Article
Engineering, Multidisciplinary
Alireza Eydi, Seyed Ali Ghasemi-Nezhad
Summary: This study proposed a new mathematical model through multi-objective optimization approach, making the logistic problems involving occasional goods in the real world more efficient. The research covers time windows, multiple demands, and two conflicting objectives, and proposes two metaheuristic algorithms.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Article
Green & Sustainable Science & Technology
Seyed Zeinab Aliahmadi, Farnaz Barzinpour, Mir Saman Pishvaee
Summary: In this study, a bi-objective vehicle routing mathematical model was proposed and solved using Non-dominated Sorting Genetic Algorithm II, which achieved significant optimization results in terms of total economic cost and total time for waste collection.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Green & Sustainable Science & Technology
Seyed Omid Hasanpour Jesri, Mohsen Akbarpour Shirazi
Summary: This paper proposes an integer bi-objective optimization model that integrates vehicle assignment, vehicle routing, and passenger assignment to find a non-dominated solution based on cost and time. The model allows passengers to use the same vehicle multiple times, achieving cost and travel time savings. A real case study validates the applicability of the proposed model, showing that ridesharing can help passengers save money without significant increases in travel time.
Article
Green & Sustainable Science & Technology
Huo Chai, Ruichun He, Ronggui Kang, Xiaoyan Jia, Cunjie Dai
Summary: In this study, a transport risk evaluation method considering driving risk was proposed. A model of vehicle routing problems considering a soft time window for the transportation of hazardous materials was established, and a non-dominated genetic algorithm was designed to solve the bi-objective optimization model. Using a network example of 23 nodes and 38 road segments, 59 pareto-optimal solutions were obtained for six drivers on nine different paths. Comparing different solutions, it was found that driving risk, road population density, and transportation distance have different impacts on transport cost and risk. Choosing drivers and routes can adjust the propensity of cost and risk, allowing decision-makers to select a solution for allocating drivers and routing vehicles according to their risk preference.
Article
Computer Science, Interdisciplinary Applications
Wei Qin, Zilong Zhuang, Zizhao Huang, Haozhe Huang
Summary: This study uses a mixed-integer linear programming (MILP) model to obtain optimal solutions for small-scale problems and develops a reinforcement learning-based hyper-heuristic to improve solution quality for large-scale problems. The proposed algorithm outperforms existing meta-heuristic algorithms on large-scale problems.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Diego Rocha, Daniel Aloise, Dario J. Aloise, Claudio Contardo
Summary: This paper proposes a bi-objective capacitated vehicle routing problem that aims to design a cost-effective and visually attractive distribution system. The model is solved using a multi-objective evolutionary algorithm, and computational experiments demonstrate its ability to find vehicle routing solutions with low costs and strong visual appeal.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Article
Management
Cheng Chen, Emrah Demir, Yuan Huang
Summary: This paper investigates the routing and scheduling of autonomous delivery robots in urban logistics, proposing an algorithm to solve the VRPTWDR and demonstrating its performance and effectiveness. The research shows that self-driving parcel delivery robots can be a new alternative for last mile service.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Cybernetics
Xiao-Cheng Liao, Ya-Hui Jia, Xiao-Min Hu, Wei-Neng Chen
Summary: The traffic assignment problem is important for the development of smart cities and society. However, in reality, traffic demand, especially foot traffic assignment in buildings, is often unpredictable. This study focuses on the dynamic version of the problem, proposing a genetic programming hyper-heuristic method to assign uncertain commuters in real-time. Through training and evolution, all commuters are able to find their optimal paths to maximize traffic network throughput.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Construction & Building Technology
Nilotpal Chakraborty, Arijit Mondal, Samrat Mondal
Summary: This paper addresses the problem of charge scheduling and route management for electric vehicles, proposing an intelligent heuristic mechanism and formulating it as a multi-objective optimization problem, with a graph-based algorithm to quickly obtain solutions. The results show that the energy-aware-MoHA variant performs better in minimizing energy consumption compared to the time-aware-MoHA.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Interdisciplinary Applications
Christian Fikar, Kris Braekers
Summary: Motivated by urban e-grocery deliveries, this study introduces a vehicle routing procedure to reduce food waste. By considering the trade-offs between travel distances and food quality losses, it highlights the importance of considering these aspects in related delivery operations to facilitate food waste reduction.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
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
Engineering, Civil
Nayera Elgharably, Said Easa, Ashraf Nassef, Ashraf El Damatty
Summary: This paper studies the stochastic multi-objective Vehicle Routing Problem in a green environment, introduces a hybrid search algorithm, and considers economic, environmental, and social aspects.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Qidong Lai, Zizhen Zhang, Mingzhu Yu, Jiahai Wang
Summary: Motivated by practical applications in urban services, this study focuses on the split-delivery capacitated arc-routing problem with time windows (SDCARPTW). A mathematical formulation for SDCARPTW is proposed, and the effectiveness and efficiency of the algorithm are validated through computational studies.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Lixin Cheng, Qiuhua Tang, Liping Zhang, Zikai Zhang
Summary: This study addresses the scheduling problem in mixed shop production systems and proposes an optimization method using speed-scaling policy and no-idle time strategy. By formulating a mathematical model and developing a Q-learning algorithm, simultaneous optimization of production efficiency and energy consumption is achieved.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Feng Wang, Fanshu Liao, Yixuan Li, Xuesong Yan, Xu Chen
Summary: This paper proposes a new algorithm EL-DMOEA for solving the Dynamic Vehicle Routing Problem with Time Window, using ensemble learning method to improve algorithm performance. Multiple strategies are employed during training process to enhance population diversity and accelerate convergence, with experimental results showing promising routing plans can be effectively developed by the proposed algorithm.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Engineering, Industrial
Bing Chen, Ruibin Bai, Jiawei Li, Yueni Liu, Ning Xue, Jianfeng Ren
Summary: This paper discusses the current situation and limitations of current methods for addressing uncertainties in real-life optimization problems. The authors propose a novel framework that combines mathematical models and machine learning modules to overcome these limitations and demonstrate its practicality and feasibility through real-life and artificial bus scheduling instances. The proposed framework represents the first multi-objective bus-headway-optimisation method for non-timetabled bus schedules with major practical constraints being considered.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Management
Yuchang Zhang, Ruibin Bai, Rong Qu, Chaofan Tu, Jiahuan Jin
Summary: This paper presents the advancements in computational intelligence and operations research and identifies the limitations of current optimization methods in dealing with uncertainties. To address this research gap, a deep reinforcement learning based hyper-heuristic framework is proposed. Experimental results demonstrate the superior performance of this framework in solving real-world optimization problems.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Management
Xiaoping Jiang, Ruibin Bai, Jianfeng Ren, Jiawei Li, Graham Kendall
Summary: This paper uses the Lagrange dual problem to compute lower bounds for stochastic service network design, showing the superiority of the resulting optimal Lagrange dual bound. By employing an improved algorithm, the computing efficiency is enhanced, as demonstrated in computational experiments.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Engineering, Industrial
Ruibin Bai, Xinan Chen, Zhi-Long Chen, Tianxiang Cui, Shuhui Gong, Wentao He, Xiaoping Jiang, Huan Jin, Jiahuan Jin, Graham Kendall, Jiawei Li, Zheng Lu, Jianfeng Ren, Paul Weng, Ning Xue, Huayan Zhang
Summary: This paper provides a comprehensive review of hybrid methods that combine machine learning techniques with analytical approaches to address the Vehicle Routing Problem (VRP). The review highlights the potential benefits of using machine learning in enhancing VRP modeling and improving the performance of VRP optimization algorithms, both in online and offline scenarios.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Multidisciplinary Sciences
Bingchen Lin, Jiawei Li, Ruibin Bai, Rong Qu, Tianxiang Cui, Huan Jin
Summary: This article introduces a solution to the online bin packing problem - pattern-based adaptive heuristics, which improves the efficiency of packing by predicting the distribution of items and incorporating their characteristics.
Article
Computer Science, Artificial Intelligence
Jiandong Liu, Jianfeng Ren, Zheng Lu, Wentao He, Menglin Cui, Zibo Zhang, Ruibin Bai
Summary: This paper proposes a Co-Attention-based Multi-document Inference (CAMI) framework for better reasoning over multiple documents. The model utilizes both cross-document information and attentional information to enhance automatic reasoning.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Editorial Material
Engineering, Industrial
Ruibin Bai, Zhi-Long Chen, Graham Kendall
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Computer Science, Information Systems
Treerak Kongthanasuwan, Nakarin Sriwiboon, Banpot Horbanluekit, Wasakorn Laesanklang, Tipaluck Krityakierne
Summary: The purpose of this research is to develop a Business Intelligence system for a brake pad manufacturing company in Thailand, by analyzing the relationship between market demand and supply components of the company through regression analysis and the principles of the marketing mix, a product lifecycle curve is developed to forecast product sales. The developed system increases workflow efficiency, simplifies traditional data preparation process, and an intelligence dashboard is created to support decision-making, facilitate communication, and improve team efficiency and productivity.
Article
Computer Science, Artificial Intelligence
Shihe Wang, Jianfeng Ren, Ruibin Bai
Summary: Recently, improved naive Bayes methods, including regularized naive Bayes (RNB), have been developed to enhance discrimination capabilities. However, these methods often result in significant information loss due to inadequate data discretization. To address this issue, we propose a semi-supervised adaptive discriminative discretization framework that utilizes both labeled and unlabeled data to better estimate the data distribution. Our proposed method, called RNB+, shows superior performance compared to state-of-the-art NB classifiers by significantly reducing information loss and improving discrimination power.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Chenglin Yao, Jianfeng Ren, Ruibin Bai, Heshan Du, Jiang Liu, Xudong Jiang
Summary: Detecting 3D mask attacks to a face recognition system is challenging due to unstable face alignment and weak rPPG signals. To address these issues, a landmark-anchored face stitching method and a weighted spatial-temporal representation of rPPG signals are proposed. A lightweight EfficientNet with a GRU is designed to extract features for classification. The proposed method outperforms other state-of-the-art rPPG-based methods for face spoofing detection.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Shihe Wang, Jianfeng Ren, Xiaoyu Lian, Ruibin Bai, Xudong Jiang
Summary: In this paper, a feature augmentation method using a stack auto-encoder is proposed to enhance the performance of naive Bayes by reducing noise in the data and boosting the discriminant power of features. Experimental results show that the proposed method consistently outperforms state-of-the-art naive Bayes classifiers.
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Xinyang Du, Ruibin Bai, Tianxiang Cui, Rong Qu, Jiawei Li
Summary: The competitive traveling salesmen problem is a complex decision-making issue that lacks effective algorithms. This research explores an enhanced ant colony approach with a time dominance mechanism and revised pheromone depositing method to improve solution quality with reduced computational complexity. Simulation results demonstrate that the proposed algorithm surpasses current state-of-the-art algorithms.
2022 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)
(2022)
Article
Engineering, Aerospace
Ning Zhou, Lawrence Lau, Ruibin Bai, Terry Moore
Summary: This paper proposes a robust particle-filter-based indoor positioning algorithm to mitigate the effects of delayed range measurements and improve positioning accuracy. The algorithm includes an outlier detection method for delayed measurement identification and a constrained particle sampling method to optimize the distribution of predicted particles.
NAVIGATION-JOURNAL OF THE INSTITUTE OF NAVIGATION
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Chenglin Yao, Shihe Wang, Jialu Zhang, Wentao He, Heshan Du, Jianfeng Ren, Ruibin Bai, Jiang Liu
Summary: This paper proposes an rPPG-based face-spoofing detection method, utilizing multiple regions of interests with emphasis on regions containing richer rPPG signals to form a weighted spatial-temporal map, addressing the issue of rPPG signal distortion caused by background noise or object motion.
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiawei Li, Can Zhou, Kejia Wu, Ruibin Bai
Summary: This paper investigates the issue of uncertain weight information of outbound containers and proposes a fuzzy logic-based heuristic algorithm to minimize re-handling operations. By tuning the algorithm parameters online to handle weight uncertainty, the computational complexity is reduced. The proposed algorithm is independent from re-handling algorithms, making it suitable for real-world applications.
2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021)
(2021)