Swarm and Evolutionary Computation最新文献

Scheduling two-stage healthcare appointment systems via a knowledge-based biased random-key genetic algorithm

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-09 DOI: 10.1016/j.swevo.2025.101864

Fajun Yang , Chao Li , Feng Wang , Zhi Yang , Kaizhou Gao

{"title":"Scheduling two-stage healthcare appointment systems via a knowledge-based biased random-key genetic algorithm","authors":"Fajun Yang , Chao Li , Feng Wang , Zhi Yang , Kaizhou Gao","doi":"10.1016/j.swevo.2025.101864","DOIUrl":"10.1016/j.swevo.2025.101864","url":null,"abstract":"<div><div>To address the scheduling problem of two-stage healthcare appointment systems, previous studies always assume that a positive linear correlation is obeyed between the customer waiting time and service dissatisfaction, and an arrived customer is served immediately if the provider at the first stage becomes available, which usually leads to heavy congestion at the second stage and a rapid decline in service satisfaction. To tackle this problem further, this paper assumes that customer waiting time within different ranges impacts service dissatisfaction differently. Then, it develops an efficient real-time scheduling strategy to decide the exact starting time of each customer's service at the first stage. Considering no-shows and non-punctual appointments, a knowledge-based biased random-key genetic algorithm (<em>K-BRKGA</em>) is used to determine the number of customers at each appointment slot, such that the total weighted cost associated with customers’ waiting time, providers’ idle time, and overtime at two stages can be minimized. Based on the data sets used, <em>K-BRKGA</em> reduces the total cost by 2.01 % and 1.01 % compared to the other two famous algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101864"},"PeriodicalIF":8.2,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372895","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 large-scale optimization algorithm based on variable decomposition and space compression

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-08 DOI: 10.1016/j.swevo.2025.101863

Haiyan Liu , Wenlong Song , Yi Cheng , Shouheng Tuo , Yuping Wang

{"title":"A large-scale optimization algorithm based on variable decomposition and space compression","authors":"Haiyan Liu , Wenlong Song , Yi Cheng , Shouheng Tuo , Yuping Wang","doi":"10.1016/j.swevo.2025.101863","DOIUrl":"10.1016/j.swevo.2025.101863","url":null,"abstract":"<div><div>Optimizing large-scale problem is very challenging due to the unknown landscape, huge search space of countless combinations of decision variables and the inner complexity of the problem. To better solve this kind of problem, a decomposition and compression based algorithm (DCBA) is proposed to decompose the problem and compress the search space for efficient optimization. Firstly, three space compression based linear search methods are designed with two functionalities: (1) to carry out a quick and rough optimization and find relatively good initial solutions; (2) to gather important information of each dimension (decision variable) for subsequent processing. In the three linear search methods, we design ways to evaluate the search region and compress it into smaller regions that may contain better solutions. Then, four decomposition methods are designed for fully non-separable large-scale problems. These methods can generate as many as twenty-nine different decomposition results to enhance the decomposition diversity in order to make a better trade-off of the non-separability characteristic and the decomposition for complexity reduction of fully non-separable large-scale problems. Finally, a decomposition and compression based algorithm (DCBA) is proposed to solve large-scale problems. Numerical experiments are conducted on two widely used benchmark suites and comparisons with state-of-the-art algorithms are made. The results show that the proposed algorithm is effective and efficient.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101863"},"PeriodicalIF":8.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143351179","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

Enhanced QPSO driven by swarm cooperative evolution and its applications in portfolio optimization

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-07 DOI: 10.1016/j.swevo.2025.101872

Xiao-li Lu , Guang He

{"title":"Enhanced QPSO driven by swarm cooperative evolution and its applications in portfolio optimization","authors":"Xiao-li Lu , Guang He","doi":"10.1016/j.swevo.2025.101872","DOIUrl":"10.1016/j.swevo.2025.101872","url":null,"abstract":"<div><div>Being a simple and popular method grounded in swarm evolution, Quantum-behaved particle swarm optimization (QPSO) has been extensively implemented to seek the optimal solution of various practical cases. Nevertheless, while managing intricate multimodal problems, the original QPSO algorithm renders the algorithm susceptible to premature convergence, characterized by slow iteration speed and suboptimal searching precision. To deal with these disadvantages, this paper puts forward an enhanced QPSO driven by swarm cooperative evolution (SCQPSO). In the SCQPSO algorithm, a binary swarm cooperative evolution strategy is designed to enhance QPSO’s convergence speed and optimization precision. Additionally, some improvement measures including Halton sequence initialization of individual locations, maintenance of population diversity, and mutation strategy for out-of-bounds particles, are also adopted to facilitate prevention of premature convergence and assist the algorithm in overcoming local optimality. Then, compared results obtained by SCQPSO and six improved intelligent approaches on CEC 2017 cases indicate that SCQPSO offers highly competitive solutions when solving complex multimodal problems. Further, the exceptional capability of SCQPSO in addressing two portfolio optimization issues demonstrates its outstanding global search performance.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101872"},"PeriodicalIF":8.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143305510","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-assisted single-objective differential evolution by reinforcement learning

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-07 DOI: 10.1016/j.swevo.2025.101866

Haotian Zhang , Xiaohong Guan , Yixin Wang , Nan Nan

{"title":"Multi-objective optimization-assisted single-objective differential evolution by reinforcement learning","authors":"Haotian Zhang , Xiaohong Guan , Yixin Wang , Nan Nan","doi":"10.1016/j.swevo.2025.101866","DOIUrl":"10.1016/j.swevo.2025.101866","url":null,"abstract":"<div><div>“Learning to optimize” design systems for evolutionary algorithm (EA) automatic design have become a trend, especially for differential evolution (DE). “Learning to optimize” design systems for EAs have two main parts: an excellent “backbone” algorithm with learnable components, and a learning scheme to determine the components of the “backbone” algorithm. A good “backbone” algorithm is of great importance for the algorithm design, because it determines the algorithm design space and potential. The learning scheme determines whether we can realize the potential or not. Existing studies generally choose one developed EA as the “backbone” algorithm, which constrains the potential of the design system because the “backbone” algorithm is relatively simple. To solve the problem and design a good EA, in this paper, we first propose a three-stage hybrid DE framework for single objective optimization, called SMS-DE, which implements single-objective DE, multi-objective DE, and single-objective DE sequentially. The multi-objective DE aims to enhance exploration ability. Second, we apply the framework to two advanced DEs, JADE and LSHADE, which results in two new algorithms: SMS-JADE and SMS-LSHADE. Third, the newly proposed algorithm, SMS-LSHADE, is considered the “backbone” algorithm, and the reinforcement learning method (Q-learning) is used to control the parameter for allocating computational resources to each stage, which results in another algorithm called QSMS-LSHADE. Experimental results on the CEC 2018 test suite show that SMS-DE, SMS-JADE, and SMS-LSHADE can perform significantly better than their counterparts and that SMS-QLSHADE performs the best among many developed DEs.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101866"},"PeriodicalIF":8.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349680","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 improved adaptive hybrid algorithm for solving distributed flexible job shop scheduling problem

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-06 DOI: 10.1016/j.swevo.2025.101873

Cuiyu Wang , Mengxi Wei , Qihao Liu , Xinjian Zhang , Xinyu Li

{"title":"An improved adaptive hybrid algorithm for solving distributed flexible job shop scheduling problem","authors":"Cuiyu Wang , Mengxi Wei , Qihao Liu , Xinjian Zhang , Xinyu Li","doi":"10.1016/j.swevo.2025.101873","DOIUrl":"10.1016/j.swevo.2025.101873","url":null,"abstract":"<div><div>With economic globalization, collaboration between enterprises has increased significantly. Complex products are now often produced in multiple workshops, either within a single company or across several. This shift has led to the rise of distributed manufacturing, a modern and rapidly expanding production method. This paper puts forward an Improved Adaptive Hybrid Algorithm (IAHA) to address the Distributed Flexible Job Shop Problem (DFJSP). A mathematical model of DFJSP is established based on the characteristics of distributed manufacturing. A hybrid decoding rule is proposed, using a dual-layer encoding approach to represent both factories and jobs. The initialization, crossover, and mutation operators are designed to efficiently tackle the job allocation challenge across distributed factories. In the local search phase, an adaptive variable neighborhood search method focuses on critical factories. Numerical experiments on a benchmark set of DFJSP instances with 2, 3, and 4 factories demonstrate the effectiveness of IAHA, breaking records for several instances and achieving optimal results for others. Comparisons with other algorithms show the IAHA's superior performance in solving the DFJSP.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101873"},"PeriodicalIF":8.2,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143305048","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

Enhancing healthcare resource allocation through large language models

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-05 DOI: 10.1016/j.swevo.2025.101859

Fang Wan , Kezhi Wang , Tao Wang , Hu Qin , Julien Fondrevelle , Antoine Duclos

{"title":"Enhancing healthcare resource allocation through large language models","authors":"Fang Wan , Kezhi Wang , Tao Wang , Hu Qin , Julien Fondrevelle , Antoine Duclos","doi":"10.1016/j.swevo.2025.101859","DOIUrl":"10.1016/j.swevo.2025.101859","url":null,"abstract":"<div><div>Recognizing the growing capabilities of large language models (LLMs) and their potential in healthcare, this study explores the application of LLMs in healthcare resource allocation using Prompt Engineering, Retrieval-Augmented Generation (RAG), and Tool Utilization. It addresses both optimizable and non-optimizable challenges in allocating operating rooms (ORs), postoperative beds, and surgeons, while also identifying key factors like ethical and legal constraints through a medical knowledge Q&A survey. Among the seven evaluated LLMs, including LaMDA 2, PaLM 2, and Qwen, ChatGPT-4o demonstrated superior performance by reducing OR and surgeon overtime, alleviating peak bed demand, and achieving the highest accuracy in medical knowledge queries. Comprehensive comparisons with traditional methods (exact and heuristic algorithm), varying problem sizes, and hybrid approaches from the literature revealed that as problem size increased, LLMs performed better and faster by integrating historical experience with new data. They adapted to changes in problem scale or demand without requiring re-optimization, effectively addressing the runtime limitations of traditional methods. These findings underscore the potential of LLMs in advancing dynamic and efficient healthcare resource management.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101859"},"PeriodicalIF":8.2,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176222","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 particle swarm algorithm for effluent scheduling problem with an influent estimation of WWTP

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-03 DOI: 10.1016/j.swevo.2025.101871

HAN HongGui , XU ZiAng , WANG JingJing

{"title":"Reinforcement learning-assisted particle swarm algorithm for effluent scheduling problem with an influent estimation of WWTP","authors":"HAN HongGui , XU ZiAng , WANG JingJing","doi":"10.1016/j.swevo.2025.101871","DOIUrl":"10.1016/j.swevo.2025.101871","url":null,"abstract":"<div><div>Effluent scheduling of wastewater treatment process (WWTP) is essential to ensure compliance with regulatory standards regarding effluent quality. Through the integration of pipe and plant systems, the influent can be estimated prior to entering the treatment process, providing additional information for scheduling. However, the traditional evolutionary computation methods face challenges in utilizing information from inflow estimation, resulting in decisions that do not account for long-term returns. For solving effluent scheduling problems with influent estimation, reinforcement learning can facilitate decision-making based on long-term environmental factors to improve the optimization ability of evolutionary computations. Thus, a framework of reinforcement learning-assisted particle swarm optimization algorithm (RLA-PSO) is proposed, using reinforcement learning part to generate solutions and guide optimization by learning from the influent estimation on a long-time scale. Meanwhile, it employs the optimization part to find the optimal solutions to intensify the learning effect of the reinforcement learning part. For the reinforcement learning part, a deep <em>Q</em>-network method with appropriate states and rewards is designed to efficiently learn the relationship between state, action and reward for the coming period. For the optimization part, a set-based particle optimization algorithm is employed to search for the optimized solution in a future period. The benchmark simulation model No.1(BSM1) is used to evaluate the performance of the proposed RLA-PSO algorithm for the effluent scheduling problem of WWTP. The computational experiments to the state-of-the-art methods show the proposed algorithm can achieve superior performance in effluent quality and process efficiency.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101871"},"PeriodicalIF":8.2,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175329","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

Integrated scheduling problem of multi-load AGVs and parallel machines considering the recovery process

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-03 DOI: 10.1016/j.swevo.2025.101861

Xin Fan , Hongyan Sang , Mengxi Tian , Yang Yu , Song Chen

引用次数: 0

Convolutional neural network combined with reinforcement learning-based dual-mode grey wolf optimizer to identify crop diseases and pests

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-03 DOI: 10.1016/j.swevo.2025.101874

Yangchen Lu , Xiaobing Yu , Zhengpeng Hu , Xuming Wang

{"title":"Convolutional neural network combined with reinforcement learning-based dual-mode grey wolf optimizer to identify crop diseases and pests","authors":"Yangchen Lu , Xiaobing Yu , Zhengpeng Hu , Xuming Wang","doi":"10.1016/j.swevo.2025.101874","DOIUrl":"10.1016/j.swevo.2025.101874","url":null,"abstract":"<div><div>Agriculture is crucial for national food security, but crop pests and diseases pose significant threats. Traditional manual methods for detection are subjective, costly, and less accurate. Deep learning, especially convolutional neural network, is revolutionizing crop pest and disease identification, manual hyperparameter tuning can lead to suboptimal results. In contrast, grey wolf optimizer has demonstrated effective global search capabilities in hyperparameter optimization, improving model performance. Therefore, a reinforcement learning-based dual-mode grey wolf optimizer is introduced to enhance the performance of the original algorithm in hyperparameter optimization and identify the optimal hyperparameters, which combines a dynamic elite learning strategy and a dual-mode adaptive strategy well balanced with the exploration and exploitation of populations, while the integration of the reinforcement learning technique strengthens the information feedback. To validate the effectiveness of the proposed algorithm, additional ablation experiments were conducted, and experiments using CPU time as the termination criterion were included to increase rigor and ensure fairness. The main hyperparameters of convolutional neural network optimized by the proposed algorithm is utilized for the recognition of the pentatomidae stinkbug pests and corn diseases, with experimental results compared against six other intelligent optimization algorithms. Results from two sets of experiments indicate that the proposed algorithm improves the recognition accuracy of the original convolutional neural networks model, achieving the highest accuracy on the pest dataset at 95.83 % and on the corn disease dataset at 96.51 %.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101874"},"PeriodicalIF":8.2,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175332","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

Handling objective preference and variable uncertainty in evolutionary multi-objective optimization

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-02-03 DOI: 10.1016/j.swevo.2025.101860

Deepanshu Yadav , Palaniappan Ramu , Kalyanmoy Deb

{"title":"Handling objective preference and variable uncertainty in evolutionary multi-objective optimization","authors":"Deepanshu Yadav , Palaniappan Ramu , Kalyanmoy Deb","doi":"10.1016/j.swevo.2025.101860","DOIUrl":"10.1016/j.swevo.2025.101860","url":null,"abstract":"<div><div>Evolutionary algorithms (EAs) are widely employed in multi-objective optimization (MOO) to find a well-distributed set of near-Pareto solutions. Among various types of practicalities that demand standard evolutionary multi-objective optimization (EMO) algorithms to be modified suitably, we propose here a framework for handling two important ones: (i) decision-making to choose one or more preferred Pareto regions, rather than finding the entire Pareto set, and (i) uncertainty in variables and parameters of the problem which is inevitable in any practical problem. While the first practicality will allow a focused set of preferred solutions to be found, the second practicality will enable finding robust yet high-performing non-dominated solutions. We propose and analyze four different approaches for finding preferred and robust solutions for handling both practicalities simultaneously. Our results on a number of two to 10-objective tests and engineering problems indicate the superiority of one specific approach. For a comprehensive evaluation of new EMO algorithms for finding a preferred and robust solution set, we also propose a new performance metric by identifying and utilizing a number of desired properties of such trade-off solutions. The study is comprehensive and should encourage researchers to develop more competitive EMO algorithms for finding preferred and robust Pareto solutions.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"94 ","pages":"Article 101860"},"PeriodicalIF":8.2,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175330","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