Swarm and Evolutionary Computation最新文献

{"title":"An ensemble reinforcement learning-assisted deep learning framework for enhanced lung cancer diagnosis","authors":"Richa Jain,&nbsp;Parminder Singh,&nbsp;Avinash Kaur","doi":"10.1016/j.swevo.2024.101767","DOIUrl":"10.1016/j.swevo.2024.101767","url":null,"abstract":"<div><div>Lung cancer ranks among the most lethal diseases, highlighting the necessity of early detection to facilitate timely therapeutic intervention. Deep learning has significantly improved lung cancer prediction by analyzing large healthcare datasets and making accurate decisions. This paper proposes a novel framework combining deep learning with integrated reinforcement learning to improve lung cancer diagnosis accuracy from CT scans. The data set utilized in this study consists of CT scans from healthy individuals and patients with various lung stages. We address class imbalance through elastic transformation and employ data augmentation techniques to enhance model generalization. For multi-class classification of lung tumors, five pre-trained convolutional neural network architectures (DenseNet201, EfficientNetB7, VGG16, MobileNet and VGG19) are used, and the models are refined by transfer learning. To further boost performance, we introduce a weighted average ensemble model “DEV-MV”, coupled with grid search hyperparameter optimization, achieving an impressive diagnostic accuracy of 99.40%. The integration of ensemble reinforcement learning also contributes to improved robustness and reliability in predictions. This approach represents a significant advancement in automated lung cancer detection, offering a highly accurate, scalable solution for early diagnosis.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101767"},"PeriodicalIF":8.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658391","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":"Multi-population coevolutionary algorithm for a green multi-objective flexible job shop scheduling problem with automated guided vehicles and variable processing speed constraints","authors":"Chao Liu ,&nbsp;Yuyan Han ,&nbsp;Yuting Wang ,&nbsp;Junqing Li ,&nbsp;Yiping Liu","doi":"10.1016/j.swevo.2024.101774","DOIUrl":"10.1016/j.swevo.2024.101774","url":null,"abstract":"<div><div>This study focuses on addressing a multi-objective Flexible Job Shop Scheduling Problem with Automated Guided Vehicles (FJSP-AGVs) and variable processing speed constraints. First, a position-based mixed integer linear programming model (MILP) is proposed to optimize simultaneously the maximum completion time and the total energy consumption. Then, we decompose FJSP-AGVs into four interrelated subproblems and design a Multi-Population Coevolutionary Algorithm (MCEA) to solve them. In MCEA, (1) The effective encoding and decoding methods are used to accurately reflect the characteristics of the problem, and generate feasible scheduling solutions. (2) A multi-rule-based heuristic is proposed to enrich the diversity of four populations. (3) A disjunctive graph is constructed to depict and obtain the critical path(s). On this basis, (4) two cooperative evolution strategies based on critical paths are proposed to facilitate collaborative evolution between different populations and improve the global search capability of the algorithm. Furthermore, (5) a consumption reduction strategy is proposed by reducing the processing speed of operations on non-critical paths while ensuring that it does not affect the makespan. Finally, we validate the effectiveness of MCEA by GD, and IGD, and set coverage metrics on the four typical benchmark datasets. Based on the average GD (IGD) metric across 65 instances, MCEA shows reductions of 77.63% (93.60%), 95.30% (97.27%), and 96.17%(97.89%) relative to EHA, EMOEA, and mop-BRKGA, respectively. The set coverage metric, MCEA outperforms EHA, EMOEA, and mop-BRKGA in 59, 64, and 64 instances, respectively. These results clearly indicate that MCEA can solve the FJSP-AGVs with variable processing speed constraints.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101774"},"PeriodicalIF":8.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658392","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 knowledge-driven many-objective algorithm for energy-efficient distributed heterogeneous hybrid flowshop scheduling with lot-streaming","authors":"Sanyan Chen,&nbsp;Xuewu Wang,&nbsp;Ye Wang,&nbsp;Xingsheng Gu","doi":"10.1016/j.swevo.2024.101771","DOIUrl":"10.1016/j.swevo.2024.101771","url":null,"abstract":"<div><div>More enterprises are enhancing their productive capacity to keep up with the rapidly shifting market demands. Meanwhile, with increasing environmental consciousness, sustainable manufacturing has drawn greater attention. In this paper, the many-objective energy-efficient distributed heterogeneous hybrid flowshop scheduling problem with lot-streaming (DHHFSPLS) is investigated, where the number of sublots is variable. To settle this challenging issue, a mathematical model is established, and a knowledge-driven many-objective optimization evolutionary algorithm (KDMaOEA) is proposed for minimizing makespan, total earliness, total tardiness and total energy consumption. In the KDMaOEA, a knowledge-driven multiple populations collaborative search strategy is devised to strengthen exploitation capabilities. Specifically, the population is divided into five subpopulations, where four superior subpopulations are employed to facilitate the optimization of each objective and one inferior subpopulation learns from four superior subpopulations to effectively utilize the optimization knowledge. Furthermore, an adaptive switching-based environmental selection strategy is fulfilled to guarantee the distribution and convergence of the solution set. Finally, extensive numerical simulations are undertaken to verify the effectiveness of the KDMaOEA in solving the many-objective energy-efficient DHHFSPLS.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101771"},"PeriodicalIF":8.2,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658389","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":"Balancing heterogeneous assembly line with multi-skilled human-robot collaboration via Adaptive cooperative co-evolutionary algorithm","authors":"Bo Tian ,&nbsp;Himanshu Kaul ,&nbsp;Mukund Janardhanan","doi":"10.1016/j.swevo.2024.101762","DOIUrl":"10.1016/j.swevo.2024.101762","url":null,"abstract":"<div><div>In human-centred manufacturing, deploying collaborative robots (cobots) is recognized as a promising strategy to enhance the inclusiveness and resilience of production systems. Despite notable progress, current production scheduling methods for human-robot collaboration (HRC) still fail to adequately accommodate workforce heterogeneity, significantly reducing their adoption and implementation. To address this gap, we introduce a novel model for the Assembly Line Worker Integration and Balancing Problem considering Multi-skilled Human-Robot Collaboration (ALWIBP-mHRC). This model aims to optimize task scheduling between semi-skilled workers and cobots, aiming to maximize productivity and minimize costs. It features a multi-skilled human-robot collaboration (mHRC) task assignment scheme that selects the optimal assembly/collaboration mode from seven scenarios, based on specific task requirements and resource-skill availability, thus maximizing resource-skill complementarity. To tackle the complexities of this problem, we propose an adaptive multi-objective cooperative co-evolutionary algorithm (a-MOCC) that incorporates a sub-problem decomposition and decoding framework tailored for ALWIBP-mHRC, enhanced by an adaptive evolutionary strategy based on Q-learning (Q-Coevolution). Experimental tests demonstrate the superior performance of the proposed method compared to other established metaheuristic algorithms across various instance sizes, underscoring its effectiveness in enhancing the productivity of production systems for semi-skilled workers. The findings are significant for investment decision-making and resource planning, as they highlight the strategic value of integrating cobots in large-scale heterogeneous workforce production. This work underscores the potential of cobots to mitigate skill gaps in assembly systems, laying the groundwork for future research and industrial strategies focused on enhancing productivity, inclusivity, and adaptability in a dynamically changing labour market.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101762"},"PeriodicalIF":8.2,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658390","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":"A collaborative-learning multi-agent reinforcement learning method for distributed hybrid flow shop scheduling problem","authors":"Yuanzhu Di ,&nbsp;Libao Deng ,&nbsp;Lili Zhang","doi":"10.1016/j.swevo.2024.101764","DOIUrl":"10.1016/j.swevo.2024.101764","url":null,"abstract":"<div><div>As the increasing level of implementation of artificial intelligence technology in solving complex engineering optimization problems, various learning mechanisms, including deep learning (DL) and reinforcement learning (RL), have been developed for manufacturing scheduling. In this paper, a collaborative-learning multi-agent RL method (CL-MARL) is proposed for solving distributed hybrid flow-shop scheduling problem (DHFSP), minimizing both makespan and total energy consumption. First, the DHFSP is formulated as the Markov decision process, the features of machines and jobs are represented as state and observation matrixes according to their characteristics, the candidate operation set is used as action space, and a reward mechanism is designed based on the machine utilization. Next, a set of critic networks and actor networks, consist of recurrent neural networks and fully connected networks, are employed to map the states and observations into the output values. Then, a novel distance matching strategy is designed for each agent to select the most appropriate action at each scheduling step. Finally, the proposed CL-MARL model is trained through multi-agent deep deterministic policy gradient algorithm in collaborative-learning manner. The numerical results prove the effectiveness of the proposed multi-agent system, and the comparisons with existing algorithms demonstrate the high-potential of CL-MARL in solving DHFSP.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101764"},"PeriodicalIF":8.2,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658384","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":"MFWOA: Multifactorial Whale Optimization Algorithm","authors":"Lei Ye ,&nbsp;Hangqi Ding ,&nbsp;Haoran Xu ,&nbsp;Benhua Xiang ,&nbsp;Yue Wu ,&nbsp;Maoguo Gong","doi":"10.1016/j.swevo.2024.101768","DOIUrl":"10.1016/j.swevo.2024.101768","url":null,"abstract":"<div><div>Multi-task optimization is an emerging research topic in the field of evolutionary computation, which can exploit the synergy between tasks to solve multiple optimization problems simultaneously and efficiently. However, the correlation and negative transfer problems between tasks are the main challenges faced by multi-task optimization. To this end, this paper proposes a new multi-task optimization algorithm, named Multifactorial Whale Optimization Algorithm (MFWOA). MFWOA uses the Whale Optimization Algorithm (WOA) as a search mechanism and designs an adaptive knowledge transfer strategy to effectively exploit the correlation between tasks. This strategy includes two ways: one is to exchange search experience by adding distance terms from other tasks; the other is to generate new random individuals or optimal individuals through crossover and mutation operations and use them to guide position updates. By combining these two methods, MFWOA can explore a wider area. In addition, in order to better balance the useful information transfer between and within tasks, MFWOA also designs a random mating probability parameter adaptive strategy. Experimental results show that MFWOA can achieve effective and efficient knowledge transfer, and outperforms other multi-task optimization algorithms in terms of convergence speed and accuracy. It is a promising multi-task optimization algorithm.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101768"},"PeriodicalIF":8.2,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658388","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":"Transferring knowledge by budget online learning for multiobjective multitasking optimization","authors":"Fuhao Gao ,&nbsp;Lingling Huang ,&nbsp;Weifeng Gao ,&nbsp;Longyue Li ,&nbsp;Shuqi Wang ,&nbsp;Maoguo Gong ,&nbsp;Ling Wang","doi":"10.1016/j.swevo.2024.101765","DOIUrl":"10.1016/j.swevo.2024.101765","url":null,"abstract":"<div><div>Multiobjective multitasking optimization (MO-MTO) has attracted increasing attention in the evolutionary computation field. Evolutionary multitasking (EMT) algorithms can improve the overall performance of multiple multiobjective optimization tasks through transferring knowledge among tasks. Negative transfer resulting from the indeterminacy of the transferred knowledge may bring about the degradation of the algorithm performance. Identifying the valuable knowledge to transfer by learning the historical samples is a feasible way to reduce negative transfer. Taking this into account, this paper proposes a budget online learning based EMT algorithm for MO-MTO problems. Specifically, by regarding the historical transferred solutions as samples, a classifier would be trained to identified the valuable knowledge. The solutions which are considered containing valuable knowledge will have more opportunity to be transfer. For the samples arrive in the form of streaming data, the classifier would be updated in a budget online learning way during the evolution process to address the concept drift problem. Furthermore, the exceptional case that the classifier fails to identify the valuable knowledge is considered. Experimental results on two MO-MTO test suits show that the proposed algorithm achieves highly competitive performance compared with several traditional and state-of-the-art EMT methods.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"91 ","pages":"Article 101765"},"PeriodicalIF":8.2,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658383","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 congestion-based local search for transmission expansion planning problems","authors":"Phillipe Vilaça ,&nbsp;Luiz Oliveira ,&nbsp;João Saraiva","doi":"10.1016/j.swevo.2023.101422","DOIUrl":"https://doi.org/10.1016/j.swevo.2023.101422","url":null,"abstract":"<div><p>Transmission Expansion Planning (TEP) is a challenging task that takes into consideration future representations of electricity consumption behavior and generation capacity/technology. Besides, the investment in new transmission assets is a capital-intensive task, which motivates a clear and well-justified decision-making process. As the most frequent industry practice relies on cost–benefit analysis with the evaluation of individual reinforcements, Metaheuristic Algorithms (MAs) are the most suitable techniques to evaluate candidate projects efficiently. Likewise, the intrinsic features of the problem can be incorporated into these methods taking advantage of the stochastic knowledge, to build more efficient heuristics instead of considering the solver just as a black box. In this way, this paper proposes a congestion-based local search to improve the performance of metaheuristics when solving the TEP problem. The novelty of the method lies in the utilization of the congestion level of the transmission assets to guide the search procedure. Further, this work also presents an up-to-date comparison between five MAs in solving the TEP problem. The experimental experience is conducted using the mentioned MAs in different test systems, and the results confirm that the novel approach is successful in improving the performance of the solution technique while obtaining better solutions in all test cases.</p></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"83 ","pages":"Article 101422"},"PeriodicalIF":10.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2210650223001955/pdfft?md5=52d7be4960eca5fb201f795edbc6d213&pid=1-s2.0-S2210650223001955-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91987261","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":"A Kriging-assisted Double Population Differential Evolution for Mixed-Integer Expensive Constrained Optimization Problems with Mixed Constraints","authors":"Yuanhao Liu ,&nbsp;Zan Yang ,&nbsp;Danyang Xu ,&nbsp;Haobo Qiu ,&nbsp;Liang Gao","doi":"10.1016/j.swevo.2023.101428","DOIUrl":"10.1016/j.swevo.2023.101428","url":null,"abstract":"<div><p>Many surrogate-assisted evolutionary algorithms (SAEA) with outstanding performance have been developed to handle Expensive Constrained Optimization Problems (ECOPs). But most of them are limited to solving ECOPs with continuous variables and inequality constraints. Therefore, a Kriging-assisted Double Population Differential Evolution (KDPDE) is proposed to deal with mixed-integer ECOPs with inequality and equality constraints. In particular, promising regions near the feasible region are created by Integer restriction Relaxation-based Double Population (IRDP) search framework, and then an Expected Improvement-based Classification local Search (EICS) is adopted to guide the infeasible solutions in the promising region into the feasible region. In order to improve the robustness of the algorithm, the widely distributed elite solutions are utilized by Elite solutions Retention-based Multi-directional Exploration (ERME) for diverse exploration, and the repetition rate information of individuals in the population is used by Population Diversity Maintenance Operation (PDMO) to adaptively avoid the population from falling into a local region. Therefore, KDPDE is capable of balancing the performance between convergence and robustness for mixed-integer ECOPS with mixed constraints. Experimental studies on several benchmark problems and a real-world application example demonstrate that KDPDE has excellent performance on solving such kind of problems under a limited computational budget.</p></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"84 ","pages":"Article 101428"},"PeriodicalIF":10.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2210650223002006/pdfft?md5=7b6398e413e4180c768351cf8b5cb1ce&pid=1-s2.0-S2210650223002006-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135510229","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":"Energy-efficient flexible job shop scheduling problem considering discrete operation sequence flexibility","authors":"Guiliang Gong ,&nbsp;Jiuqiang Tang ,&nbsp;Dan Huang ,&nbsp;Qiang Luo ,&nbsp;Kaikai Zhu ,&nbsp;Ningtao Peng","doi":"10.1016/j.swevo.2023.101421","DOIUrl":"10.1016/j.swevo.2023.101421","url":null,"abstract":"<div><p>The classical flexible job shop scheduling problem (FJSP) normally assumes that operations of each job have strict sequence constraints, i.e., each operation can be processed only after its previous operation is completed. However, in the actual production, the phenomenon that some operations of a job don't have any sequence constraints is very common. With regard to this, we firstly propose a FJSP with discrete operation sequence flexibility (FJSPDS) aiming at minimizing the makespan and total energy consumption, simultaneously. An effective mathematical model is established for the FJSPDS and its validity is proved by the CPLEX; and then an improved memetic algorithm (IMA) is designed to solve the FJSPDS. In the IMA, a new flexible sequencing method for determining process plan of each job and a right-leaning decoding method are proposed. And some effective crossover and mutation operators and an effective local search operator are designed to accelerate the convergence speed and expand the solution space of the algorithm. A total of 110 FJSPDS benchmark instances are constructed to conduct numerical simulation experiments. Experimental results show that our proposed IMA has superior performance in almost all of the instances compared with three well-known evolutionary algorithms. Our proposed model and algorithm can help the production managers who work with flexible manufacturing systems to obtain optimal scheduling schemes considering operations which have or don't have sequence constraints.</p></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"84 ","pages":"Article 101421"},"PeriodicalIF":10.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2210650223001943/pdfft?md5=8be6eec444eb74de54d4c74ee55b1bcc&pid=1-s2.0-S2210650223001943-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135455174","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}