhang , Yilan He , Jing Rong , Ye Tian , Yajie Zhang , Shangshang Yang , Xingyi Zhang

{"title":"Reinforcement learning assisted sparse population coevolutionary algorithm for multi-component spectral feature selection","authors":"Panpan Zhang , Yilan He , Jing Rong , Ye Tian , Yajie Zhang , Shangshang Yang , Xingyi Zhang","doi":"10.1016/j.swevo.2026.102292","DOIUrl":"10.1016/j.swevo.2026.102292","url":null,"abstract":"<div><div>As an essential step in spectral quantitative analysis, spectral feature selection identifies the most relevant and significant features from high-dimensional spectral data. This process aims to improve the accuracy of concentration prediction models while also reducing model complexity. However, existing evolutionary algorithms fail to account for the potential cooperation in this problem, which may degrade performance. This paper proposes a sparse population coevolutionary algorithm based on deep reinforcement learning for multi-component spectral feature selection. It introduces auxiliary sparse populations for single-component spectral feature selection and utilizes the Deep Q-learning Network (DQN) to select a population as an evolutionary helper, thereby accelerating the exploration and exploitation of the main sparse population for multi-component spectral feature selection. DQN establishes a mapping from population states to the selection action of an auxiliary population used for coevolution. The best auxiliary evolutionary population is selected based on the current state of the main population at each generation, thus promoting convergence towards the Pareto-optimal fronts. In the experiments, the meat and flue gas datasets are used to evaluate the effectiveness of the proposed algorithm. Experimental results indicate that the proposed algorithm is superior for multi-component spectral feature selection over four state-of-the-art evolutionary algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102292"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual-population metaheuristic with Adversarial Strategy Adaptation for global optimization 具有对抗策略自适应的双种群元启发式全局优化

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-02-05 DOI: 10.1016/j.swevo.2026.102320

Haythem Ghazouani

{"title":"Dual-population metaheuristic with Adversarial Strategy Adaptation for global optimization","authors":"Haythem Ghazouani","doi":"10.1016/j.swevo.2026.102320","DOIUrl":"10.1016/j.swevo.2026.102320","url":null,"abstract":"<div><div>Population-based metaheuristics often struggle to balance exploration and exploitation in high-dimensional landscapes due to the tight coupling between search strategies and candidate solutions. This paper proposes DPASA (Dual-Population Adversarial Strategy Adaptation), a framework that fundamentally decouples these components into two co-evolving populations to enable continuous meta-optimization. The contributions are threefold: (1) a <strong>dual-population architecture</strong> that treats search strategy as an independently evolvable entity; (2) <strong>sinusoidal guidance functions</strong> that compress complex search trajectories into parsimonious, learnable parameters; and (3) a novel <strong>adversarial negation operator</strong> that systematically generates counter-strategies to actively refute converging trends and force exploration. Experimental evaluation on 15 classical and 29 multidimensional CEC 2017 benchmark functions indicates that DPASA achieves a competitive Friedman rank of 2.07. Extended validation on CEC 2022 benchmarks (e.g., F1 error 0.44) confirms the algorithm’s generalization capability. Crucially, statistical analysis reveals a distinctive performance profile: while recent state-of-the-art methods like L-SRTDE (rank 1.47) achieve superior precision on unimodal basins, DPASA demonstrates resilience on deceptive multimodal landscapes, successfully escaping local optima where competitors stagnate. On five constrained engineering design problems, the algorithm achieves near-optimal gaps (<span><math><mrow><mo>≤</mo><mn>0</mn><mo>.</mo><mn>11</mn><mtext>%</mtext></mrow></math></span>). These findings establish DPASA not merely as another variation, but as a specialized, reliable option for sophisticated, deceptive landscapes where standard covariance-based methods falter. Source code is available at <span><span>https://github.com/haythemghz/DPASA-algorithm</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102320"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147398162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-objective optimization in autonomous foraging using swarm robots 群机器人自主觅食的多目标优化

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-01-16 DOI: 10.1016/j.swevo.2026.102294

Erick J. Ordáz-Rivas, Angel Rodríguez-Liñan, Luis M. Torres-Treviño

{"title":"Multi-objective optimization in autonomous foraging using swarm robots","authors":"Erick J. Ordáz-Rivas, Angel Rodríguez-Liñan, Luis M. Torres-Treviño","doi":"10.1016/j.swevo.2026.102294","DOIUrl":"10.1016/j.swevo.2026.102294","url":null,"abstract":"<div><div>Swarm robotics is an innovative field focused on developing collective behaviors through local interactions among simple robots, enabling scalability and flexibility across a wide range of tasks. This study presents a behavioral model for collective foraging based on <em>RAOI</em> (repulsion, attraction, orientation, and influence) parameters, and investigates how their tuning affects multi-objective performance in robot swarms. Our approach explores the relationship between <em>RAOI</em> parameter configurations and task-level performance metrics, allowing systematic analysis of emergent swarm behaviors in dynamic environments.</div><div>In this work, the tuning of <em>RAOI</em> parameters is formulated as a multi-objective optimization problem guided by established evolutionary algorithms (MOEA/D and NSGA-III), yielding Pareto-optimal trade-offs among competing objectives. The obtained solutions illustrate improvements across multiple criteria, including task completion time, energy consumption, workload distribution, and swarm size efficiency, highlighting inherent trade-offs rather than a single optimal configuration.</div><div>The results provide insights into how <em>RAOI</em>-based interaction parameters influence collective foraging dynamics and overall swarm performance. The study focuses on simulation-based evaluation, offering a structured framework for analyzing and tuning swarm behaviors in foraging tasks and related collective robotics scenarios.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102294"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An ensemble model for high dimensional feature selection based on binary arithmetic optimization algorithm 基于二元算法优化的高维特征选择集成模型

IF 8.5 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-02-01 Epub Date: 2026-01-22 DOI: 10.1016/j.swevo.2026.102298

Shu-Chuan Chu , Zhongjie Zhuang , Haibin Sun , Jia Zhao , Jeng-Shyang Pan

{"title":"An ensemble model for high dimensional feature selection based on binary arithmetic optimization algorithm","authors":"Shu-Chuan Chu , Zhongjie Zhuang , Haibin Sun , Jia Zhao , Jeng-Shyang Pan","doi":"10.1016/j.swevo.2026.102298","DOIUrl":"10.1016/j.swevo.2026.102298","url":null,"abstract":"<div><div>Traditional feature selection algorithms often face performance degradation or even fail to execute when handling high-dimensional data with over 1000 features. Existing studies predominantly rely on the classical Particle Swarm Optimization (PSO). To investigate the applicability of multigoal strategies to other evolutionary algorithms, this paper extends the binary arithmetic optimization algorithm (BAOA) by incorporating a multigoal framework. The method begins by designing eight distinct yet interrelated goals based on four filter-based algorithms (PCC, CHI2, ReliefF, and NCA) to form goal groups. Furthermore, a sparse initialization method employing a roulette wheel selection strategy is introduced to reduce the number of initially selected features. The proposed Ensemble Binary Arithmetic Optimization Algorithm (EBAOA) integrates a multi-goal optimization mechanism into the original binary arithmetic optimization framework, achieving a significant reduction in error rate. Extensive experiments on 24 high-dimensional datasets demonstrate that EBAOA consistently selects the smallest feature subsets while maintaining the lowest error rates across multiple classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results highlight the effectiveness of the multi-goal strategy, and sparse initialization in enhancing feature selection performance for high-dimensional data. The source code will be released upon acceptance at: <span><span>https://github.com/zhongjiezhuang/EBAOA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"101 ","pages":"Article 102298"},"PeriodicalIF":8.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0