Article
Computer Science, Interdisciplinary Applications
Janis Brammer, Bernhard Lutz, Dirk Neumann
Summary: This study introduces a reinforcement learning approach to minimize work overload situations in the mixed model sequencing problem. By generating sequences in a constructive way and using metaheuristics, the trained policy can quickly create an initial sequence to improve solution quality. Numerical evaluation on benchmark datasets shows superior performance to established methods when demand plan distribution aligns with learning process expectations.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Mathematics
Zhengwen Liao, Ce Mu
Summary: This paper evaluates the capacity of railway station layouts using optimization modeling and planning algorithms. The study finds that determining an adaptable layout according to the complex traffic pattern is necessary during the station's design phase. Based on the results of a case study, the paper proposes design recommendations for station capacity.
Article
Computer Science, Interdisciplinary Applications
Shuang Zheng, Zhengwen He, Zhen Yang, Chengbin Chu, Nengmin Wang
Summary: This paper studies a realistic two-stage reentrant flexible flow shop scheduling problem (TSRFFS) with broad applications in aircraft scheduling, manufacturing, and the medical industry, etc. A mixed integer programming mathematical model and a greedy random constructive heuristic for near optimal solutions are proposed. Extensive numerical experiments demonstrate the effectiveness of the proposed algorithms.
COMPUTERS & OPERATIONS RESEARCH
(2023)
Article
Chemistry, Multidisciplinary
Soukaina Oujana, Lionel Amodeo, Farouk Yalaoui, David Brodart
Summary: This paper discusses a research project that aims to optimize the scheduling of production orders in the packaging field. The problem is modeled as an extended version of the hybrid and flexible flowshop scheduling problem with precedence constraints, parallel machines, and sequence-dependent setups. Two methodologies, mixed-integer linear programming (MILP) and constraint programming (CP), are used to tackle the problem. Resource calendar constraints are added to the models, and a novel heuristic is designed for quick solutions. The proposed problem can be easily modified to suit real-world situations involving similar scheduling characteristics.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Wisute Ongcunaruk, Pornthipa Ongkunaruk, Gerrit K. Janssens
Summary: This study aims to improve transportation planning decisions for a production company in Thailand through a mixed integer programming model and a genetic algorithm, resulting in reduced costs and increased efficiency.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Mathematics
Fabian Riquelme, Elizabeth Montero, Leslie Perez-Caceres, Nicolas Rojas-Morales
Summary: This work focuses on generating conference programs that organize talks into different tracks, with main contributions in literature review, problem formulation and benchmarking, and heuristic approach. A new track-based conference scheduling problem formulation is introduced, with a proposed heuristic method for solving it efficiently.
Article
Computer Science, Information Systems
Yarong Chen, Zailin Guan, Ya-Chih Tsai, Fuh-Der Chou
Summary: The research addresses the single-machine scheduling problem with a weight-modifying-activity (WMA) and proposes two mathematical models and a heuristic algorithm for optimization. The results show that the proposed method efficiently solves problems with up to 40 jobs and the heuristic algorithm has a high accuracy and hit rate. The study also analyzes the influence of parameters on the method's performance.
Article
Mathematics
Teeradech Laisupannawong, Boonyarit Intiyot, Chawalit Jeenanunta
Summary: This paper discusses the scheduling of the pressing process in PCB manufacturing, presenting a novel MILP optimization model and a heuristic algorithm. Experimental results show that the MILP model can find optimal schedules for small- to medium-sized problems within 2 hours, while the 3P-PCB-PH can find optimal schedules in a shorter computational time.
Article
Operations Research & Management Science
Mohamadreza Dabiri, Mehdi Yazdani, Bahman Naderi, Hassan Haleh
Summary: This paper tackles the hybrid flow shop scheduling problem by minimizing the total tardiness cost and rejected job cost through job rejection as a single-objective problem. It presents a mixed-integer linear programming model and innovative heuristic algorithms along with meta-heuristics for solving large-sized problems effectively. Different encoding and decoding methods are adapted to algorithms to ensure efficiency of the solutions based on schedules. Results demonstrate the effectiveness of the mathematical model and proposed algorithms in scheduling the production system of a real-world hybrid flow shop in the tile industry. Additionally, the study explores the efficacy of job rejection and compares single-objective and bi-objective approaches on small and large-sized problems.
OPERATIONAL RESEARCH
(2022)
Article
Health Care Sciences & Services
Pi-Yu Hsu, Shao-Hua Lo, Hsin-Gin Hwang, Bertrand M. T. Lin
Summary: This paper investigates the scheduling of surgical operations in multiple operating rooms with limited availability of anaesthetists. By proposing an integer programming model and developing two approximation methods, the research aims to minimize the makespan of all operations. The computational study shows that the proposed methods can generate quality solutions in just a few seconds.
Article
Computer Science, Information Systems
Qin-zhe Xiao, Jinghui Zhong, Liang Feng, Linbo Luo, Jianming Lv
Summary: This paper proposes a cooperative coevolution hyper-heuristic framework to solve the workflow scheduling problem, aiming to minimize the completion time of the workflow. The framework automatically learns the task selection rule and resource selection rule using a cooperative coevolution genetic programming algorithm. A set of low-level heuristics is defined to improve the search efficiency. Experimental results demonstrate the superior performance of the proposed framework on multiple metrics.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Vicky Mak-Hau, Brendan Hill, David Kirszenblat, Bill Moran, Vivian Nguyen, Ana Novak
Summary: This paper addresses a unique combinatorial optimization problem derived from helicopter aircrew training for the Royal Australian Navy. The main objective is to find optimal course scheduling solutions and minimize the total time required to complete the syllabus.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Economics
Matias Alvo, Gustavo Angulo, Mathias A. Klapp
Summary: The study focuses on efficiently planning a bus dispatch operation within a public transport terminal with a mixed fleet and limited chargers, modeling the problem as an extension of the Vehicle Scheduling Problem and using a Benders' type decomposition approach to solve it. Feasibility cuts dynamically injected into the branch-and-bound tree help remove infeasible bus charging operations, with computational experiments showing the effectiveness of the approach over a single-stage model. Insights for planners include the marginal benefit of additional chargers or electric buses and the value added by a mixed fleet compared to a pure electric one.
TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW
(2021)
Article
Mathematics
Yong-Jae Kim, Byung-Soo Kim
Summary: This paper addresses an integrated scheduling problem of batch manufacturing and delivery processes, aiming to minimize the total tardiness of jobs delivered to customers by dynamically adjusting and optimizing production and delivery batches. Sensitivity analyses are conducted on the effect of problem parameters on manufacturing and delivery time.
Article
Chemistry, Multidisciplinary
Che Han Lim, Seung Ki Moon
Summary: In this article, a two-phase iterative mathematical programming-based heuristic is proposed to minimize makespan in a flexible job shop problem with transportation (FJSPT). The proposed approach considers job pre-emption and outperforms certain established benchmarks, confirming the importance of considering job pre-emption.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Shuai Chen, Quan-Ke Pan, Liang Gao, Zhong-Hua Miao, Chen Peng
Summary: This paper studies an energy-efficient distributed blocking flowshop scheduling problem and proposes a knowledge-based iterated Pareto greedy algorithm (KBIPG) to simultaneously minimize the makespan and total energy consumption. By adjusting machine speeds and designing local intensification methods, the effectiveness of the algorithm is demonstrated.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Rahul Sharma, Tripti Goel, M. Tanveer, P. N. Suganthan, Imran Razzak, R. Murugan
Summary: As per the latest statistics, Alzheimer's disease has become a global burden. This paper proposes a novel fusion approach using MRI and PET scans for identifying Alzheimer's disease at an early stage. The approach utilizes a trained CNN and RVFL models to extract features and make the final decision. Experimental results prove the effectiveness of the fusion-based ensemble approach.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Xuan He, Quan-Ke Pan, Liang Gao, Ling Wang, Ponnuthurai Nagaratnam Suganthan
Summary: This article addresses the flowshop sequence-dependent group scheduling problem (FSDGSP) by considering both production efficiency measures and energy efficiency indicators. A mixed-integer linear programming model and a critical path-based accelerated evaluation method are proposed. A greedy cooperative co-evolutionary algorithm (GCCEA) is designed to explore the solution space, and a random mutation operator and a greedy energy-saving strategy are employed.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Automation & Control Systems
Zhongkai Li, Hongyan Sang, Quanke Pan, Kaizhou Gao, Yuyan Han, Junqing Li
Summary: In this article, a dynamic AGV scheduling model is proposed, which includes an aperiodic departure method and a real-time task list update method. The model can reassign AGVs for new tasks and special cases, proving its effectiveness through verification using a discrete invasive weed optimization algorithm.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Parul Arora, Seyed Mohammad Jafar Jalali, Sajad Ahmadian, B. K. Panigrahi, P. N. Suganthan, Abbas Khosravi
Summary: Wind power forecasting is crucial for power system planning and scheduling. Optimizing the hyperparameters of deep neural networks (DNNs) using evolutionary algorithms is an effective approach. In this article, a novel evolutionary algorithm based on the grasshopper optimization algorithm is proposed to optimize the hyperparameters of a wind power forecasting model. The proposed model outperforms benchmark DNNs and other neuroevolutionary models in terms of learning speed and prediction accuracy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Civil
Jianhui Mou, Peiyong Duan, Liang Gao, Quanke Pan, Kaizhou Gao, Amit Kumar Singh
Summary: This study explores the application of biologically inspired Plasticity Neural Network in the industrial intelligent dispatching energy storage system, focusing on the intelligence and fault detection performance of the control system. By implementing a fault diagnosis model based on Deep Belief Network, the study achieves a 100% transmission probability for the constructed intelligent energy storage scheduling system. Compared with other classical algorithm models, the proposed algorithm shows a higher success rate, detection accuracy, lower energy consumption, and more significant detection effect. Therefore, the constructed system has higher real-time performance, more accurate fault detection performance, and significantly better system detection and protection performance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ruilin Li, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan
Summary: In this study, a novel decomposition-based hybrid ensemble convolutional neural network (CNN) framework is proposed to enhance the capability of decoding EEG signals. Four decomposition methods are employed to disassemble the EEG signals into components of different complexity. The CNNs in this framework directly learn from the decomposed components, and a component-specific batch normalization layer is employed to reduce subject variability. The models under the framework showed better performance than the strong baselines in the challenging cross-subject driver fatigue recognition task.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Heba Abdel-Nabi, Mostafa Z. Ali, Arafat Awajan, Rami Alazrai, Mohammad I. Daoud, Ponnuthurai N. Suganthan
Summary: This paper proposes a novel evolutionary algorithm, Ic3-aDSF-EA, which combines the exploitative and explorative merits of two main evolutionary algorithms, Stochastic Fractal Search (SFS) and a Differential Evolution (DE) variant. The algorithm gradually emphasizes the work of the best-performing algorithm during the search process without ignoring the effects of other inferior algorithms.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Jinlong Zhou, Yinggui Zhang, P. N. Suganthan
Summary: This paper proposes a novel dual population algorithm to approximate the constrained Pareto front (CPF) from both sides of the constraint boundaries. The algorithm uses the constrained-domination principle and an improved c-constrained method to approximate the feasible and infeasible regions respectively. Experimental results show that the algorithm achieves superior performance, especially for CMOPs with CPF located at constraint boundaries.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Lingping Kong, Varun Ojha, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan, Vaclav Snasel
Summary: This study proposes a Global Representation (GR) based attention mechanism to alleviate the heterophily and over-smoothing issues. The model integrates geometric information and uses GR to construct the Key, discovering the relation between nodes and the structural representation of the graph. Experimental tests validate the performance of the proposed method and provide insights for future improvements.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Xin-Rui Tao, Quan-Ke Pan, Hong-Yan Sang, Liang Gao, Ao-Lei Yang, Miao Rong
Summary: This study develops a nondominated sorting genetic algorithm-II (NSGA-II) with Q-learning to address the disturbance factors in the distributed permutation flowshop problem. An iterated greedy algorithm (IG) is proposed to generate an initial solution, and the NSGA-II algorithm is designed to optimize dual-objective problems. The results confirm the high efficiency of the proposed algorithm in solving the rescheduling problem in the distributed permutation flowshop.
KNOWLEDGE-BASED SYSTEMS
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Rui Wang, Lining Xing, Maoguo Gong, Ponnuthurai Nagaratnam Suganthan, Hisao Ishibuchi
Summary: Optimization is an important research topic in engineering and various methods, including evolutionary algorithms, have been proposed. Evolutionary algorithms have gained attention for their robustness, but their iterative nature results in high computational effort, making them unsuitable for online or real-time optimization.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yu Du, Jun-qing Li, Xiao-long Chen, Pei-yong Duan, Quan-ke Pan
Summary: This study introduces a hybrid multi-objective optimization algorithm to solve a flexible job shop scheduling problem with time-of-use electricity price constraint, involving machine processing speed, setup time, idle time, and the transportation time between machines. The algorithm combines estimation of distribution algorithm and deep Q-network, with two knowledge-based initialization strategies designed for better performance.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Minghui Hu, Ruobin Gao, Ponnuthurai Nagaratnam Suganthan
Summary: Knowledge distillation is a common method in deep learning that improves the performance of a student model by transferring dark knowledge from a teacher model. However, in randomized neural networks, KD does not work well due to the simple network architecture and the weak relationship between model performance and size. In this work, we propose a self-distillation pipeline for randomized neural networks that utilizes the network's own predictions as an additional target, combined with the original target containing dark knowledge, to supervise the training of the model. We demonstrate the effectiveness of our method on several benchmark datasets and provide theoretical analysis on self-distillation for randomized neural networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)