Journal of Industrial Information Integration最新文献_第2页

Adaptive hybrid quantum-classical computing framework for deep space exploration mission applications

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

Journal of Industrial Information Integration

Pub Date : 2025-02-15 DOI: 10.1016/j.jii.2025.100803

M.W. Geda , Yuk Ming Tang

Quantum computing presents transformative potential for solving complex problems in industrial systems, particularly through its application in space mission operations. However, the practical deployment of fully quantum systems faces substantial challenges due to hardware noise, decoherence, and limited qubit coherence times. To address this challenge, this study proposes a framework for hybrid quantum-classical computing tailored to space systems' unique demands. The framework integrates quantum sensors, processors, and communication components with conventional spacecraft computing systems to overcome quantum hardware constraints. Through quantum-classical computing integration, the framework enhances operational efficiency and information integration essential for complex space mission operations. We discuss the critical components and integration interfaces of the hybrid framework and demonstrate its application through a case study on satellite imaging task scheduling. We implement the Quantum Approximate Optimization Algorithm (QAOA) and IBM's Qiskit quantum simulator to solve the scheduling task scheduling problem. Results obtained from the simulation demonstrate enhanced optimization capabilities compared to a greedy algorithm. The results highlight the advantages of information integration between quantum and classical systems for solving complex satellite scheduling tasks.

{"title":"Adaptive hybrid quantum-classical computing framework for deep space exploration mission applications","authors":"M.W. Geda , Yuk Ming Tang","doi":"10.1016/j.jii.2025.100803","DOIUrl":"10.1016/j.jii.2025.100803","url":null,"abstract":"<div><div>Quantum computing presents transformative potential for solving complex problems in industrial systems, particularly through its application in space mission operations. However, the practical deployment of fully quantum systems faces substantial challenges due to hardware noise, decoherence, and limited qubit coherence times. To address this challenge, this study proposes a framework for hybrid quantum-classical computing tailored to space systems' unique demands. The framework integrates quantum sensors, processors, and communication components with conventional spacecraft computing systems to overcome quantum hardware constraints. Through quantum-classical computing integration, the framework enhances operational efficiency and information integration essential for complex space mission operations. We discuss the critical components and integration interfaces of the hybrid framework and demonstrate its application through a case study on satellite imaging task scheduling. We implement the Quantum Approximate Optimization Algorithm (QAOA) and IBM's Qiskit quantum simulator to solve the scheduling task scheduling problem. Results obtained from the simulation demonstrate enhanced optimization capabilities compared to a greedy algorithm. The results highlight the advantages of information integration between quantum and classical systems for solving complex satellite scheduling tasks.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100803"},"PeriodicalIF":10.4,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454998","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

SEAL+: A subgraph-enhanced framework for link prediction with graph neural networks

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

Journal of Industrial Information Integration

Pub Date : 2025-02-15 DOI: 10.1016/j.jii.2025.100802

Reyhane Karami , S. Mehdi Vahidipour , Alireza Rezvanian

Link prediction is a critical research topic in network analysis, typically formulated as a classification problem where the goal is to determine whether a link exists between a pair of nodes (denoted as 1 in existence and 0 for non-existence). In most existing works, the feature vectors of a pair of nodes are combined to obtain the feature vector representing the link between them; these feature vectors (or embeddings) are constructed using graph neural networks (GNNs). This paper uses a GNN-based link prediction method called EAL as the baseline. EAL consists of an Encoder and a Decoder. A significant challenge in EAL is that the feature vector extracted by the GNN can be identical for different pairs of nodes. To address this issue, we propose leveraging the concept of subgraphs to enhance link prediction performance. To this end, the Encoder is equipped with subgraphs, forming the SEAL framework. One limitation of SEAL is that it generates identical link representations for different links when the embeddings of the nodes involved are the same. To overcome this limitation, the Decoder of SEAL also uses the subgraph information, resulting in the novel framework SEAL+. We evaluate these two frameworks against baseline methods using various metrics, demonstrating their superiority. Specifically, SEAL+ achieves average improvements of 10.25 %, 17.25 %, 3.75 %, and 4.65 % in terms of accuracy, F1-Score, average precision, and area under the precision-recall curve, respectively, compared to the SEAL.

{"title":"SEAL+: A subgraph-enhanced framework for link prediction with graph neural networks","authors":"Reyhane Karami , S. Mehdi Vahidipour , Alireza Rezvanian","doi":"10.1016/j.jii.2025.100802","DOIUrl":"10.1016/j.jii.2025.100802","url":null,"abstract":"<div><div>Link prediction is a critical research topic in network analysis, typically formulated as a classification problem where the goal is to determine whether a link exists between a pair of nodes (denoted as 1 in existence and 0 for non-existence). In most existing works, the feature vectors of a pair of nodes are combined to obtain the feature vector representing the link between them; these feature vectors (or embeddings) are constructed using graph neural networks (GNNs). This paper uses a GNN-based link prediction method called EAL as the baseline. EAL consists of an Encoder and a Decoder. A significant challenge in EAL is that the feature vector extracted by the GNN can be identical for different pairs of nodes. To address this issue, we propose leveraging the concept of subgraphs to enhance link prediction performance. To this end, the Encoder is equipped with subgraphs, forming the SEAL framework. One limitation of SEAL is that it generates identical link representations for different links when the embeddings of the nodes involved are the same. To overcome this limitation, the Decoder of SEAL also uses the subgraph information, resulting in the novel framework SEAL+. We evaluate these two frameworks against baseline methods using various metrics, demonstrating their superiority. Specifically, SEAL+ achieves average improvements of 10.25 %, 17.25 %, 3.75 %, and 4.65 % in terms of accuracy, F1-Score, average precision, and area under the precision-recall curve, respectively, compared to the SEAL.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100802"},"PeriodicalIF":10.4,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463985","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

A novel paradigm on data and knowledge-driven drug formulation development: Opportunities and challenges of machine learning

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

Journal of Industrial Information Integration

Pub Date : 2025-02-15 DOI: 10.1016/j.jii.2025.100796

Xinrui Wang , Zhenda Liu , Xiao Lin , Yanlong Hong , Lan Shen , Lijie Zhao

In the context of Industry 4.0, and Pharma 4.0, the application of machine learning (ML) is gaining growing recognition in the field of drug formulation, where the application of these technologies has the potential to significantly improve the agility, efficiency, flexibility, and quality of production in the pharmaceutical industry. Establishing control strategies that meet product performance requirements and have robust processes allows for precise quality control, enabling pharmaceutical scientists to enhance the safety and effectiveness of drug formulations. Compared to traditional prescription development, big data-based ML formulation development focuses on integrating and mining data and extracting data features to better guide the formulation design. This review starts from the perspective of big data-based ML drug formulation development processes, summarizes recent advancements in utilizing ML tools to address significant challenges, and highlights successful cases in formulation research and development. It provides a comprehensive summary and synthesis of quality control measures and process evaluation methodologies employed in ML-driven drug formulation development and manufacturing, effectively implementing the entire life-cycle of drug formulations. This review is devoted to an in-depth discussion on the Intelligence of drug formulation production and development, which is of great significance in guiding the application of efficient and safe drug formulation.

{"title":"A novel paradigm on data and knowledge-driven drug formulation development: Opportunities and challenges of machine learning","authors":"Xinrui Wang , Zhenda Liu , Xiao Lin , Yanlong Hong , Lan Shen , Lijie Zhao","doi":"10.1016/j.jii.2025.100796","DOIUrl":"10.1016/j.jii.2025.100796","url":null,"abstract":"<div><div>In the context of Industry 4.0, and Pharma 4.0, the application of machine learning (ML) is gaining growing recognition in the field of drug formulation, where the application of these technologies has the potential to significantly improve the agility, efficiency, flexibility, and quality of production in the pharmaceutical industry. Establishing control strategies that meet product performance requirements and have robust processes allows for precise quality control, enabling pharmaceutical scientists to enhance the safety and effectiveness of drug formulations. Compared to traditional prescription development, big data-based ML formulation development focuses on integrating and mining data and extracting data features to better guide the formulation design. This review starts from the perspective of big data-based ML drug formulation development processes, summarizes recent advancements in utilizing ML tools to address significant challenges, and highlights successful cases in formulation research and development. It provides a comprehensive summary and synthesis of quality control measures and process evaluation methodologies employed in ML-driven drug formulation development and manufacturing, effectively implementing the entire life-cycle of drug formulations. This review is devoted to an in-depth discussion on the Intelligence of drug formulation production and development, which is of great significance in guiding the application of efficient and safe drug formulation.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100796"},"PeriodicalIF":10.4,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437565","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

End-to-end autonomous underwater vehicle path following control method based on improved soft actor–critic for deep space exploration

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

Journal of Industrial Information Integration

Pub Date : 2025-02-15 DOI: 10.1016/j.jii.2025.100792

Na Dong , Shoufu Liu , Andrew W.H. Ip , Kai Leung Yung , Zhongke Gao , Rongshun Juan , Yanhui Wang

The vast extraterrestrial ocean is becoming a hotspot for deep space exploration of life in the future. Considering autonomous underwater vehicle (AUV) has a larger range of activities and greater flexibility, it plays an important role in extraterrestrial ocean research. To solve the problems in path following tasks of AUV, such as high training cost and poor exploration ability, an end-to-end AUV path following control method based on an improved soft actor–critic (SAC) algorithm is designed in this paper, leveraging the advancements in deep reinforcement learning (DRL) to enhance performance and efficiency. It uses sensor information to understand the environment and its state to output the policy to complete the adaptive action. Policies that consider long-term effects can be learned through continuous interaction with the environment, which is helpful in improving adaptability and enhancing the robustness of AUV control. A non-policy sampling method is designed to improve the utilization efficiency of experience transitions in the replay buffer, accelerate convergence, and enhance its stability. A reward function on the current position and heading angle of AUV is designed to avoid the situation of sparse reward leading to slow learning or ineffective learning of agents. In the meantime, we use the continuous action space instead of the discrete action space to make the real-time control of the AUV more accurate. Finally, it is tested on the gazebo simulation platform, and the results confirm that reinforcement learning is effective in AUV control, and the method proposed in this paper has faster and better following performance than traditional reinforcement learning methods.

{"title":"End-to-end autonomous underwater vehicle path following control method based on improved soft actor–critic for deep space exploration","authors":"Na Dong , Shoufu Liu , Andrew W.H. Ip , Kai Leung Yung , Zhongke Gao , Rongshun Juan , Yanhui Wang","doi":"10.1016/j.jii.2025.100792","DOIUrl":"10.1016/j.jii.2025.100792","url":null,"abstract":"<div><div>The vast extraterrestrial ocean is becoming a hotspot for deep space exploration of life in the future. Considering autonomous underwater vehicle (AUV) has a larger range of activities and greater flexibility, it plays an important role in extraterrestrial ocean research. To solve the problems in path following tasks of AUV, such as high training cost and poor exploration ability, an end-to-end AUV path following control method based on an improved soft actor–critic (SAC) algorithm is designed in this paper, leveraging the advancements in deep reinforcement learning (DRL) to enhance performance and efficiency. It uses sensor information to understand the environment and its state to output the policy to complete the adaptive action. Policies that consider long-term effects can be learned through continuous interaction with the environment, which is helpful in improving adaptability and enhancing the robustness of AUV control. A non-policy sampling method is designed to improve the utilization efficiency of experience transitions in the replay buffer, accelerate convergence, and enhance its stability. A reward function on the current position and heading angle of AUV is designed to avoid the situation of sparse reward leading to slow learning or ineffective learning of agents. In the meantime, we use the continuous action space instead of the discrete action space to make the real-time control of the AUV more accurate. Finally, it is tested on the gazebo simulation platform, and the results confirm that reinforcement learning is effective in AUV control, and the method proposed in this paper has faster and better following performance than traditional reinforcement learning methods.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100792"},"PeriodicalIF":10.4,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464105","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

Fuzzy ensemble-based federated learning for EEG-based emotion recognition in Internet of Medical Things

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

Journal of Industrial Information Integration

Pub Date : 2025-02-14 DOI: 10.1016/j.jii.2025.100789

Weiwei Jiang , Yang Zhang , Haoyu Han , Xiaozhu Liu , Jeonghwan Gwak , Weixi Gu , Achyut Shankar , Carsten Maple

Emotion recognition based on electroencephalography (EEG) is a crucial research area in the Internet of Medical Things (IoMT), with significant applications in engineering and entertainment. Addressing challenges such as efficient EEG feature extraction, accurate classification, and data privacy, this study introduces a novel fuzzy ensemble-based federated learning framework for EEG-based emotion recognition. We integrate three deep learning models, including a temporal convolutional network (TCN), long short-term memory (LSTM), and gated recurrent unit (GRU), and employ a Gompertz function-based fuzzy rank approach to combine their predictions. Additionally, we propose an asynchronous dropout algorithm within the federated learning framework to aggregate a global model, ensuring data privacy and mitigating gradient staleness. Our approach is validated using three public datasets, including GAMEEMO, SEED and DEAP, demonstrating superior performance in accuracy and F1 score compared to existing methods.

{"title":"Fuzzy ensemble-based federated learning for EEG-based emotion recognition in Internet of Medical Things","authors":"Weiwei Jiang , Yang Zhang , Haoyu Han , Xiaozhu Liu , Jeonghwan Gwak , Weixi Gu , Achyut Shankar , Carsten Maple","doi":"10.1016/j.jii.2025.100789","DOIUrl":"10.1016/j.jii.2025.100789","url":null,"abstract":"<div><div>Emotion recognition based on electroencephalography (EEG) is a crucial research area in the Internet of Medical Things (IoMT), with significant applications in engineering and entertainment. Addressing challenges such as efficient EEG feature extraction, accurate classification, and data privacy, this study introduces a novel fuzzy ensemble-based federated learning framework for EEG-based emotion recognition. We integrate three deep learning models, including a temporal convolutional network (TCN), long short-term memory (LSTM), and gated recurrent unit (GRU), and employ a Gompertz function-based fuzzy rank approach to combine their predictions. Additionally, we propose an asynchronous dropout algorithm within the federated learning framework to aggregate a global model, ensuring data privacy and mitigating gradient staleness. Our approach is validated using three public datasets, including GAMEEMO, SEED and DEAP, demonstrating superior performance in accuracy and F1 score compared to existing methods.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100789"},"PeriodicalIF":10.4,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419405","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

Unified embedded operating system for vehicle control and traffic management 用于车辆控制和交通管理的统一嵌入式操作系统

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

Journal of Industrial Information Integration

Pub Date : 2025-02-13 DOI: 10.1016/j.jii.2025.100794

Deng Pan , Jiahao Lu , Yao Li , Yuecheng Gao

Developing a unified and embedded operating system (UEOS) aims to provide services for vehicle control and traffic management. To this end, this study begins from the perspective of engineering applications to construct a mathematical model for examining key problems in vehicle-following control. This exploration extends to the behavior of individual vehicles, integrating mesoscopic and macroscopic viewpoints on traffic management. The critical need to regulate such behavior is underscored as essential for establishing a safe, efficient, and steady following state. Subsequently, we delve into state transition-based vehicle-following control and generalized control, leveraging real-time tracking of safety distance and velocity differences in vehicle velocities to establish, maintain, recover or newly reestablish a safe and efficient, and steady following state. Proposed solutions encompass identifying and managing vehicle-following relationship, along with managing vehicle information. Additionally, an agent-based model is proposed for the dynamic configuration of vehicular roles. These solutions adapt to dynamic changes in vehicle-following situation, ultimately enhancing the ability of vehicles to improve their behavior. These conceptual frameworks lay the foundation for developing the UEOS, dedicated to the control, optimization, and management of vehicle-following behaviors. We then outline a strategy that emphasizes modules closely linked to the engineering application of vehicle control and traffic management in the hardware abstraction layer and the middleware layer, paving the way for the development of the corresponding software system. When these modules become technologically mature, seamless integration into the operating system layer is envisioned. Finally, the importance of the proposed platform is highlighted and the preliminary technological route is outlined for developing the UEOS.

{"title":"Unified embedded operating system for vehicle control and traffic management","authors":"Deng Pan , Jiahao Lu , Yao Li , Yuecheng Gao","doi":"10.1016/j.jii.2025.100794","DOIUrl":"10.1016/j.jii.2025.100794","url":null,"abstract":"<div><div>Developing a unified and embedded operating system (UEOS) aims to provide services for vehicle control and traffic management. To this end, this study begins from the perspective of engineering applications to construct a mathematical model for examining key problems in vehicle-following control. This exploration extends to the behavior of individual vehicles, integrating mesoscopic and macroscopic viewpoints on traffic management. The critical need to regulate such behavior is underscored as essential for establishing a safe, efficient, and steady following state. Subsequently, we delve into state transition-based vehicle-following control and generalized control, leveraging real-time tracking of safety distance and velocity differences in vehicle velocities to establish, maintain, recover or newly reestablish a safe and efficient, and steady following state. Proposed solutions encompass identifying and managing vehicle-following relationship, along with managing vehicle information. Additionally, an agent-based model is proposed for the dynamic configuration of vehicular roles. These solutions adapt to dynamic changes in vehicle-following situation, ultimately enhancing the ability of vehicles to improve their behavior. These conceptual frameworks lay the foundation for developing the UEOS, dedicated to the control, optimization, and management of vehicle-following behaviors. We then outline a strategy that emphasizes modules closely linked to the engineering application of vehicle control and traffic management in the hardware abstraction layer and the middleware layer, paving the way for the development of the corresponding software system. When these modules become technologically mature, seamless integration into the operating system layer is envisioned. Finally, the importance of the proposed platform is highlighted and the preliminary technological route is outlined for developing the UEOS.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100794"},"PeriodicalIF":10.4,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446110","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

Design of a federated ensemble model for intrusion detection in distributed IIoT networks for enhancing cybersecurity

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

Journal of Industrial Information Integration

Pub Date : 2025-02-13 DOI: 10.1016/j.jii.2025.100800

Ayushi Chahal, Preeti Gulia, Nasib Singh Gill, Deepti Rani

Automation has become possible by the reliance of Industry 4.0 on the Internet of Things (IoT) ecosystem. IIoT brings the next phase of digital transformation, which is defined by the convergence of the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI). Industrial Internet of Things (IIoT) contributes in expansion of IoT network where large-scale data is generated continuously. Due to several security vulnerabilities in industrial information security management systems, the data can be breached by malicious attackers. Federated Learning is the best solution to address the challenge of heterogeneity and geographical locations in IIoT. This study proposes IIoT-IDFE (IIoT- Intrusion Detection Federated Ensemble) model for intrusion detection in heterogeneous IIoT environment. IIoT_IDFE model detects unwanted intrusions in two stages. In the first stage, local IIoT client devices use the Shared Local Ensemble (SLE) model to detect intrusion. In the second stage, instead of sharing actual data, the ensemble model is shared with a central federated server using the Broadcast Global Ensemble (BDE) model. By combining the advantages of ensemble and federated learning techniques, the proposed model guarantees a thorough approach to produce reliable aggregated predictions at the global scale. This allows IoT devices to maintain their privacy while improving the model's efficiency. Freely accessible industrial datasets i.e. "Edge-IIoTset" and “ToN-IoT” are used to implement the proposed intrusion detection method. Performance evaluation metrics, namely, accuracy, precision, recall, and f1-score are used to validate the performance and efficacy of the proposed IIoT-IDFE model. The performance evaluation with 99.99% to 100% accuracy confirms that the proposed model outperforms the state-of-art techniques.

{"title":"Design of a federated ensemble model for intrusion detection in distributed IIoT networks for enhancing cybersecurity","authors":"Ayushi Chahal, Preeti Gulia, Nasib Singh Gill, Deepti Rani","doi":"10.1016/j.jii.2025.100800","DOIUrl":"10.1016/j.jii.2025.100800","url":null,"abstract":"<div><div>Automation has become possible by the reliance of Industry 4.0 on the Internet of Things (IoT) ecosystem. IIoT brings the next phase of digital transformation, which is defined by the convergence of the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI). Industrial Internet of Things (IIoT) contributes in expansion of IoT network where large-scale data is generated continuously. Due to several security vulnerabilities in industrial information security management systems, the data can be breached by malicious attackers. Federated Learning is the best solution to address the challenge of heterogeneity and geographical locations in IIoT. This study proposes IIoT-IDFE (IIoT- Intrusion Detection Federated Ensemble) model for intrusion detection in heterogeneous IIoT environment. IIoT_IDFE model detects unwanted intrusions in two stages. In the first stage, local IIoT client devices use the Shared Local Ensemble (SLE) model to detect intrusion. In the second stage, instead of sharing actual data, the ensemble model is shared with a central federated server using the Broadcast Global Ensemble (BDE) model. By combining the advantages of ensemble and federated learning techniques, the proposed model guarantees a thorough approach to produce reliable aggregated predictions at the global scale. This allows IoT devices to maintain their privacy while improving the model's efficiency. Freely accessible industrial datasets i.e. \"Edge-IIoTset\" and “ToN-IoT” are used to implement the proposed intrusion detection method. Performance evaluation metrics, namely, accuracy, precision, recall, and f1-score are used to validate the performance and efficacy of the proposed IIoT-IDFE model. The performance evaluation with 99.99% to 100% accuracy confirms that the proposed model outperforms the state-of-art techniques.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100800"},"PeriodicalIF":10.4,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446109","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

Data enabling technology in digital twin and its frameworks in different industrial applications

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

Journal of Industrial Information Integration

Pub Date : 2025-02-10 DOI: 10.1016/j.jii.2025.100793

R. Mohanraj, Banda Krishna Vaishnavi

Digital twins (DT) are virtual representations of physical entities that integrate real-time data and simulation. By mirroring real-world counterparts and continuously updating based on live data, DTs allow organizations to simulate, monitor, and control processes with unprecedented precision, thus reducing costs, improving productivity, facilitating innovation and adaptability in industrial operations. Studying DT technology is critical to address the growing complexity of industrial systems and the need for more adaptable, efficient data integration of multisource, secure data enabling technologies and frameworks. The study highlighted the pivotal role of DT technology in advancing industrial digitalization, particularly within the manufacturing sector. It examined the origins, evolution, and potential applications of DTs, incorporating insights from academic and industrial perspectives. By reviewing a range of literatures, this article identifies gaps in advancing DT technology in smart manufacturing systems in terms of technical limitations hampering the implementation, emphasizing the need for more adaptable and accessible frameworks, integrating multisource data, ensuring scalability, and maintaining data security to meet the evolving demands of Industry 4.0 with better efficiency and reduce costs. The findings underscored the necessity for continued research and development to establish adaptable and robust DT technologies which provide scalable architectures, improved interoperability, and enhanced accuracy in simulations, capable of meeting the current evolving industrial demands.

{"title":"Data enabling technology in digital twin and its frameworks in different industrial applications","authors":"R. Mohanraj, Banda Krishna Vaishnavi","doi":"10.1016/j.jii.2025.100793","DOIUrl":"10.1016/j.jii.2025.100793","url":null,"abstract":"<div><div>Digital twins (DT) are virtual representations of physical entities that integrate real-time data and simulation. By mirroring real-world counterparts and continuously updating based on live data, DTs allow organizations to simulate, monitor, and control processes with unprecedented precision, thus reducing costs, improving productivity, facilitating innovation and adaptability in industrial operations. Studying DT technology is critical to address the growing complexity of industrial systems and the need for more adaptable, efficient data integration of multisource, secure data enabling technologies and frameworks. The study highlighted the pivotal role of DT technology in advancing industrial digitalization, particularly within the manufacturing sector. It examined the origins, evolution, and potential applications of DTs, incorporating insights from academic and industrial perspectives. By reviewing a range of literatures, this article identifies gaps in advancing DT technology in smart manufacturing systems in terms of technical limitations hampering the implementation, emphasizing the need for more adaptable and accessible frameworks, integrating multisource data, ensuring scalability, and maintaining data security to meet the evolving demands of Industry 4.0 with better efficiency and reduce costs. The findings underscored the necessity for continued research and development to establish adaptable and robust DT technologies which provide scalable architectures, improved interoperability, and enhanced accuracy in simulations, capable of meeting the current evolving industrial demands.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100793"},"PeriodicalIF":10.4,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395360","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

Evaluation of crawler cranes for large-scale construction and infrastructure projects: An intuitionistic fuzzy consensus-based approach

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

Journal of Industrial Information Integration

Pub Date : 2025-02-09 DOI: 10.1016/j.jii.2025.100784

Ömer Faruk Görçün , Abhijit Saha , Fatih Ecer

Choosing the proper and best crawler crane is a complicated decision-making issue due to several conflicting criteria and vagueness in the construction and project logistics industries. This decision-making problem has become compounded due to insufficient studies on crawler crane selection in the relevant literature. The current study introduces an intuitionistic fuzzy consensus-based complex proportional assessment model (IF-c-COPRAS) developed to address the existing research gaps and identify the best and most suitable crawler crane. The acquired conclusions revealed that the most potent criterion influencing the crawler crane selection is "job potential," with a weighted score of 0.7665, followed by "periodic control and inspection" and "crane model year." Once the following findings of the paper regarding crawler crane variants are evaluated, the crawler crane manufactured by Liebherr Co. is the most feasible alternative, with a relative significance score of 0.8324. These outcomes provide sensible implications and insights for practitioners and decision-makers in the construction and project logistics (overweight/oversized cargo lifting and transport firms) industries, providing an applicable guideline for improving the quality of construction operations. Additionally, crane manufacturers can consider these managerial and policy implications and insights to improve the abilities and quality of the crawler cranes they produce.

{"title":"Evaluation of crawler cranes for large-scale construction and infrastructure projects: An intuitionistic fuzzy consensus-based approach","authors":"Ömer Faruk Görçün , Abhijit Saha , Fatih Ecer","doi":"10.1016/j.jii.2025.100784","DOIUrl":"10.1016/j.jii.2025.100784","url":null,"abstract":"<div><div>Choosing the proper and best crawler crane is a complicated decision-making issue due to several conflicting criteria and vagueness in the construction and project logistics industries. This decision-making problem has become compounded due to insufficient studies on crawler crane selection in the relevant literature. The current study introduces an intuitionistic fuzzy consensus-based complex proportional assessment model (IF-c-COPRAS) developed to address the existing research gaps and identify the best and most suitable crawler crane. The acquired conclusions revealed that the most potent criterion influencing the crawler crane selection is \"job potential,\" with a weighted score of 0.7665, followed by \"periodic control and inspection\" and \"crane model year.\" Once the following findings of the paper regarding crawler crane variants are evaluated, the crawler crane manufactured by Liebherr Co. is the most feasible alternative, with a relative significance score of 0.8324. These outcomes provide sensible implications and insights for practitioners and decision-makers in the construction and project logistics (overweight/oversized cargo lifting and transport firms) industries, providing an applicable guideline for improving the quality of construction operations. Additionally, crane manufacturers can consider these managerial and policy implications and insights to improve the abilities and quality of the crawler cranes they produce.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100784"},"PeriodicalIF":10.4,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419958","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

An information integration framework toward cross-organizational management of integrated energy systems

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

Journal of Industrial Information Integration

Pub Date : 2025-02-08 DOI: 10.1016/j.jii.2025.100791

F. Babaei, R. Bozorgmehry Boozarjomehry, Z. Kheirkhah Ravandi, M.R. Pishvaie

Integrating information systems in supply chains and energy systems presents significant challenges due to diverse knowledge domains and cross-organizational processes. This study bridges the gap by employing industrial information integration engineering concepts. We propose a domain ontology framework to integrate supply chain conceptions, upon which several application-level semantic models in energy networks are developed. These ontologies, functioning as interoperable systems, enhance information sharing and data integration across strategic, tactical, and operational decision-making levels. Our proposed framework adheres to Industry 4.0 principles, offering a novel formalization of essential supply chain concepts and activities, ensuring logical consistency. This dual-level ontological approach surpasses previous models by enabling vertical and horizontal integration across supply chain hierarchies. It facilitates seamless communication between supply chain constituents, expert modelers, and software agents. Additionally, the application-level ontologies for energy networks capture various organizational operations, multi-energy vectors, demands, and conversion technologies. These semantic models reduce the knowledge management gap in integrated energy systems, aligning with Industry 4.0 objectives. Two scenarios demonstrate the framework's capabilities: virtual agents coordinate the water-energy nexus and configure integrated energy systems. Results indicate that the domain and application knowledge integration systems comprehensively cover corresponding business processes across operational hierarchies. Thus, the proposed framework supports intra- and inter-agent communications, with ontologies serving as knowledge repositories, ultimately facilitating better industrial integration.

{"title":"An information integration framework toward cross-organizational management of integrated energy systems","authors":"F. Babaei, R. Bozorgmehry Boozarjomehry, Z. Kheirkhah Ravandi, M.R. Pishvaie","doi":"10.1016/j.jii.2025.100791","DOIUrl":"10.1016/j.jii.2025.100791","url":null,"abstract":"<div><div>Integrating information systems in supply chains and energy systems presents significant challenges due to diverse knowledge domains and cross-organizational processes. This study bridges the gap by employing industrial information integration engineering concepts. We propose a domain ontology framework to integrate supply chain conceptions, upon which several application-level semantic models in energy networks are developed. These ontologies, functioning as interoperable systems, enhance information sharing and data integration across strategic, tactical, and operational decision-making levels. Our proposed framework adheres to Industry 4.0 principles, offering a novel formalization of essential supply chain concepts and activities, ensuring logical consistency. This dual-level ontological approach surpasses previous models by enabling vertical and horizontal integration across supply chain hierarchies. It facilitates seamless communication between supply chain constituents, expert modelers, and software agents. Additionally, the application-level ontologies for energy networks capture various organizational operations, multi-energy vectors, demands, and conversion technologies. These semantic models reduce the knowledge management gap in integrated energy systems, aligning with Industry 4.0 objectives. Two scenarios demonstrate the framework's capabilities: virtual agents coordinate the water-energy nexus and configure integrated energy systems. Results indicate that the domain and application knowledge integration systems comprehensively cover corresponding business processes across operational hierarchies. Thus, the proposed framework supports intra- and inter-agent communications, with ontologies serving as knowledge repositories, ultimately facilitating better industrial integration.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"44 ","pages":"Article 100791"},"PeriodicalIF":10.4,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395359","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