Journal of Industrial Information Integration最新文献

{"title":"A bi-contrast self-supervised learning framework for enhancing multi-label classification in Industrial Internet of Things","authors":"Xin Hu, Yifan Chen, Jichao Leng, Yuhua Yao, Xiaoming Hu, Zhuo Zou","doi":"10.1016/j.jii.2025.100777","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100777","url":null,"abstract":"In the Industrial Internet of Things (IIoT), multi-label classification is challenging due to limited labeled data, class imbalance, and the necessity to consider temporal and spatial dependencies. We propose BiConED, a bi-contrast encoder–decoder self-supervised model integrating two contrasting methods: RAC employs an encoder–decoder with augmented data to capture temporal dependencies and boost information entropy, enhancing generalization under label scarcity. QuadC captures spatial dependencies across channels through convolutions on hidden vectors. Evaluated on the real-world industrial benchmark SKAB, BiConED improves feature extraction for underrepresented classes, achieving a 26% increase in F1 score, a 67.72% reduction in False Alarm Rate (FAR), and a 57.25% decrease in Missed Alarm Rate (MAR) compared to models without the proposed contrasts. Even with limited labeled data, BiConED maintains a FAR below 1% and recovers up to 85% of the F1 score without resampling, demonstrating its robustness in imbalanced IIoT environments.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"35 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143049837","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}

{"title":"Backpropagation neural network model with statistical inference in manufacturing processes","authors":"Homero de León-Delgado, Rolando J. Praga-Alejo, David S. González-González","doi":"10.1016/j.jii.2025.100783","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100783","url":null,"abstract":"Nowadays, there is a growing need for tools to model the complex characteristics of manufacturing processes to support decision-making and optimize production and quality. This study proposes using a Backpropagation neural network (BPNN) to model manufacturing processes, leveraging its ability to capture complex and nonlinear relationships. Additionally, integrating statistical inference techniques from Generalized Linear Models (GLM) with the neural network is suggested. This integration combines the predictive capabilities of the BPNN with the statistical tools of GLMs, enhancing result interpretability and analysis accuracy. The proposed approach was applied to two manufacturing processes. In the die-casting process, the BPNN with a logit function showed a lower deviance (0.0399) compared to the probit model (0.0875) and a greater deviance difference (6.1280) with a <ce:italic>p</ce:italic>-value of 0.0201. Confidence intervals confirmed the significance of these results. Metal temperature and solidification time were significant predictors, with weights of -1.0375 and -0.9880, respectively. In the machining process, the BPNN model with the probit function had a lower deviance (0.0140) compared to the logit model (0.0175) and a slight precision advantage with a deviance difference of 3.9325 and a p-value of 0.0473. Parameters S1 and S2 had significant effects with weights of 72.671 and -54.397, respectively. This approach allows for selecting optimal activation functions for each process, improving efficiency and quality control in manufacturing.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"10 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143049838","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}

{"title":"Realization of the physical to virtual connection for digital twin of construction crane","authors":"Enliu Yuan, Jian Yang, Mohamed Saafi, Fei Wang, Jianqiao YE","doi":"10.1016/j.jii.2025.100779","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100779","url":null,"abstract":"A digital twin is an integrated multi-physics representation of a complex physical entity. This article develops the physical-to-virtual connection of the digital twin and proposes a framework for the construction of a tower crane digital twin. The main contributions of this paper include development of tower crane monitoring dataset, tower crane detection and tower crane operation mode recognition. By annotating &gt;20,000 tower crane images in 583 tower crane videos, a tower crane image recognition dataset and a tower crane operating mode dataset are established. Yolov5x algorithm is used in the tower crane detection, and the test set detection accuracy is 93.85 %. After comparing the LSTM and CNN algorithms, 3DResNet algorithm is selected for tower crane operational mode recognition. The dataset is augmented by rotating the image and the final recognition accuracy reaches 87 %. These models can be installed on CCTV to monitor operational status of tower crane in real time and transfer relevant information to the virtual model. The tower crane in the virtual space completes the action of the physical tower crane, thereby realizing the physical-to-virtual mapping in the digital twin.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"12 19 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142990512","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}

{"title":"Multi-criteria group decision-making with spherical fuzzy rough numbers for biomedical materials in hip prosthesis","authors":"Muhammad Akram, Maheen Sultan, Cengiz Kahraman","doi":"10.1016/j.jii.2024.100766","DOIUrl":"https://doi.org/10.1016/j.jii.2024.100766","url":null,"abstract":"Biomedical materials play a crucial role in modern medicine, helping restore and enhance function after injury or illness. These materials, whether natural or synthetic, are used in clinical applications to support, reinforce, or replace damaged tissues or biological functions. This study focuses on the effectiveness and advancements of biomedical materials in hip replacement surgery, offering various solutions for the recovery of different hip injuries. To compute biocompatibility and biodegradability of biomedical materials in hip prosthesis, this research paper develops a multi-criteria group decision making technique to encompass all aspects of an issue under consideration within a decision-making team’s governance. The suggested multi-criteria decision making outranking technique combined with spherical fuzzy rough approach excels in a unique way by encapsulating the capabilities to handle pseudo criteria and compare the considered options by referring to the indifference, strong and weak preference relation. Moreover, the proposed outranking technique effectively employs spherical fuzzy rough numbers to minimize subjective bias while addressing varying degrees of uncertainty. The practical implication of the proposed technique is addressed by considering the case study of material selection in hip prosthesis. Finally, the validity of the proposed technique is confirmed by comparing it with existing methods, and the selection of the same best alternative across all techniques reinforces its credibility.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"21 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968076","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}

{"title":"An industrial dataspace for automotive supply chain: Secure data sharing based on data association relationship","authors":"Yuqiao Liao, Xianguang Kong, Lei Yin, Yunpeng Gao, Xinghua Dong","doi":"10.1016/j.jii.2025.100778","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100778","url":null,"abstract":"The automotive supply chain (ASC) is a complex system involving every aspect of automobile manufacturing, from which the data obtained features such as massive volume, diverse types, and complex relationships. Traditional data management methods no longer meet the demands of handling heterogeneous data from multiple sources or ensuring secure cross-domain data sharing in the ASC, which leads to the isolation of information. Therefore, this paper proposes a data management method based on Industrial Dataspace (IDS), constructs a dataspace architecture for the automotive supply chain (DS-ASC). On this basis, proposes a method for data relationship mining and trusted data sharing that considers implicit associations among ASC members. The improved BiLSTM model promotes the understanding of data, and the improved DPoS algorithm reduces the risk of data leakage. Our method is validated in the practical application of a supply chain master enterprise, and the experiments show that the method proposed in this paper is able to effectively improve the accuracy of mining data association relationship. Meanwhile, it is able to prevent single-point attacks, and ensure the security of data sharing.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"27 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968092","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}

{"title":"Method towards collaborative cloud and edge computing via RBC for joint communication and computation resource allocation","authors":"Ruiling Gao, Wenzhong Zhang, Wenyi Mao, Jinjing Tan, Jin Zhang, Haiyun Huang, Wen'an Tan, Feiyue Huang","doi":"10.1016/j.jii.2025.100776","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100776","url":null,"abstract":"With the extensive adoption of cloud and edge computing in intelligent manufacturing systems driven by the Industrial Internet of Things (IIoT) and Artificial Intelligence, enhancing the efficiency of cloud-edge collaboration under constrained communication and computational resources has emerged as a prominent research focus. We develop the GRALB model, which is based on Role-Based Collaboration (RBC) in cooperative services, to comprehensively manage the offloading strategy of terminal user tasks between edge nodes and the cloud to solve the joint communication and computing resource allocation problem in intelligent manufacturing systems. First, we jointly model the end-to-end latency and energy consumption based on the physical scenario of cloud-edge collaboration. Then, we extend the GRA model based on E-CARGO and propose the GRALB model with load balancing, which formally models the original joint communication and computing resource allocation problem as an equivalent cooperative service model and provides a proof of algorithm convergence. Finally, we design an x-ILP solution to support the verification and integrated application of the proposed model. Simulation results further confirm our theoretical analysis and show that the proposed collaborative cloud and edge computing solution significantly improves the overall system performance.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"36 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968094","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}

{"title":"Context-aware cognitive augmented reality assembly: Past, present, and future","authors":"Wei Fang, Lixi Chen, Lei Han, Ji Ding","doi":"10.1016/j.jii.2025.100780","DOIUrl":"https://doi.org/10.1016/j.jii.2025.100780","url":null,"abstract":"Since the inception of Augmented Reality (AR) nearly three decades ago, numerous studies have demonstrated its potential to provide intuitive instructions for manual tasks within the manufacturing sector. This includes operations such as manual assembly, which can be executed with high efficiency and a focus on error-avoidance. Despite this, to the best of our knowledge, there has been no comprehensive review of the cognitive AR assembly method from a holistic perspective. This includes aspects such as context awareness, visual instructions, environment interaction, human factor considerations, and the impact on real-world AR assembly deployment. These factors are particularly relevant to current human-centric manufacturing practices in Industry 5.0. Since 2012, the release of Google Glass and advancements in artificial intelligence (AI) have significantly expanded actual AR deployments. Consequently, this review takes 2012 as the starting point for the literature collection. The objective of this article is to provide an overview of the context-aware cognitive AR (CA-CAR) assembly works published between 2012 and 2023. We aim to identify and classify the necessary context modules for CA-CAR assembly, and analyze potential technical barriers to their shop floor adaptation. It should be noted that this work offers both a historical perspective and a comprehensive map of the current research landscape surrounding the development of CA-CAR assembly applications. Furthermore, we discuss recent research trends and open problems in the field of CA-CAR assembly, along with potential future research directions.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968093","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}

{"title":"Energy-resilient closed-loop supply chain design managed by the 3PL provider: A pick-up strategy and data envelopment analysis","authors":"Beheshteh Moghadaspoor, Reza Tavakkoli-Moghaddam, Ali Bozorgi-Amiri, Tofigh Allahviranloo","doi":"10.1016/j.jii.2024.100763","DOIUrl":"https://doi.org/10.1016/j.jii.2024.100763","url":null,"abstract":"Population growth and the development of transportation networks have caused the world to face a larger volume of scrap tires, which can cause critical environmental challenges if they are not properly disposed of after being ultimately used. Thus, implementing appropriate recovery practices has developed. The existing challenges in the forward and reverse integration flow motivate leaders to submit a third-party logistics service provider (3PL) as an appropriate option for outsourcing activities. As a result, an inventive closed-loop supply chain (CLSC) network is necessary. A multiple objective, product, and period mathematical model is proposed to develop the CLSC under 3PL management in the tire industry. The data envelopment analysis (DEA) method is applied to choose a better set of manufacturers to coordinate with 3PL. The motivating pricing approach is also considered for appropriate recovery practices, and resiliency was investigated against disruption at crucial levels. This model aims to minimize the costs of diverse processes over scrap products and energy consumption and reach a sufficient level of responsiveness to customers. For solving the multi-objective model, the augmented ε-constraint (AUGMECON2) method leads to Pareto-optimal solutions. The results show that 3PLs improve the supply chain (SC) procedure and increase the responsiveness to customer demand. Also, by planning to increase product recycling, it is possible to save money when purchasing raw materials from suppliers.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"125 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142929357","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}

{"title":"A novel Pythagorean fuzzy correlation coefficient based on Spearman’s technique of correlation coefficient with applications in supplier selection process","authors":"Paul Augustine Ejegwa, Nasreen Kausar, Nezir Aydin, Muhammet Deveci","doi":"10.1016/j.jii.2024.100762","DOIUrl":"https://doi.org/10.1016/j.jii.2024.100762","url":null,"abstract":"A Pythagorean fuzzy correlation coefficient (PFCC) is a reliable approach for eliminating ambiguity during the measure of relationships. Numerous Pythagorean fuzzy correlation coefficient methods (PFCCMs) have been constructed using Pearson’s correlation coefficient technique. In this study, a new PFCCM is constructed based on Spearman’s correlation coefficient to eliminate all possible uncertainties that may impede decision-makers from making a dependable selection. To validate the construction of a new PFCCM, we examine the existing PFCCMs and pinpoint their inadequacies. Among the extant PFCCMs, one approach was constructed through Spearman’s correlation coefficient but it does not takes into cognizance the properties of the PFSs. In addition, it sometimes fails the axiomatic conditions of the PFCC, and yields invalid result for PFSs that are defined on a singleton set. These setbacks justify the construction of a new Spearman’s correlation coefficient-like PFCCM, which is shown to overcome the limitations of the extant PFCCMs. Equally, the strength of the new PFCCM is verified by some theoretical results, and it fulfills the conditions of PFCC. Additionally, the use of the novel PFCCM is discussed in the solution of supplier selection problems to eliminate supplier selection ambiguity through the multiple criteria decision-making (MCDM) approach. To unarguably show the intrinsic worth of the new PFCCM, the effectiveness of the new PFCCM is compared with the existing PFCCMs and it is observed that the new PFCCM is reliable, consistent and precise, and in the same way satisfies the axioms of the PFCC. In particular, the existing Spearman’s PFCCM yields <mml:math altimg=\"si1.svg\" display=\"inline\"><mml:mi>∞</mml:mi></mml:math> in Example 4, while the new PFCCM produces 0.7603, which justifies the construction of a new Spearman’s PFCCM. Finally, it is found that the new approach can suitably handle the hesitancies associated with the art of selection.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"38 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142929425","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}

{"title":"The impact of generative AI on management innovation","authors":"Caiming Zhang, Hui Zhang","doi":"10.1016/j.jii.2024.100767","DOIUrl":"https://doi.org/10.1016/j.jii.2024.100767","url":null,"abstract":"Generative Artificial Intelligence (GAI) demonstrates significant potential in the application of management and organizational innovation. This paper systematically investigates the multifaceted impacts of GAI on management decision-making, management algorithms, information integration, and various specific domains. GAI significantly enhances the accuracy of management decisions through its robust data analysis and predictive capabilities. By effectively integrating internal and external information, it reduces information asymmetry and improves both information transparency and the quality of decisions. In terms of specific application areas, GAI shows broad prospects in multiple fields, including business, education, healthcare, content creation, and game development. As GAI technology continues to advance, it will become more intelligent and adaptive. However, further research and the establishment of relevant ethical guidelines and legal frameworks are necessary to ensure its safety and reliability.","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"14 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889006","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}