{"title":"Data-driven vehicle rental and routing optimization: An application in online retailing","authors":"Jie Wei, Xianhao Xu, Bingnan Yang","doi":"10.1016/j.cie.2024.110588","DOIUrl":"10.1016/j.cie.2024.110588","url":null,"abstract":"<div><div>Due to limited self-owned vehicles, online retailers often struggle to meet high demands for deliveries, especially during large promotions. This study employs machine learning to tackle this challenge by shipping products and renting vehicles in advance. We explore a large amount of historical demand data, enabling accurate forecasting of demand information. It is then combined with an improved meta-heuristic algorithm named the Improved Discrete Whale Optimization Algorithm (IDWOA) to help online retailers make optimal decisions. The algorithm involves a discretization method and an effective perturbation strategy, along with information sharing, Cauchy mutation, and an elimination strategy. Experimental results demonstrate that our method can reduce costs by 14.78% compared to temporary vehicle rentals, and it significantly outperforms other comparative algorithms. Therefore, our study effectively integrates machine learning algorithms with an improved meta-heuristic approach, allowing for increased utilization of data-driven advantages to enhance the precision and efficiency of vehicle rental and routing optimization.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110588"},"PeriodicalIF":6.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Traveling salesman problem with time windows and a drone-utilizing intermediate points (TSPTWD-IP)","authors":"Bo Lan , Yoshinori Suzuki","doi":"10.1016/j.cie.2024.110641","DOIUrl":"10.1016/j.cie.2024.110641","url":null,"abstract":"<div><div>The fast growing of e-commerce has raised challenges to the last-mile logistics. Our study focuses on an emerging mode of transportation, i.e., a collaboration of a truck and an autonomous drone to deliver parcels. We develop a novel model of traveling salesman problem with time windows that jointly utilizes a truck and a drone in a coordinated manner. This model allows operating a drone not only on customers’ sites but also on other discrete intermediate points on arcs, and incorporates characteristics not considered previously, such as drone inoperable areas. We formulate this problem as a mixed integer linear program. We also develop a metaheuristic method that can solve the problems with up to 100 customers. Numerical experiments showed that our metaheuristic can find good solutions for many instances. Our model can cut the total delivery time by as much as 26% when compared to the traditional delivery model with only a single truck, and by 4% when compared to the existing model of a truck-and-drone operations that allows a drone to be launched or received at customers’ sites only.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"198 ","pages":"Article 110641"},"PeriodicalIF":6.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fan Zhang , Tianyu Zhu , Xinli Shi , Jinde Cao , Mahmoud Abdel-Aty
{"title":"Neural relational and dynamics inference for complex systems","authors":"Fan Zhang , Tianyu Zhu , Xinli Shi , Jinde Cao , Mahmoud Abdel-Aty","doi":"10.1016/j.cie.2024.110628","DOIUrl":"10.1016/j.cie.2024.110628","url":null,"abstract":"<div><div>Many complex processes in the real world can be viewed as complex systems and their evolution is governed by underlying nonlinear dynamics. However, one can only access the trajectories of the system without knowing the underlying system structure and dynamics in most cases. To address this challenge, this paper proposes a model called Neural Relational and Dynamics Inference (NRDI) that combines graph neural networks (GNNs) and ordinary differential equation systems (ODEs) to handle both continuous-time dynamics prediction and network topology inference for complex systems. Our model contains two modules: (1) the network inference module, which infers system structure from input system trajectories using GNNs, and (2) the dynamics learning module, which employs GNNs to fit the differential equation system for predicting future trajectories. We tested NRDI’s performance on system trajectory prediction and graph reconstruction separately. Experimental results show that the proposed NRDI outperforms many baseline models on continuous-time complex network dynamics prediction, and can explicitly infer network structures with high accuracy.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110628"},"PeriodicalIF":6.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An integrated distributionally robust model for two-echelon patient appointment scheduling","authors":"Cong Cheng, Ruixue Shan, Xiaodan Wu, Shanshan Lv","doi":"10.1016/j.cie.2024.110593","DOIUrl":"10.1016/j.cie.2024.110593","url":null,"abstract":"<div><div>We develop a distributionally robust optimization (DRO) model for the outpatient appointment scheduling problem of a set of patients served in two serial stages, consultation and examination. The arrival sequence of patients is known, and the problem of scheduling is to assign appointment time for each patient to minimize total cost with random service time for two serial stages. A max–min problem is formulated for the two-stage appointment scheduling as a whole, in which the waiting time exhibits a high degree of coupling due to the continuous two-stage process. To address this, we devise a two-stage network maximum flow model that provides an equivalent linear expression for the waiting time. For the inner maximum problem, we employ a conic programming approach for equivalent representation, incorporate the scheduling decision of the outer minimum problem, and convert the model to its equivalent copositive programming by taking the conic duality. We conduct numerical experiments and sensitivity analysis using real and simulated data, and the results verify the effectiveness of our proposed DRO model.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"198 ","pages":"Article 110593"},"PeriodicalIF":6.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhancing group decision-making: Maximum consensus aggregation for fuzzy cross-efficiency under hesitant fuzzy linguistic information","authors":"Hui-Hui Song , Ying-Ming Wang , Luis Martínez","doi":"10.1016/j.cie.2024.110622","DOIUrl":"10.1016/j.cie.2024.110622","url":null,"abstract":"<div><div>Group decision-making (GDM) is essential as it recognizes the inherent complexity of many decision scenarios, which frequently require the collective wisdom and knowledge of multiple decision-makers (DMs) to be effectively resolved. The proposed method aims to develop fuzzy data envelopment analysis (DEA) cross-efficiency models tailored to address GDM challenges, wherein attribute values are provided by DMs using hesitant fuzzy linguistic term sets (HFLTSs). For this purpose, we initially transform HFLTSs into their corresponding fuzzy envelopes, defined as trapezoidal fuzzy numbers (TrFNs). This conversion strategy effectively minimizes the loss in assessments based on HFLTSs while retaining the inherent ambiguity of the original information. Building upon this foundation, we develop fuzzy cross-efficiency models by leveraging the <span><math><mi>α</mi></math></span>-level sets of fuzzy envelopes. These models are designed to handle fuzzy input and output variables under various <span><math><mi>α</mi></math></span>-level sets, which are capable of considering all possible attribute values for each alternative. Following this, we implement a maximum consensus model using fuzzy cross-efficiency to assign weights to DMs. These weights facilitate the aggregation of individual fuzzy cross-efficiency intervals obtained from DMs’ assessments into collective ones, which serve to rank alternatives. Finally, we showcase the effectiveness and superiority of our proposal through numerical validation and comparative analysis.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110622"},"PeriodicalIF":6.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Most important performance evaluation methods of production lines: A comprehensive review on historical perspective and emerging trends","authors":"Mehmet Ulaş Koyuncuoğlu","doi":"10.1016/j.cie.2024.110623","DOIUrl":"10.1016/j.cie.2024.110623","url":null,"abstract":"<div><div>Production is one of the most significant building blocks that strengthen the sustainable economy of companies and thus contribute to the countries’ welfare. Performance indicators of the production line affect planning operations and the efficiency of the supply chain to which the factory is connected. The key indicators for production line designers and performance analysts to monitor and improve include production rate, resource utilization rate, and average inventory level. The production rate is the most important indicator closely affecting an industrial plant's productivity and efficiency levels. From this perspective, accurate and fast estimation of this indicator is very critical. Production rate can be calculated by simulation, analytical technique, or artificial intelligence methods according to the production line characteristics. In this comprehensive review, the most important performance evaluation methods are discussed historically and systematically about the buffer allocation problem using the snowball sampling method. With this explicit motivation, 145 papers were reviewed and classified according to production line topology, hypothetical/real-case line, machine reliability, previous method on which the method is based, and originality and/or line characteristics. To present a comprehensive comparison, the methods considered were analyzed according to different criteria. This review provides general/in-depth qualitative and quantitative discussions and highlights insights to practitioners and scholars. In addition, the impact of recent key work on production line analysis in the field is assessed along with emerging trends, evolving manufacturing paradigms are discussed, and the challenges associated with performance analysis are addressed.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110623"},"PeriodicalIF":6.7,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A blockchain-enabled private parking space allocation with improved parking space utilization","authors":"Keshab Kumar Gaurav , Gaurav Baranwal","doi":"10.1016/j.cie.2024.110613","DOIUrl":"10.1016/j.cie.2024.110613","url":null,"abstract":"<div><div>With the rapid development of the world’s infrastructure, we are moving towards making cities smart, known as smart cities. To make smart cities sustainable, designing efficient solutions is needed to reduce traffic congestion due to the lack of parking spaces within the constrained land areas of many metropolitan city centres. Parking problems in urban areas can be reduced by sharing vacant private parking spaces with others. In this work, we propose a decentralized and shared private parking management system using blockchain, which helps private parking owners and users fulfil their demands without the involvement of central authority. The proposed parking allocation method assigns parking to a single user from multiple parking providers, but the requester does not need to relocate between different parking spaces. The proposed method significantly improves private parking space utilization compared to a state-of-the-art parking allocation system. Hence, the system satisfies more user requests and generates more profit for parking owners than the state-of-the-art parking allocation system. The proposed system is a winning strategy because it maximizes the utilization of private parking spaces for the entire community’s benefit and helps to reduce traffic congestion. Experiments conducted in the simulated environment validate the benefits of the proposed model and show that it outperforms the state-of-the-art parking allocation system. A prototype of the proposed system is also developed in the Ethereum blockchain to validate the work, and the gas cost used to deploy the proposed model is analyzed.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110613"},"PeriodicalIF":6.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Selling mode choice and return policy for advance selling in an e-commerce platform with social influence","authors":"Haijiao Li , Kuan Yang , Ye Yao , Guoqing Zhang","doi":"10.1016/j.cie.2024.110620","DOIUrl":"10.1016/j.cie.2024.110620","url":null,"abstract":"<div><div>Advance selling is increasingly employed to mitigate demand uncertainty, raise consumer awareness of products, and even exert social influence on subsequent sales. However, consumers may hesitate to pre-order products due to uncertainty about product valuation. As a response, sellers have begun implementing return policies and utilizing online retail platforms to alleviate the uncertainty. This study aims to investigate the interaction between return policies for advance selling and selling formats of e-commerce platforms considering the impact of social influence. We examine a two-period platform supply chain that includes agency selling, reselling, and hybrid selling formats with and without return policies. Using game theory models, we analyze pricing decisions and profits of each player under six possible scenarios. The results indicate that the manufacturer consistently prefers adopting a Money-Back Guarantee (MBG) return policy regardless of the selling format. However, the MBG return policy is not always advantageous for the platform, except in the case of low social influence. In such a case, the platform may implement the MBG return policy to boost advance sales, thereby enhancing the penetration power from advance sales to regular sales. Regarding selling formats, the platform and the manufacturer opt for the reselling and agency selling, respectively, when the commission rate is low; otherwise, they adopt the agency selling and hybrid selling, respectively. Furthermore, we explore the impact of critical drivers on the pricing decisions and profits within the platform supply chain. Our study offers valuable insights into implementing return policies and determining selling formats.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110620"},"PeriodicalIF":6.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Romão Santos, Henrique Piqueiro, Rui Dias, Cláudia D. Rocha
{"title":"Transitioning trends into action: A simulation-based Digital Twin architecture for enhanced strategic and operational decision-making","authors":"Romão Santos, Henrique Piqueiro, Rui Dias, Cláudia D. Rocha","doi":"10.1016/j.cie.2024.110616","DOIUrl":"10.1016/j.cie.2024.110616","url":null,"abstract":"<div><div>In the dynamic realm of nowadays manufacturing, integrating digital technologies has become paramount for enhancing operational efficiency and decision-making processes. This article presents a novel system architecture that integrates a Simulation-based Digital Twin (DT) with emerging trends in manufacturing to enhance decision-making, accompanied by a detailed technical approach encompassing protocols and technologies for each component. The DT leverages advanced simulation techniques to model, monitor, and optimize production processes in real time, facilitating both strategic and operational decision-making. Complementing the DT, trending technologies such as artificial intelligence, additive manufacturing, collaborative robots, autonomous vehicles, and connectivity advancements are strategically integrated to enhance operational efficiency and facilitate the adoption of the Manufacturing as a Service (MaaS) paradigm. A case study within a MaaS supplier context, deployed in an industrial laboratory with advanced robotic systems, demonstrates the practical application of optimizing dynamic job-shop configurations using Simulation-based DT, showcasing strategies to improve operational efficiency and resource utilization. The results of the industrial experiment were highly encouraging, underscoring the potential for extension to more intricate industrial systems, with particular emphasis on incorporating sustainability and remanufacturing principles.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"198 ","pages":"Article 110616"},"PeriodicalIF":6.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Meiwei Zhang , Qiushi Cui , Yang Lü , Weihua Yu , Wenyuan Li
{"title":"A multimodal learning machine framework for Alzheimer’s disease diagnosis based on neuropsychological and neuroimaging data","authors":"Meiwei Zhang , Qiushi Cui , Yang Lü , Weihua Yu , Wenyuan Li","doi":"10.1016/j.cie.2024.110625","DOIUrl":"10.1016/j.cie.2024.110625","url":null,"abstract":"<div><div>Alzheimer’s disease (AD) is the most prevalent form of dementia, with no current cure. Early screening and intervention are vital. In multimodal AD data, besides neuroimaging dimensions, neuropsychological tests based on cognitive domains also provide the clinical information for diagnosing AD. However, previous multimodal methods often fuse these neuropsychological test scores with other data, losing the rich clinical details inherent in each test, including videos, speech, images, and text. To address this, we propose a novel framework with an entropy-based polynomial dimension expansion function that restores this critical information by accurately calculating the optimal polynomial degree. Additionally, the proposed framework offers a series of cognitive-based Extreme Learning Machine (ELM) models to better utilize the detailed clinical insights from neuropsychological tests, reducing diagnostic redundancy and noise. Finally, we design a boosting ensemble strategy that combines diagnostic models from various dimensions and cognitive domains, automatically optimizing weights to enhance diagnostic accuracy. Tested on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, our approach achieves over 98% accuracy and F1 scores, with no observed bias between mild cognitive impairment (MCI) and AD groups. Therefore, our framework can offer clinicians more logical recommendations for diagnosing and managing the disease.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"197 ","pages":"Article 110625"},"PeriodicalIF":6.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}