Article
Computer Science, Artificial Intelligence
Chupeng Su, Cong Zhang, Dan Xia, Baoan Han, Chuang Wang, Gang Chen, Longhan Xie
Summary: This paper proposes a framework based on Graph Neural Network and deep reinforcement learning to solve the dynamic job shop scheduling problem with machine breakdown and stochastic processing time. The model effectively extracts the embeddings of the state by considering the features of the dynamic events and the stochasticity of the problem. Evolution strategies are utilized to find optimal policies that are more stable and robust than conventional deep reinforcement learning algorithms. Extensive experiments demonstrate the superiority of the proposed method over existing reinforcement learning-based and traditional methods on multiple classic benchmarks.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Industrial
Junyoung Park, Jaehyeong Chun, Sang Hun Kim, Youngkook Kim, Jinkyoo Park
Summary: The proposed framework utilizes GNN and RL to learn a solution for JSSP scheduling problem, demonstrating its superiority over traditional dispatching rules and RL schedulers. The learned policy from the framework exhibits strong generalization capabilities, performing well on new JSSP instances.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2021)
Article
Automation & Control Systems
Wen Song, Xinyang Chen, Qiqiang Li, Zhiguang Cao
Summary: This article proposes a novel DRL method to learn high-quality PDRs for solving the flexible job-shop scheduling problem. The method combines operation selection and machine assignment as a composite decision and utilizes a heterogeneous graph representation to capture complex relationships.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Multidisciplinary
Jianfeng Ren, Chunming Ye, Feng Yang
Summary: This paper proposes a method to solve the flow-shop scheduling problem using reinforcement learning and neural networks, achieving satisfactory results by mapping FSP information into RL states and training NN to establish the mapping between states and actions.
ALEXANDRIA ENGINEERING JOURNAL
(2021)
Article
Engineering, Industrial
Jiang-Ping Huang, Liang Gao, Xin-Yu Li, Chun-Jiang Zhang
Summary: This paper proposes a novel Priority Dispatch Rules (PDRs) generation method based on Graph Neural Network (GNN) and Reinforcement Learning (RL) for the Distributed Job-shop Scheduling Problem (DJSP). The method can self-learn and self-evolve by interacting with the scheduling environment. A new solution representation based on disjunctive graph is designed to combine DJSP with GNN closely. Comprehensive experiments show that the proposed method performs better than other classical PDRs, metaheuristics, and RL-based methods in terms of effectiveness, generalizability, and stability.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Automation & Control Systems
Chien-Liang Liu, Tzu-Hsuan Huang
Summary: This article proposes a novel framework based on graph neural networks and deep reinforcement learning to deal with the dynamic job-shop scheduling problem. The proposed method achieves excellent results considering efficiency, effectiveness, robustness, and generalizability. It outperforms another DRL-based method in terms of generalizability and effectiveness.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zixiao Pan, Ling Wang, Jingjing Wang, Jiawen Lu
Summary: This paper proposes an optimization algorithm based on deep reinforcement learning for solving permutation flow-shop scheduling problem. By designing a new deep neural network and using reinforcement learning methods, the algorithm achieves better results than existing heuristics in similar computational time.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Zhuoran Dong, Tao Ren, Jiacheng Weng, Fang Qi, Xinyue Wang
Summary: This article proposes a learning-based approach using deep reinforcement learning (DRL) and graph isomorphism network (GIN) to solve the permutation flow shop scheduling problem (PFSP) in industrial manufacturing. By combining graph representation and job sequence information, the approach predicts the distribution of candidate jobs and uses an improved iterative greedy algorithm for local search. Experimental results show that this method can obtain better solutions than other algorithms in a short time.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Multidisciplinary
Tao Zhou, Liang Luo, Shengchen Ji, Yuanxin He
Summary: This study proposes a new method to solve the permutation flow shop scheduling problem (PFSP) using an end-to-end deep reinforcement learning approach to minimize the maximum completion time. Experimental results demonstrate the superiority of the proposed method in multiple metrics.
Article
Computer Science, Interdisciplinary Applications
Min Zhang, Liang Wang, Fusheng Qiu, Xiaorui Liu
Summary: This paper addresses the dynamic flexible job shop scheduling problem with insufficient transportation resources in smart workshop environment. It proposes a deep reinforcement learning method to learn high-quality priority dispatching rule and minimize the makespan. An architecture based on heterogeneous graph neural network and deep reinforcement learning is proposed to achieve integrated decision making for operation, machine, and AGV. Experimental results show the proposed method's superiority and good generalization ability regardless of the AGV distribution strategy used.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Management
Marta Monaci, Valerio Agasucci, Giorgio Grani
Summary: In this research, we applied deep reinforcement learning to tackle the job shop scheduling problem. The study showed that a greedy-like heuristic trained on a subset of problems could effectively generalize to unseen instances and be competitive compared to other methods. The experiments demonstrated that this algorithm was able to generate good solutions in a short time, indicating the feasibility of learning-based methodologies in generating new greedy heuristics.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Computer Science, Artificial Intelligence
Sebastian Lang, Tobias Reggelin, Johann Schmidt, Marcel Mueller, Abdulrahman Nahhas
Summary: The study investigates the application of NEAT algorithm in a two-stage hybrid flow shop scheduling environment and finds that NEAT performs well in terms of solution quality and computational efficiency.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Chemical
Zhong Yang, Li Bi, Xiaogang Jiao
Summary: Smart factories have complex and dynamic production processes, attracting the attention of scholars to study intelligent scheduling problems. The dynamic job shop scheduling problem (DJSP) aims to optimize scheduling decisions in real-time dynamic job shop environments. This paper combines graph neural network (GNN) and deep reinforcement learning (DRL) algorithms to solve DJSP, constructing an agent model from job shop state analysis graph to scheduling rules. The proposed reward method is proven to be more effective through experimental results.
Article
Engineering, Manufacturing
Shengluo Yang, Junyi Wang, Liming Xin, Zhigang Xu
Summary: In this study, we investigated the real-time and concurrent optimization of scheduling and reconfiguration for a dynamic reconfigurable flow shop using deep reinforcement learning. The objective was to minimize the total tardiness cost of all jobs by configuring flow lines and scheduling jobs. We established an intelligent scheduling and reconfiguration system and proposed a new variant of deep Q-network algorithm and an EDQN_T algorithm. Experimental results showed that our proposed algorithms outperformed popular DRL algorithms and priority dispatching rules in terms of solution quality, with a decision time of only a few milliseconds.
CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Industrial
Jun-Ho Lee, Hyun-Jung Kim
Summary: This study addresses a robotic flow shop scheduling problem using reinforcement learning (RL) to model and optimize robot task sequences. The results show that the RL approach outperforms FIFO and RS rules, with a small gap between the makespan from the proposed algorithm and a lower bound.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Management
Mumtaz Karatas
Summary: This paper presents a dynamic multi-objective mixed integer linear programming model to optimize the performance of maritime SAR missions. By defining three objectives and implementing a goal programming approach, the study shows that the proposed model and solution approach can significantly improve SAR performance and provide decision support for planners.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Operations Research & Management Science
Mumtaz Karatas, Ertan Yakici, Abdullah Dasci
Summary: This paper introduces a bi-objective location-allocation problem for UASs in a hostile environment, utilizing mixed integer nonlinear programming for modeling and the elitist non-dominated sorting genetic algorithm for solving large-scale problems. By linearization and hybrid approach, the effectiveness of the solutions has been improved.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Operations Research & Management Science
F. Tevhide Altekin, Abdullah Dasci, Mumtaz Karatas
Summary: This paper introduces three reformulations for the maximum capture location problem under multinomial logit choice, including two linear and one conic reformulation. The numerical experiments show that the conic reformulation greatly improves solution times and the size of solvable problems compared to the most successful reformulations to date.
OPTIMIZATION LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Qin Song, Yu-Jun Zheng, Wei-Guo Sheng, Jun Yang
Summary: This study proposes a tridirectional transfer learning approach that successfully predicts the morbidity of different diseases in different regions by combining univariate regression and multivariate Gaussian models, as well as mapping-based deep transfer learning. By selecting gastric cancer as the target disease, the approach achieves high prediction accuracy in both the source region and three target regions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Hardware & Architecture
Yakici Ertan, Mumtaz Karatas
Summary: This paper considers a multi-purpose two-level location problem aiming to enhance the coverage performance of heterogeneous sensor networks by determining the best location scheme of sensors in a belt-shaped boundary area. The study finds that a heuristic algorithm can generate diverse and high-quality solutions in a short computational time compared to an exact solver.
Article
Operations Research & Management Science
Levent Eriskin, Mumtaz Karatas
Summary: This study addresses the problem of shelter location and allocation under demand uncertainty, aiming to enhance the disaster preparedness level in Turkey. By utilizing a robust optimization approach, the study develops a model that considers the uncertainties in seismic parameters and urban vulnerability. The proposed formulation outperforms deterministic and stochastic counterparts, resulting in socially more acceptable and preferable solutions.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Operations Research & Management Science
Levent Eriskin, Mumtaz Karatas, Yu-Jun Zheng
Summary: This study focuses on improving the preparedness level and response effectiveness of healthcare authorities in fighting pandemics/epidemics by implementing analytical techniques. By developing multi-level planning models which consider demand uncertainty and across scenario robustness, more realistic and effective solutions can be achieved in managing healthcare resources and locations during the early stages of a pandemic/epidemic.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Operations Research & Management Science
Elif Bozkaya, Levent Eriskin, Mumtaz Karatas
Summary: The study reviews research on addressing transportation and location issues during the COVID-19 pandemic, emphasizing the importance of data analytics. It discusses the major data collection streams, highlights the significance of rapid and reliable data sharing, and provides an overview of the challenges and limitations in using data.
ANNALS OF OPERATIONS RESEARCH
(2023)
Review
Computer Science, Artificial Intelligence
Mumtaz Karatas, Levent Eriskin, Muhammet Deveci, Dragan Pamucar, Harish Garg
Summary: Industry 4.0 and Big Data play a significant role in enhancing and optimizing healthcare operations.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Engineering, Civil
Mumtaz Karatas, Levent Eriskin, Elif Bozkaya
Summary: Explored transportation and location-related decision problems during the COVID-19 pandemic and applied Operations Research tools to solve them.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Physical
Levent Eriskin, Mumtaz Karatas
Summary: Due to their sustainability and high energy efficiency, hydrogen fuel vehicles are gradually replacing gasoline internal combustion engine vehicles. This study focuses on the problem of locating and sizing hydrogen fuel storage areas for the Anatolian side of Istanbul, and formulates it as a bi-objective facility location problem considering both social and transshipment costs. A weighted goal programming framework is adopted to minimize deviations from desired goals while accounting for various rules and parameters, and a representative set of non-dominated solutions is generated for decision support. Sensitivity analysis is performed to assess the impact of district demand uncertainty on the preferred solution.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2023)
Article
Computer Science, Artificial Intelligence
Xin Chen, Hong-Fang Yan, Yu-Jun Zheng, Mumtaz Karatas
Summary: The COVID-19 pandemic has led to a high demand for medical masks, requiring efficient delivery to multiple locations. However, the complex nature of the problem, with scattered demand points and delayed information, makes it challenging. To address this, a hybrid machine learning and heuristic optimization method is proposed, utilizing deep learning to predict demand, scheduling vehicle distribution, reassigning demand points, and optimizing delivery routes. Application of this method during the peak of COVID-19 in three Chinese megacities demonstrated its superior performance compared to other methods. Lessons learned and key success factors are discussed to facilitate its application to a wider range of problems.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Editorial Material
Chemistry, Analytical
Syed Agha Hassnain Mohsan, Muhammad Asghar Khan, Mumtaz Karatas
Article
Management
Mumtaz Karatas, Levent Eriskin
Summary: This paper discusses a hierarchical location and sizing problem in a supply chain network involving joint partial coverage and unreliable facilities. The authors propose an integer non-linear program and a mixed integer linear programming formulation to determine facility number, location, and size, as well as primary and backup assignments. They also introduce two competing piece-wise linear approximations, which outperform the exact formulation in terms of computation time and solution quality.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2023)
Article
Engineering, Industrial
Ertan Yakici, Mumtaz Karatas, Serhan Duran
Summary: This study focuses on the structural optimization of pre-positioning warehouse networks for disaster response. By using a multi-objective approach and analyzing non-dominated solutions, it recommends CARE International to open a warehouse in Kenya and pre-position a certain percentage of relief items to this location while operating the Denmark warehouse instead of the Dubai warehouse.
EUROPEAN JOURNAL OF INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jin Zhang, Zekang Bian, Shitong Wang
Summary: This study proposes a novel style linear k-nearest neighbor method to extract stylistic features using matrix expressions and improve the generalizability of the predictor through style membership vectors.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Qifeng Wan, Xuanhua Xu, Jing Han
Summary: In this study, we propose an innovative approach for dimensionality reduction in large-scale group decision-making scenarios that targets linguistic preferences. The method combines TF-IDF feature similarity and information loss entropy to address challenges in decision-making with a large number of decision makers.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Hegui Zhu, Yuchen Ren, Chong Liu, Xiaoyan Sui, Libo Zhang
Summary: This paper proposes an adversarial attack method based on frequency information, which optimizes the imperceptibility and transferability of adversarial examples in white-box and black-box scenarios respectively. Experimental results validate the superiority of the proposed method and its application in real-world online model evaluation reveals their vulnerability.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Jing Tang, Xinwang Liu, Weizhong Wang
Summary: This paper proposes a hybrid generalized TODIM approach in the Fine-Kinney framework to evaluate occupational health and safety hazards. The approach integrates CRP, dynamic SIN, and PLTSs to handle opinion interactions and incomplete opinions among decision makers. The efficiency and rationality of the proposed approach are demonstrated through a numerical example, comparison, and sensitivity studies.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Shigen Shen, Chenpeng Cai, Zhenwei Li, Yizhou Shen, Guowen Wu, Shui Yu
Summary: To address the damage caused by zero-day attacks on SIoT systems, researchers propose a heuristic learning intrusion detection system named DQN-HIDS. By integrating Deep Q-Networks (DQN) into the system, DQN-HIDS gradually improves its ability to identify malicious traffic and reduces resource workloads. Experiments demonstrate the superior performance of DQN-HIDS in terms of workload, delayed sample queue, rewards, and classifier accuracy.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Song Deng, Qianliang Li, Renjie Dai, Siming Wei, Di Wu, Yi He, Xindong Wu
Summary: In this paper, we propose a Chinese text classification algorithm based on deep active learning for the power system, which addresses the challenge of specialized text classification. By applying a hierarchical confidence strategy, our model achieves higher classification accuracy with fewer labeled training data.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Kaan Deveci, Onder Guler
Summary: This study proves the lack of robustness in nonlinear IF distance functions for ranking intuitionistic fuzzy sets (IFS) and proposes an alternative ranking method based on hypervolume metric. Additionally, the suggested method is extended as a new multi-criteria decision making method called HEART, which is applied to evaluate Turkey's energy alternatives.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Fu-Wing Yu, Wai-Tung Ho, Chak-Fung Jeff Wong
Summary: This research aims to enhance the energy management in commercial building air-conditioning systems, specifically focusing on chillers. Ridge regression is found to outperform lasso and elastic net regression when optimized with the appropriate hyperparameter, making it the most suitable method for modeling the system coefficient of performance (SCOP). The key variables that strongly influence SCOP include part load ratios, the operating numbers of chillers and pumps, and the temperatures of chilled water and condenser water. Additionally, July is identified as the month with the highest potential for performance improvement. This study introduces a novel approach that balances feature selection, model accuracy, and optimal tuning of hyperparameters, highlighting the significance of a generic and simplified chiller system model in evaluating energy management opportunities for sustainable operation. The findings from this research can guide future efforts towards more energy-efficient and sustainable operations in commercial buildings.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Xiaoyan Chen, Yilin Sun, Qiuju Zhang, Xuesong Dai, Shen Tian, Yongxin Guo
Summary: In this study, a method for dynamically non-destructive grasping of thin-skinned fruits is proposed. It utilizes a multi-modal depth fusion convolutional neural network for image processing and segmentation, and combines the evaluation mechanism of optimal grasping stability and the forward-looking non-destructive grasp control algorithm. The proposed method greatly improves the comprehensive performance of grasping delicate fruits using flexible hands.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Yuxuan Yang, Siyuan Zhou, He Weng, Dongjing Wang, Xin Zhang, Dongjin Yu, Shuiguang Deng
Summary: The study proposes a novel model, POIGDE, which addresses the challenges of data sparsity and elusive motives by solving graph differential equations to capture continuous variation of users' interests. The model learns interest transference dynamics using a time-serial graph and an interval-aware attention mechanism, and applies Siamese learning to directly learn from label representations for predicting future POI visits. The model outperforms state-of-the-art models on real-world datasets, showing potential in the POI recommendation domain.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
S. Karthika, P. Rathika
Summary: The widespread development of monitoring devices in the power system has generated a large amount of power consumption data. Storing and transmitting this data has become a significant challenge. This paper proposes an adaptive data compression algorithm based on the discrete wavelet transform (DWT) for power system applications. It utilizes multi-objective particle swarm optimization (MO-PSO) to select the optimal threshold. The algorithm has been tested and outperforms other existing algorithms.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Jiaqi Guo, Haiyan Wu, Xiaolei Chen, Weiguo Lin
Summary: In this study, an adaptive SV-Borderline SMOTE-SVM algorithm is proposed to address the challenge of imbalanced data classification. The algorithm maps the data into kernel space using SVM and identifies support vectors, then generates new samples based on the neighbors of these support vectors. Extensive experiments show that this method is more effective than other approaches in imbalanced data classification.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Qiumei Zheng, Linkang Xu, Fenghua Wang, Yongqi Xu, Chao Lin, Guoqiang Zhang
Summary: This paper proposes a new semantic segmentation network model called HilbertSCNet, which combines the Hilbert curve traversal and the dual pathway idea to design a new spatial computation module to address the problem of loss of information for small targets in high-resolution images. The experiments show that the proposed network performs well in the segmentation of small targets in high-resolution maps such as drone aerial photography.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Mojtaba Ashour, Amir Mahdiyar
Summary: Analytic Hierarchy Process (AHP) is a widely applied technique in multi-criteria decision-making problems, but the sheer number of AHP methods presents challenges for scholars and practitioners in selecting the most suitable method. This paper reviews articles published between 2010 and 2023 proposing hybrid, improved, or modified AHP methods, classifies them based on their contributions, and provides a comprehensive summary table and roadmap to guide the method selection process.
APPLIED SOFT COMPUTING
(2024)
Review
Computer Science, Artificial Intelligence
Gerardo Humberto Valencia-Rivera, Maria Torcoroma Benavides-Robles, Alonso Vela Morales, Ivan Amaya, Jorge M. Cruz-Duarte, Jose Carlos Ortiz-Bayliss, Juan Gabriel Avina-Cervantes
Summary: Electric power system applications are complex optimization problems. Most literature reviews focus on studying electrical paradigms using different optimization techniques, but there is a lack of review on Metaheuristics (MHs) in these applications. Our work provides an overview of the paradigms underlying such applications and analyzes the most commonly used MHs and their search operators. We also discover a strong synergy between the Renewable Energies paradigm and other paradigms, and a significant interest in Load-Forecasting optimization problems. Based on our findings, we provide helpful recommendations for current challenges and potential research paths to support further development in this field.
APPLIED SOFT COMPUTING
(2024)