Journal of Industrial Information Integration最新文献

Compendium law in iterative information management: A comprehensive model perspective

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-24 DOI: 10.1016/j.jii.2025.100808

Qiang Li , Zhi Li

The existing limitations of the fundamental laws necessary for constructing a comprehensive and widely accepted theoretical framework have significantly hindered the progress of Information Management. This lack has resulted in a predominant reliance on indirect strategies to address information management challenges, often leading to complex, inefficient, and somewhat stochastic analyses and evaluations. For instance, the failure rate of digital transformation in global enterprises is as high as 80 %, and that of data-driven organizational change reaches 85 %, highlighting the urgency and difficulty of resolving these challenges. Through an in-depth analysis of the spiral model and derivation of the Shannon-Weaver model, we unearthed the objective and universal Compendium Law of iterative information management. Building on this law, we propose the application of information system modeling and Hamiltonian graph theory to develop a comprehensive analytical model for iterative information management. This model provides a theoretical approach for the scientific analysis and optimal design of iterative information management, enabling efficient comparative analysis and knowledge transfer among various iterative information management systems. This study contributes to the foundational understanding of Information Management as an independent discipline capable of addressing cross-disciplinary challenges related to information resources, including those found in artificial intelligence, blockchains, quantum communication, the Internet of Things, and digitization.

{"title":"Compendium law in iterative information management: A comprehensive model perspective","authors":"Qiang Li , Zhi Li","doi":"10.1016/j.jii.2025.100808","DOIUrl":"10.1016/j.jii.2025.100808","url":null,"abstract":"<div><div>The existing limitations of the fundamental laws necessary for constructing a comprehensive and widely accepted theoretical framework have significantly hindered the progress of Information Management. This lack has resulted in a predominant reliance on indirect strategies to address information management challenges, often leading to complex, inefficient, and somewhat stochastic analyses and evaluations. For instance, the failure rate of digital transformation in global enterprises is as high as 80 %, and that of data-driven organizational change reaches 85 %, highlighting the urgency and difficulty of resolving these challenges. Through an in-depth analysis of the spiral model and derivation of the Shannon-Weaver model, we unearthed the objective and universal Compendium Law of iterative information management. Building on this law, we propose the application of information system modeling and Hamiltonian graph theory to develop a comprehensive analytical model for iterative information management. This model provides a theoretical approach for the scientific analysis and optimal design of iterative information management, enabling efficient comparative analysis and knowledge transfer among various iterative information management systems. This study contributes to the foundational understanding of Information Management as an independent discipline capable of addressing cross-disciplinary challenges related to information resources, including those found in artificial intelligence, blockchains, quantum communication, the Internet of Things, and digitization.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100808"},"PeriodicalIF":10.4,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143534623","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}

引用次数: 0

Challenges in feature importance interpretation: Analyzing LSTM-NN predictions in battery material flotation

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-24 DOI: 10.1016/j.jii.2025.100809

Yoshiyasu Takefuji

Gomez-Flores et al. proposed a Long Short-Term Memory Neural Network (LSTM-NN) for predicting the flotation behavior of battery active materials using various physicochemical and hydrodynamic variables. While they achieved high prediction accuracy, validated through Mean Relative Error (MRE) and Mean Squared Error (MSE) metrics, concerns arise regarding the integrity of feature importance assessments derived from SAGE and SHAP methodologies. Specifically, the reliance on these model-specific techniques can introduce biases, obscuring the true relationships between features. Additionally, while Spearman's correlation elucidated significant relationships among variables, the absence of discussion on p-values left gaps in interpretation. This study emphasizes the need for cautious interpretation of feature importance metrics and the elimination of less significant variables, aiming to enhance model robustness and improve actionable insights in machine learning contexts.

引用次数: 0

Geometric deep learning as an enabler for data consistency and interoperability in manufacturing

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-22 DOI: 10.1016/j.jii.2025.100806

Patrick Bründl , Benedikt Scheffler , Christopher Straub , Micha Stoidner , Huong Giang Nguyen , Jörg Franke

Skilled labor shortages and the growing trend for customized products are increasing the complexity of manufacturing systems. Automation is often proposed to address these challenges, but industries operating under the engineer-to-order, lot-size-one production model often face significant limitations due to the lack of relevant data. This study investigates an approach for the extraction of assembly-relevant information, using only vendor-independent STEP files, and the integration and validation of these information in an exemplary industrial use case. The study shows that different postprocessing approaches of the same segmentation mask can result in significant differences regarding the data quality. This approach improves data quality and facilitates data transferability to components not listed in leading ECAD databases, suggesting broader potential for generalization across different components and use cases. In addition, an end-to-end inference pipeline without proprietary formats ensures high data integrity while approximating the surface of the underlying topology, making it suitable for small and medium-sized companies with limited computing resources. Furthermore, the pipeline presented in this study achieves improved accuracies through enhanced post-segmentation calculation approaches that successfully overcome the typical domain gap between data detected solely on virtual models and their physical application. The study not only achieves the accuracy required for full automation, but also introduces the Spherical Boundary Score (SBS), a metric for evaluating the quality of assembly-relevant information and its application in real-world scenarios.

{"title":"Geometric deep learning as an enabler for data consistency and interoperability in manufacturing","authors":"Patrick Bründl , Benedikt Scheffler , Christopher Straub , Micha Stoidner , Huong Giang Nguyen , Jörg Franke","doi":"10.1016/j.jii.2025.100806","DOIUrl":"10.1016/j.jii.2025.100806","url":null,"abstract":"<div><div>Skilled labor shortages and the growing trend for customized products are increasing the complexity of manufacturing systems. Automation is often proposed to address these challenges, but industries operating under the engineer-to-order, lot-size-one production model often face significant limitations due to the lack of relevant data. This study investigates an approach for the extraction of assembly-relevant information, using only vendor-independent STEP files, and the integration and validation of these information in an exemplary industrial use case. The study shows that different postprocessing approaches of the same segmentation mask can result in significant differences regarding the data quality. This approach improves data quality and facilitates data transferability to components not listed in leading ECAD databases, suggesting broader potential for generalization across different components and use cases. In addition, an end-to-end inference pipeline without proprietary formats ensures high data integrity while approximating the surface of the underlying topology, making it suitable for small and medium-sized companies with limited computing resources. Furthermore, the pipeline presented in this study achieves improved accuracies through enhanced post-segmentation calculation approaches that successfully overcome the typical domain gap between data detected solely on virtual models and their physical application. The study not only achieves the accuracy required for full automation, but also introduces the Spherical Boundary Score (SBS), a metric for evaluating the quality of assembly-relevant information and its application in real-world scenarios.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100806"},"PeriodicalIF":10.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-speed image enhancement: Real-time super-resolution and artifact removal for degraded analog footage

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-21 DOI: 10.1016/j.jii.2025.100798

Lorenzo Berlincioni, Marco Bertini, Alberto Del Bimbo

In this work we tackle the challenge of enhancing the quality of analog recorded images in real-time. This involves two key aspects: super-resolution to improve visual detail, and artifact removal to address specific issues unique to analog footage. We propose ARENet, a memory-efficient architecture trained in an adversarial setting that can handle analog videos with VHS-like artifacts while maintaining small memory footprint compared to other approaches. The model improves on SRUnet (Vaccaro et al., 2021) by working on its shortcomings when it comes to the diverse spectrum of analog video borne artifacts. More over, in order to be able to process large archives of stored analog videos our model was purposefully designed for fast visual quality improvement (i.e. capable of operating faster than 25 FPS on consumer hardware) and small memory footprint. The experimental results show that the proposed single frame based method achieves better perceptual performances with respect to the compared models while maintaining real time capabilities and being more suited for unique analog video artifacts. Our proposed approach has immediate implications for various industrial applications that involve working with analog video footage, including broadcasting, film restoration, and historical document preservation. By enhancing the visual quality of these recordings in real-time, our method can improve viewer experience, facilitate more accurate analysis and interpretation of content, and enable the digitization and archiving of previously inaccessible or degraded materials. Code and samples are available at https://github.com/LoreBerli/VHSRestoration

{"title":"High-speed image enhancement: Real-time super-resolution and artifact removal for degraded analog footage","authors":"Lorenzo Berlincioni, Marco Bertini, Alberto Del Bimbo","doi":"10.1016/j.jii.2025.100798","DOIUrl":"10.1016/j.jii.2025.100798","url":null,"abstract":"<div><div>In this work we tackle the challenge of enhancing the quality of analog recorded images in real-time. This involves two key aspects: super-resolution to improve visual detail, and artifact removal to address specific issues unique to analog footage. We propose ARENet, a memory-efficient architecture trained in an adversarial setting that can handle analog videos with VHS-like artifacts while maintaining small memory footprint compared to other approaches. The model improves on SRUnet (Vaccaro et al., 2021) by working on its shortcomings when it comes to the diverse spectrum of analog video borne artifacts. More over, in order to be able to process large archives of stored analog videos our model was purposefully designed for fast visual quality improvement (i.e. capable of operating faster than 25 FPS on consumer hardware) and small memory footprint. The experimental results show that the proposed single frame based method achieves better perceptual performances with respect to the compared models while maintaining real time capabilities and being more suited for unique analog video artifacts. Our proposed approach has immediate implications for various industrial applications that involve working with analog video footage, including broadcasting, film restoration, and historical document preservation. By enhancing the visual quality of these recordings in real-time, our method can improve viewer experience, facilitate more accurate analysis and interpretation of content, and enable the digitization and archiving of previously inaccessible or degraded materials. Code and samples are available at <span><span>https://github.com/LoreBerli/VHSRestoration</span><svg><path></path></svg></span></div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100798"},"PeriodicalIF":10.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474764","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}

引用次数: 0

Multi-agent digital twinning for collaborative logistics: Framework and implementation

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-21 DOI: 10.1016/j.jii.2025.100799

Liming Xu , Stephen Mak , Stefan Schoepf , Michael Ostroumov , Alexandra Brintrup

Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders’ participation in collaborations is hindered by information-sharing barriers and absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that facilitates collaboration through the integration of agents with digital twins. Specifically, we employ a multi-agent system approach to integrate stakeholders and physical assets in collaborative logistics, representing them as agents. We introduce a loosely-coupled system architecture that facilitates the connection between physical and digital systems, enabling the integration of agents with digital twins. Using this architecture, we implement a prototypical testbed. The resulting testbed, comprising a physical environment and a digital replica, is a digital twin that integrates distributed entities involved in collaborative logistics. Its effectiveness on integrating both physical and digital, stationary and mobile objects is demonstrated through a carrier collaboration scenario. This paper is among the few earliest efforts to examine the integration of agents and digital twin concepts in logistics sector and goes beyond the conceptual discussion of existing studies to the technical implementation of such integration.

{"title":"Multi-agent digital twinning for collaborative logistics: Framework and implementation","authors":"Liming Xu , Stephen Mak , Stefan Schoepf , Michael Ostroumov , Alexandra Brintrup","doi":"10.1016/j.jii.2025.100799","DOIUrl":"10.1016/j.jii.2025.100799","url":null,"abstract":"<div><div>Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders’ participation in collaborations is hindered by information-sharing barriers and absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that facilitates collaboration through the integration of agents with digital twins. Specifically, we employ a multi-agent system approach to integrate stakeholders and physical assets in collaborative logistics, representing them as agents. We introduce a loosely-coupled system architecture that facilitates the connection between physical and digital systems, enabling the integration of agents with digital twins. Using this architecture, we implement a prototypical testbed. The resulting testbed, comprising a physical environment and a digital replica, is a digital twin that integrates distributed entities involved in collaborative logistics. Its effectiveness on integrating both physical and digital, stationary and mobile objects is demonstrated through a carrier collaboration scenario. This paper is among the few earliest efforts to examine the integration of agents and digital twin concepts in logistics sector and goes beyond the conceptual discussion of existing studies to the technical implementation of such integration.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100799"},"PeriodicalIF":10.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent IoT-enabled healthcare solutions implementing federated meta-learning with blockchain

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-20 DOI: 10.1016/j.jii.2025.100797

Puja Das , Naresh Kumar , Chitra Jain , Ansul , Moutushi Singh

The rapid advancement and incorporation of Artificial Intelligence (AI) and the Internet of Things (IoT) have created exceptional opportunities to revolutionize healthcare and treatment methods and offer significant potential for broader industrial information integration. Nevertheless, the growth of intelligent healthcare systems faces challenges such as data confidentiality concerns and the safety of AI algorithms. The need for local datasets is the main problem in applying traditional AI to the development of a personalized model for health care. Thus, to tackle these issues, a novel healthcare system based on blockchain powered by federated matrix meta-learning supported by IoT. In this system, IoT devices function as light nodes, uploading local, shareable information to an edge server for model training, while non-tampered models downloaded through smart contracts handle local private data. This framework comprises four key modules: a hierarchical feature extraction module, a graph topology formulation unit, a dynamic prototype optimization algorithm, and a predictive query integration system. Blockchain technology ensures the healthcare model remains consistent and protects private data from leaks. Also, it has offered a federated matrix meta-learning model known as the federated Matrix-prototype Graph Network (MGN) to handle heterogeneous healthcare data efficiently. This model, based on metrics and graph networks, excels at capturing data distributions even with limited labeled data. To validate the efficacy of the proposed framework, we conducted extensive evaluations using two widely recognized datasets: CheXpert only for medical imaging and CIFAR 100 for general image classification. These experiments increased the performance of up to 85 percent of existing healthcare systems, demonstrating the potential of the proposed integrated approach to solve the industry’s main problems. Thus, this study advances the current discourses on the development of strong, privacy-oriented, and context-aware AI solutions for health systems, which, together with intelligent health technology, will help to raise the efficiency and effectiveness of patient care in the future.

{"title":"Intelligent IoT-enabled healthcare solutions implementing federated meta-learning with blockchain","authors":"Puja Das , Naresh Kumar , Chitra Jain , Ansul , Moutushi Singh","doi":"10.1016/j.jii.2025.100797","DOIUrl":"10.1016/j.jii.2025.100797","url":null,"abstract":"<div><div>The rapid advancement and incorporation of Artificial Intelligence (AI) and the Internet of Things (IoT) have created exceptional opportunities to revolutionize healthcare and treatment methods and offer significant potential for broader industrial information integration. Nevertheless, the growth of intelligent healthcare systems faces challenges such as data confidentiality concerns and the safety of AI algorithms. The need for local datasets is the main problem in applying traditional AI to the development of a personalized model for health care. Thus, to tackle these issues, a novel healthcare system based on blockchain powered by federated matrix meta-learning supported by IoT. In this system, IoT devices function as light nodes, uploading local, shareable information to an edge server for model training, while non-tampered models downloaded through smart contracts handle local private data. This framework comprises four key modules: a hierarchical feature extraction module, a graph topology formulation unit, a dynamic prototype optimization algorithm, and a predictive query integration system. Blockchain technology ensures the healthcare model remains consistent and protects private data from leaks. Also, it has offered a federated matrix meta-learning model known as the federated Matrix-prototype Graph Network (MGN) to handle heterogeneous healthcare data efficiently. This model, based on metrics and graph networks, excels at capturing data distributions even with limited labeled data. To validate the efficacy of the proposed framework, we conducted extensive evaluations using two widely recognized datasets: CheXpert only for medical imaging and CIFAR 100 for general image classification. These experiments increased the performance of up to 85 percent of existing healthcare systems, demonstrating the potential of the proposed integrated approach to solve the industry’s main problems. Thus, this study advances the current discourses on the development of strong, privacy-oriented, and context-aware AI solutions for health systems, which, together with intelligent health technology, will help to raise the efficiency and effectiveness of patient care in the future.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100797"},"PeriodicalIF":10.4,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human-Centric Green Design for automatic production lines: Using virtual and augmented reality to integrate industrial data and promote sustainability

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-18 DOI: 10.1016/j.jii.2025.100801

Giuditta Contini , Fabio Grandi , Margherita Peruzzini

The rapid evolution from Industry 4.0 to Industry 5.0 has heightened the need for integrating sustainability practices within complex system designs, particularly in the manufacturing sector. The research presents the development of a Sustainability Digital Twin (SDT) framework aimed at enhancing sustainable design practices for complex engineering systems. This framework integrates digital product models with sustainability indicators and uses Virtual Reality (VR) and Augmented Reality (AR) to promote Green Design principles. The approach begins with the definition of specific Sustainability Key Performance Indicators (S-KPIs) obtained by Life Cycle Assessment (LCA) tools. After that, using VR and AR allows to design and develop customized interactive dashboards to provide a comprehensive overview of sustainability indicators across the social, environmental, and economic dimensions, and to support decision-making along the product lifecycle. A core element of this transdisciplinary methodology is the adoption of a human-centered design philosophy, ensuring that user interfaces are intuitive and user-friendly, to Green Design tools, with the support of advanced digital technologies. The integration of human-machine interaction models aims at extending the current Green Design practices, mainly focused on environmental performances, towards social areas, including human-centric aspects such as usability, accessibility, comfort and pleasure in use. The research applies the proposed transdisciplinary approach to an industrial case study on automatic production lines, focusing on the ceramics industry, developed in collaboration with a world leading company in this sector. The case study highlighted the potential of combining SDT and AR/VR to create a dynamic and interactive platform for sustainable co-design, ultimately contributing to the advancement of Green Design practices in the ceramic industry and providing a scalable model for other industries aiming to achieve similar goals.

{"title":"Human-Centric Green Design for automatic production lines: Using virtual and augmented reality to integrate industrial data and promote sustainability","authors":"Giuditta Contini , Fabio Grandi , Margherita Peruzzini","doi":"10.1016/j.jii.2025.100801","DOIUrl":"10.1016/j.jii.2025.100801","url":null,"abstract":"<div><div>The rapid evolution from Industry 4.0 to Industry 5.0 has heightened the need for integrating sustainability practices within complex system designs, particularly in the manufacturing sector. The research presents the development of a Sustainability Digital Twin (SDT) framework aimed at enhancing sustainable design practices for complex engineering systems. This framework integrates digital product models with sustainability indicators and uses Virtual Reality (VR) and Augmented Reality (AR) to promote Green Design principles. The approach begins with the definition of specific Sustainability Key Performance Indicators (S-KPIs) obtained by Life Cycle Assessment (LCA) tools. After that, using VR and AR allows to design and develop customized interactive dashboards to provide a comprehensive overview of sustainability indicators across the social, environmental, and economic dimensions, and to support decision-making along the product lifecycle. A core element of this transdisciplinary methodology is the adoption of a human-centered design philosophy, ensuring that user interfaces are intuitive and user-friendly, to Green Design tools, with the support of advanced digital technologies. The integration of human-machine interaction models aims at extending the current Green Design practices, mainly focused on environmental performances, towards social areas, including human-centric aspects such as usability, accessibility, comfort and pleasure in use. The research applies the proposed transdisciplinary approach to an industrial case study on automatic production lines, focusing on the ceramics industry, developed in collaboration with a world leading company in this sector. The case study highlighted the potential of combining SDT and AR/VR to create a dynamic and interactive platform for sustainable co-design, ultimately contributing to the advancement of Green Design practices in the ceramic industry and providing a scalable model for other industries aiming to achieve similar goals.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100801"},"PeriodicalIF":10.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effects of Lean Tools and Industry 4.0 technology on productivity: An empirical study

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-17 DOI: 10.1016/j.jii.2025.100787

André Guimarães , Eduardo e Oliveira , Marisa Oliveira , Teresa Pereira

Purpose:

In the 4th Industrial Revolution era, companies are increasingly adopting strategies to maximize the potential of Industry 4.0 technologies. Many organizations integrate established Lean and Six Sigma tools to support the effective deployment of these innovations. Although existing literature explores the interplay between Industry 4.0 and Lean methodologies, there is limited focus on their direct impact on productivity. This study bridges that gap by analyzing how Industry 4.0 technologies and Lean and Six Sigma practices influence overall productivity, emphasizing two dimensions: operational efficiency, achieved through process optimization and waste reduction, and financial performance, centered on profitability and economic sustainability.

Methodology:

The investigation is conducted through an empirical study involving surveys of industrial companies in a central region of Portugal. The analysis of the research results includes the application of statistical tests, such as exploratory factor analysis, and the use of structural equation modeling techniques for confirmatory analysis.

Findings:

The results indicate that Industry 4.0 immediately impacts productivity. On the other hand, the influence of Lean and Six Sigma tools on productivity may not be immediate. Still, when analyzed over a more extensive time, their impact becomes more significant.

Originality/value:

This paper contributes significantly by presenting an empirical study that examines the impact of Lean tools and Industry 4.0 technologies on productivity. While the existing literature mainly consists of literature reviews or empirical analyses linking Lean tools and Industry 4.0, this study uniquely addresses the connection between these two concepts and productivity through an empirical study. Additionally, the findings emphasize that the influence of both Lean tools and Industry 4.0 on productivity is contingent on the duration since their implementation.

{"title":"Effects of Lean Tools and Industry 4.0 technology on productivity: An empirical study","authors":"André Guimarães , Eduardo e Oliveira , Marisa Oliveira , Teresa Pereira","doi":"10.1016/j.jii.2025.100787","DOIUrl":"10.1016/j.jii.2025.100787","url":null,"abstract":"<div><h3>Purpose:</h3><div>In the 4th Industrial Revolution era, companies are increasingly adopting strategies to maximize the potential of Industry 4.0 technologies. Many organizations integrate established Lean and Six Sigma tools to support the effective deployment of these innovations. Although existing literature explores the interplay between Industry 4.0 and Lean methodologies, there is limited focus on their direct impact on productivity. This study bridges that gap by analyzing how Industry 4.0 technologies and Lean and Six Sigma practices influence overall productivity, emphasizing two dimensions: operational efficiency, achieved through process optimization and waste reduction, and financial performance, centered on profitability and economic sustainability.</div></div><div><h3>Methodology:</h3><div>The investigation is conducted through an empirical study involving surveys of industrial companies in a central region of Portugal. The analysis of the research results includes the application of statistical tests, such as exploratory factor analysis, and the use of structural equation modeling techniques for confirmatory analysis.</div></div><div><h3>Findings:</h3><div>The results indicate that Industry 4.0 immediately impacts productivity. On the other hand, the influence of Lean and Six Sigma tools on productivity may not be immediate. Still, when analyzed over a more extensive time, their impact becomes more significant.</div></div><div><h3>Originality/value:</h3><div>This paper contributes significantly by presenting an empirical study that examines the impact of Lean tools and Industry 4.0 technologies on productivity. While the existing literature mainly consists of literature reviews or empirical analyses linking Lean tools and Industry 4.0, this study uniquely addresses the connection between these two concepts and productivity through an empirical study. Additionally, the findings emphasize that the influence of both Lean tools and Industry 4.0 on productivity is contingent on the duration since their implementation.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100787"},"PeriodicalIF":10.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429597","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}

引用次数: 0

Cross-patch graph transformer enforced by contrastive information fusion for energy demand forecasting towards sustainable additive manufacturing

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-17 DOI: 10.1016/j.jii.2025.100795

Kang Wang , Haoneng Lin , Naiyu Fang , Jinghua Xu , Shuyou Zhang , Jianrong Tan , Jing Qin , Xuan Liang

We propose an effective deep learning method, called Cross-patch Graph Transformer, for predicting the energy demand of Additive Manufacturing (AM) products, which helps to determine the solution with minimal fabrication energy for sustainable AM. This novel method can predict the energy demand of intricate structures by training with simple structures, which alleviates the expensive burden of collecting training data. Our method efficiently integrates node-level, patch-level, and image-level information from part geometry, enabling precise energy demand predictions for products manufactured using AM technology. This approach contributes methodological insights into developing a contrastive information fusion model that enhances energy-related representations even with limited data resources. The incorporation of the cross-patch interaction module enables the method to effectively capture structural relationships, enriching the learning process. Extensive experimental results show our method achieves a higher mean prediction accuracy of 98.3%, validating the effectiveness of our approach across a diverse set of intricate structures. This method not only provides a robust and quantitative tool for identifying optimal solutions with minimal energy demand during the manufacturing of complex structures, but also holds the potential to drive the evolution of computer-aided design towards more sustainable AM practices.

{"title":"Cross-patch graph transformer enforced by contrastive information fusion for energy demand forecasting towards sustainable additive manufacturing","authors":"Kang Wang , Haoneng Lin , Naiyu Fang , Jinghua Xu , Shuyou Zhang , Jianrong Tan , Jing Qin , Xuan Liang","doi":"10.1016/j.jii.2025.100795","DOIUrl":"10.1016/j.jii.2025.100795","url":null,"abstract":"<div><div>We propose an effective deep learning method, called Cross-patch Graph Transformer, for predicting the energy demand of Additive Manufacturing (AM) products, which helps to determine the solution with minimal fabrication energy for sustainable AM. This novel method can predict the energy demand of intricate structures by training with simple structures, which alleviates the expensive burden of collecting training data. Our method efficiently integrates node-level, patch-level, and image-level information from part geometry, enabling precise energy demand predictions for products manufactured using AM technology. This approach contributes methodological insights into developing a contrastive information fusion model that enhances energy-related representations even with limited data resources. The incorporation of the cross-patch interaction module enables the method to effectively capture structural relationships, enriching the learning process. Extensive experimental results show our method achieves a higher mean prediction accuracy of 98.3%, validating the effectiveness of our approach across a diverse set of intricate structures. This method not only provides a robust and quantitative tool for identifying optimal solutions with minimal energy demand during the manufacturing of complex structures, but also holds the potential to drive the evolution of computer-aided design towards more sustainable AM practices.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100795"},"PeriodicalIF":10.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464104","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}

引用次数: 0

Next generation road safety solutions: IoT-driven accident prevention for smart riders

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-02-16 DOI: 10.1016/j.jii.2025.100804

Santhiya Ravindran, Gurukarthik Babu Balachandran

In recent days, two wheeler users have more probability to meet accidents due to high number of utilization than others. To manage this scenario, we proposed an Internet of Things(IoT) based approach with three phases.1.Pre-Accident warning System which helps to reduce the two wheeler accidents greatly through distance based warning to the user when a vehicle moving in surrounding of them reached close to it &supports the users/drivers to avoid the accidents due to drowsiness, night time travelling(for poor visibility).Drunk and drive warning is also introduced to avoid unpleasant situations.2.Post-Accident Reporting system:It will send the SMS alert automatically using webhook SMS services with accident location, vehicle type &vehicle number to the trusted contact number &make them to provide the medical emergency at right time.3.Automatic Road Accident Database Updating System: road accidents statistic report helped to formulate the road safety rules and regulations. Currently, accident data are collected manually from police department/transport department &updated in an accident database management system. We developed a model to collect the accident data automatically and to store in cloud based time series database. Also a website is created using google sites to monitor the status of all three phases of above including the details of vehicle type wise number of accidents. It helps road safety &police department to know about basic accident details immediately and to take appropriate actions. The developed system is fully self-operated &tested under prototype model of bicycle, scooty &bike and also experimentally verified in real vehicles with the response time <40 s.

{"title":"Next generation road safety solutions: IoT-driven accident prevention for smart riders","authors":"Santhiya Ravindran, Gurukarthik Babu Balachandran","doi":"10.1016/j.jii.2025.100804","DOIUrl":"10.1016/j.jii.2025.100804","url":null,"abstract":"<div><div>In recent days, two wheeler users have more probability to meet accidents due to high number of utilization than others. To manage this scenario, we proposed an Internet of Things(IoT) based approach with three phases.1.Pre-Accident warning System which helps to reduce the two wheeler accidents greatly through distance based warning to the user when a vehicle moving in surrounding of them reached close to it &supports the users/drivers to avoid the accidents due to drowsiness, night time travelling(for poor visibility).Drunk and drive warning is also introduced to avoid unpleasant situations.2.Post-Accident Reporting system:It will send the SMS alert automatically using webhook SMS services with accident location, vehicle type &vehicle number to the trusted contact number &make them to provide the medical emergency at right time.3.Automatic Road Accident Database Updating System: road accidents statistic report helped to formulate the road safety rules and regulations. Currently, accident data are collected manually from police department/transport department &updated in an accident database management system. We developed a model to collect the accident data automatically and to store in cloud based time series database. Also a website is created using google sites to monitor the status of all three phases of above including the details of vehicle type wise number of accidents. It helps road safety &police department to know about basic accident details immediately and to take appropriate actions. The developed system is fully self-operated &tested under prototype model of bicycle, scooty &bike and also experimentally verified in real vehicles with the response time <40 s.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100804"},"PeriodicalIF":10.4,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455001","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}

引用次数: 0