Swarm and Evolutionary Computation最新文献

{"title":"Hybrid IPSO-Optimized Machine Learning for Aging Classification of Polymeric Insulators under Dry and Wet Conditions","authors":"Ali Ahmed Salem,&nbsp;Waleed M. Hamanah,&nbsp;Salem Mgammal Al-Ameri","doi":"10.1016/j.swevo.2026.102537","DOIUrl":"10.1016/j.swevo.2026.102537","url":null,"abstract":"<div><div>The surface aging of polymeric insulators, extensively employed in power systems, presents significant challenges. This aging can lead to reduced insulation performance, increased leakage currents, and a higher risk of equipment failure. This paper proposes an efficient framework that integrates a hybrid machine learning (ML) model, Extreme Gradient Boosting and Multilayer Perceptron (XGBoost-MLP), with improved PSO (IPSO) for classifying polymeric insulators' aging status under dry and wet conditions. The proposed model is evaluated using a four-fold Leave-One-Insulator-Per-Class-Out (LOIPCO) protocol to provide a robust assessment across unseen insulators. Uniform Manifold Approximation and Projection (UMAP) is applied as a data-driven dimensionality reduction technique in model improvement. The leakage current of the selected samples has been tested, and the 14 features of the time and frequency domains of the LC signal are extracted to classify insulator aging. Based on the permutation importance technique, ten features were selected in this study. Examining the suggested criteria reveals that they are strongly correlated with insulator aging. Even though XGBoost-MLP outperformed traditional models, hyperparameter optimization with an improved PSO further reduced misclassification. IPSO-XGBoost-MLP achieved the best classification accuracy. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to analyze and interpret the results, providing insights into the factors influencing model predictions. SHAP analysis showed that PSD_mean, energy, and peak have the greatest effect on the aging classification model. In the dry insulator dataset, Peak dominates, while in the wet model, energy dominates. In both cases, Std and Ent always rank last. The outcome of this work aids in evaluating surface aging and has potential applications in the condition assessment of polymeric insulation.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102537"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149004638","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}

{"title":"Optimized Task Scheduling in Cloud Computing Environments Using Adaptive Enhanced Particle Swarm Optimization","authors":"Vaishali Mehta,&nbsp;Anu Gupta Prof.","doi":"10.1016/j.swevo.2026.102510","DOIUrl":"10.1016/j.swevo.2026.102510","url":null,"abstract":"<div><div>Cloud computing has become a fundamental platform for data-intensive applications, but efficient task scheduling remains challenging because of workload variability, resource heterogeneity, and the need to balance multiple conflicting objectives. This study presents an Adaptive Enhanced Particle Swarm Optimization (AEPSO) model for a cloud task scheduling problem involving makespan, execution cost, load imbalance, and energy consumption. In the proposed framework, these objectives are handled through weighted, normalized scalarization, which reduces them to a single scalar fitness value. To improve convergence stability and scheduling quality, the model integrates stagnation-aware inertia control, time-varying schedules for the cognitive and social coefficients, velocity clamping, elitist preservation, and repair-based refinement. The method is evaluated in the CloudSim environment using Bitbrains-based workload traces for independent cloudlet scheduling and is compared with baseline algorithms, including PSO, PSO-Boost, MrLBA-ACO, and GA, over selected workload levels. The results indicate that AEPSO provides the most favorable overall trade-off among the methods compared, with clear gains in makespan and strong performance on load imbalance and energy consumption, while maintaining competitive execution-cost performance. Additional analysis through repeated-run statistics, significance testing, weight sensitivity analysis, and ablation study further supports the effectiveness of the proposed integrated scheduling framework under the considered simulation setting.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102510"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148855791","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}

{"title":"MOVLPSO-CNN-BiLSTM: Multi-objective variable-length particle swarm optimization-based CNN-BiLSTM for medium-term electric load forecasting","authors":"Guo-Qiang Zeng,&nbsp;De-Gui Yu,&nbsp;Li-Min Li,&nbsp;Yi-Peng Xu,&nbsp;Guang-Gang Geng,&nbsp;Chen Peng,&nbsp;Fei Chu","doi":"10.1016/j.swevo.2026.102520","DOIUrl":"10.1016/j.swevo.2026.102520","url":null,"abstract":"<div><div>In recent years, deep learning-based electric load forecasting models have been widely applied, but most existing approaches rely on single deep learning, where both neural architecture and hyper-parameters are typically designed through manual trial-and-error processes. Furthermore, these methods often focus exclusively on forecasting accuracy while neglecting model complexity considerations during the design process. To address these limitations, this paper proposes an innovative automated deep learning-based load forecasting method, i.e., multi-objective variable-length particle swarm optimization (MOVLPSO)-based convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM), abbreviated as MOVLPSO-CNN-BiLSTM. The framework utilizes CNN-BiLSTM as its foundational predictor, effectively combining CNN’s feature extraction capabilities with BiLSTM’s temporal sequence processing strengths. Firstly, the automated design issue of the neural architecture and hyper-parameters for CNN-BiLSTM-based forecasting model is formulated as a multi-objective optimization problem by considering both minimizing the forecasting error, i.e., mean squared error, and the model complexity, i.e., the number of model parameters (NoMPs). Then, we develop a tailored hybrid variable-length encoding strategy to represent the neural architecture and hyper-parameters of CNN-BiLSTM and the adaptive particle updating mechanism to efficiently evolve the Pareto front in MOVLPSO framework. The experimental results on 12 real-world load datasets obtained from the Australian Energy Market Operator demonstrate that the proposed MOVLPSO-CNN-BiLSTM achieves superior forecasting performance and enhanced model lightweightness compared with one state-of-the-art handcrafted deep neural networks-based and four automated deep learning-based load forecasting approaches in terms of root mean square error, mean absolute error, mean absolute percentage error, and NoMPs.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102520"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148855792","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}

{"title":"A property-aware empirical analysis of differential evolution variants using the generalized numerical benchmark generator","authors":"Rohit Salgotra,&nbsp;Reshu Chaudhary,&nbsp;Amanjot Kaur Lamba,&nbsp;Amir H. Gandomi","doi":"10.1016/j.swevo.2026.102515","DOIUrl":"10.1016/j.swevo.2026.102515","url":null,"abstract":"<div><div>Benchmarking studies in continuous optimization often report aggregate rankings, yet provide limited insight into why particular algorithms succeed or fail under specific landscape conditions. This paper presents a property-aware empirical assessment of ten competitive Differential Evolution (DE) variants using the Generalized Numerical Benchmark Generator (GNBG), a configurable framework that enables controlled manipulation of problem characteristics. Ten state-of-the art variants of DE are tested across three distinct datasets. The first dataset, GNBG-45, featuring 45 problem instances, each designed to isolate a single landscape property such as basin linearity, conditioning, variable interactions, symmetry or deceptiveness. The remaining datasets, GNBG-I and GNBG-II, are well established in the literature and include 24 functions each, covering unimodal, multimodal single component and multimodal multiple component problems. Together, these data sets provide a layered and comprehensive benchmarking environment. Experimental results show that ALSHADE exhibits the strongest overall robustness and consistency across diverse landscape categories and benchmark suites, while LSHADE-SPACMA exhibits the strongest scalability and robustness in multiple dimensional settings. Other variants, including IMODE, EA4eig, APSM-jSO, and TSALSHADE, demonstrate competitive behavior on selected problem classes but lower overall consistency. Overall, the study shows the ability of GNBG to distinguish algorithmic behavior in a variety of problem structures, supporting its use as a detailed and property-aware benchmarking suite.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102515"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149004177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated scheduling of machines and AGVs for a multi-objective flexible job shop scheduling problem with AGV charging constraints","authors":"Xiaoxiao Lin,&nbsp;Wenjie Liu,&nbsp;Jian Chen,&nbsp;Jianfu Chen,&nbsp;Liang Liu","doi":"10.1016/j.swevo.2026.102521","DOIUrl":"10.1016/j.swevo.2026.102521","url":null,"abstract":"<div><div>The flexible job-shop scheduling problem with automated guided vehicles (FJSP-AGV) is increasingly situated within highly complex manufacturing environments, marked by frequent AGV recharging requirements and the necessity of simultaneously optimizing multiple, often conflicting, performance objectives. Unscheduled AGV charging operations significantly undermine the coherence and implement ability of integrated scheduling decisions, thereby degrading performance across all key optimization objectives. To address this gap, this study proposes a novel multi-objective optimization model for the FJSP-AGV which jointly optimizes job sequencing, machine assignment, AGV task allocation, and AGV charging scheduling. The model simultaneously minimizes three key performance indicators: exit time, total energy consumption, and maximum machine workload. An enhanced NSGA-II algorithm, incorporating three improvement strategies, is developed to obtain high-quality Pareto solutions for the integrated scheduling of machines, AGVs, and charging activities. The proposed model and algorithm are evaluated using 90 scaled FJSP-AGV benchmark instances with charging constraints, 10 classical FJSP instances, and a real-world electronics manufacturing case. The results demonstrated that the proposed algorithm significantly outperformed the state-of–art representative multi-objective algorithms and obtain high-quality Pareto solutions. Moreover, sensitivity analyses further show that AGV battery capacity, charging rate, charging threshold, and fleet size have substantial effects on scheduling performance, and then optimal AGV parameter configurations were identified. These findings provide actionable, evidence-based managerial insights for the strategic configuration of AGV systems and support integrated decision-making across production scheduling, material handling, and AGV charging decisions in intelligent manufacturing enterprises.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102521"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148953523","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}

{"title":"Landscape-driven stochastic variation: A Data-Driven Meta-Learning Framework for Adaptive Mutation Control (DD-AMC) in constrained evolutionary multi-objective optimisation","authors":"Nedjma Abidallah,&nbsp;Samir Bourekkache,&nbsp;Laid Kahloul,&nbsp;Okba Ben Atia,&nbsp;Mohamed Khalgui,&nbsp;Pascal Lorenz","doi":"10.1016/j.swevo.2026.102535","DOIUrl":"10.1016/j.swevo.2026.102535","url":null,"abstract":"<div><div>Evolutionary multi-objective optimisation frameworks, such as CNSGA-II and CMOEA/D, heavily rely on precise parameter configurations – particularly the mutation rate – to balance local exploitation and global exploration. However, these frameworks are predominantly deployed using static mutation rates (e.g., <span><math><mrow><msub><mrow><mi>p</mi></mrow><mrow><mi>m</mi></mrow></msub><mo>=</mo><mn>1</mn><mo>/</mo><mi>D</mi></mrow></math></span>) or rigid dynamic heuristics. As objective and constraint dimensions scale, these static approaches lack situational awareness, frequently causing the search process to stagnate in highly fragmented feasible regions. To address this limitation, we propose the Data-Driven Meta-Learning Adaptive Mutation Controller (DD-AMC). Our framework replaces static heuristics with a multi-layered control paradigm: an offline-trained ensemble model that executes a priori inference to establish an optimal initial mutation rate based on structural meta-features at <span><math><mrow><mi>t</mi><mo>=</mo><mn>0</mn></mrow></math></span>, and an online feedback controller that continuously monitors evolutionary stagnation. To prevent premature convergence, this controller dynamically scales the mutation probability and triggers a biologically-inspired “Stagnation Override System (SOS) Mode” to forcefully escape deep local optima. Finally, an archival data-driven logging loop systematically captures successful parameter configurations from completed runs to expand the repository for subsequent offline retraining. We evaluate DD-AMC enhanced algorithms across a diverse suite of constrained multi-objective benchmarks, including scalable many-objective instances. Experimental results demonstrate that our approach generally improves upon static and conventional dynamic counterparts, particularly on scalable many-objective and fragmented constrained instances, while acknowledging that highly volatile, time-varying topologies (e.g., DASCMOP1/3) remain challenging across key convergence metrics, effectively preventing stagnation and ensuring robust adaptability across varying objective dimensions.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102535"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149004179","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}

{"title":"Reinforcement learning based multi-population co-evolution algorithm with indicator preference guidance for multiobjective optimization","authors":"Kaibin Xu,&nbsp;Te Xu,&nbsp;Xianpeng Wang,&nbsp;Erchao Li","doi":"10.1016/j.swevo.2026.102534","DOIUrl":"10.1016/j.swevo.2026.102534","url":null,"abstract":"<div><div>Multiobjective optimization problems (MOPs) require a delicate balance between convergence to the Pareto front (PF) and diversity maintenance. Traditional algorithms often struggle with high-dimensional objectives and a complex PF. This paper introduces a reinforcement learning (RL)-based multi-population co-evolution algorithm with indicator preference guidance (MPCEP), in which each subpopulation plays a specific role. The first subpopulation focuses on improving solution quality through a convergent external archive and a preference evolution strategy, utilizing preference guidance based on solution similarity and reverse evolution to direct solutions towards the true PF. The second subpopulation encourages exploration and ensures diversity by employing a dynamic penalty strategy that prevents premature convergence. The third subpopulation integrates reinforcement learning with a reward–penalty mechanism to promote the emergence of suboptimal solutions, allowing for adaptive preference adjustments during the search process. This co-evolutionary structure facilitates dynamic adjustment for efficient exploration and exploitation of the decision space, while promoting collaboration between subpopulations. Extensive experiments on benchmark problems and real-world problems demonstrate that MPCEP consistently outperforms existing algorithms in terms of both convergence and diversity, highlighting its robustness and adaptability in solving multiobjective optimization problems across various domains.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102534"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148996307","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}

{"title":"A systematic survey on large-scale multi-agent reinforcement learning: Abstraction, decomposition, and evolution","authors":"Lun Zhang,&nbsp;Baichuan Wang,&nbsp;Zhifang Chen,&nbsp;Hao Chen,&nbsp;Jianxing Gong,&nbsp;Jian Huang,&nbsp;Sihang Zhou","doi":"10.1016/j.swevo.2026.102529","DOIUrl":"10.1016/j.swevo.2026.102529","url":null,"abstract":"<div><div>As multi-agent systems expand to massive scales, traditional Multi-Agent Reinforcement Learning (MARL) is severely constrained by the curse of dimensionality, environmental non-stationarity, and intensified credit assignment issues. Existing surveys focus on general MARL or small-scale cooperation, lacking a systematic synthesis of approaches specifically designed for large-scale settings. This survey systematically reviews a curated body of papers published between 2016 and 2026, identified through keyword-based search across six major databases (IEEE Xplore, ACM Digital Library, arXiv, Web of Science, Scopus, and Google Scholar) with defined inclusion and exclusion criteria. We propose a novel taxonomy that categorizes large-scale MARL algorithms based on their underlying problem-solving philosophies: abstraction (temporal, spatial, and population) to reduce model complexity, and decomposition combined with progressive evolution to reduce task difficulty. For each category, we provide critical comparative analysis, discuss failure modes and limitations, and map methods to the specific scalability bottlenecks they address. We further review representative engineering applications—ranging from computational job scheduling and intelligent transportation systems to physical swarm confrontation—and critically evaluate standard benchmark environments. Finally, we identify open challenges, formulate concrete research questions, and propose a three-stage roadmap for the field. This survey aims to serve as a structured guide for researchers entering LS-MARL and a critical reference for practitioners designing scalable multi-agent systems.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102529"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149004640","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}

{"title":"A surrogate-assisted multi-objective optimization algorithm for antibody design with multi-source datasets","authors":"Ziyang Shi,&nbsp;Xinyi Xu,&nbsp;Haotian Zhang,&nbsp;Shenghan Ren,&nbsp;Handing Wang","doi":"10.1016/j.swevo.2026.102526","DOIUrl":"10.1016/j.swevo.2026.102526","url":null,"abstract":"<div><div>Antibody design plays a crucial role in therapeutic development and can be formulated as a multi-objective optimization problem, in which multiple favorable biophysical properties with strong trade-offs must be optimized simultaneously. Since evaluating these properties is computationally expensive, newly generated antibodies during the optimization process cannot be evaluated and are instead estimated using surrogate models. However, the data available for surrogate training are limited and originate from multiple sources with varying experimental standards, making prediction accuracy difficult to guarantee. This issue may mislead the multi-objective optimization process. To address this issue, we propose a surrogate-assisted multi-objective optimization algorithm that fully leverages limited multi-source datasets. The proposed method integrates a global evolutionary search guided by a global surrogate model with a local refinement stage guided by a local surrogate model, thereby effectively enhancing optimization performance. Computational experiments demonstrate that the proposed method significantly outperforms state-of-the-art offline multi-objective baselines, achieving superior hypervolume values and consistently identifying a diverse set of high-quality antibody variants. Rosetta ddG simulations indicate that 93.8% of the optimized variants exhibit lower binding free energy values than the previously reported optimal antibody, while over 50% of the variants also maintain comparable specificity according to antibody–antigen binding site analysis. Structural modeling analysis further reveals the enhanced affinity and specificity of the optimized variants at the molecular level.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102526"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148953522","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}

{"title":"Dijkstra-assisted evolutionary multiobjective optimization for a sustainable user urban multimodal transport routing","authors":"Guilherme Barbosa,&nbsp;Pedro José Pereira,&nbsp;Rui Mendes,&nbsp;Paulo Cortez","doi":"10.1016/j.swevo.2026.102512","DOIUrl":"10.1016/j.swevo.2026.102512","url":null,"abstract":"<div><div>Assuming the Mobility as a Service (MaaS) paradigm, this paper addresses a sustainable multimodal user routing problem by jointly minimizing total travel time and CO₂ emissions in large-scale public transport networks. We propose the enhanced Dijkstra-assisted Non-dominated Sorting Genetic Algorithm II (eD50N-II) method, an evolutionary multiobjective approach that uses the Dijkstra’s (DJ) shortest path algorithm to generate an informed seeding strategy with tailored crossover and mutation operators. The method operates on real-world multimodal multigraphs, supports flexible integer-based solution representations and considers realistic public transport schedules, transfer times, walking connections, and physical effort constraints. An extensive experimental evaluation is conducted on two large metropolitan case studies, Oporto and Lisbon, which are here made publicly available for the first time. Results show that eD50N-II consistently outperforms other evolutionary approaches, including the DJ Seeded NSGA-II (D2N-II, the baseline algorithm), eN-II (an improved NSGA-II variant) and Haq* (an adaptation of a state-of-the-art method), in terms of hypervolume, number of Pareto-optimal solutions, and feasibility with respect to walking distance constraints. As for simpler DJ configurations, such as the weighted D50 variant, they require less computation and may be suitable for time-critical applications where solution quality is less critical. Nevertheless, eD50N-II obtains a richer set of Pareto-optimal solutions under a reasonable computational effort, resulting in the most effective option when high-quality and practically meaningful (human effort-friendly) routes are required. The results also confirm the scalability and robustness of the proposed method across different urban contexts, reinforcing its suitability for real-world MaaS decision support systems.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"108 ","pages":"Article 102512"},"PeriodicalIF":9.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148855779","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}