Journal of Industrial Information Integration最新文献_第10页

A knowledge-driven decision support architecture for sustainable supplier analysis in an infrastructure project 一个知识驱动的决策支持架构，用于基础设施项目中可持续的供应商分析

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

Journal of Industrial Information Integration

Pub Date : 2025-10-25 DOI: 10.1016/j.jii.2025.100994

Song-Shun Lin , Xin-Jiang Zheng , Zhao-Yao Bao

As supplier analysis becomes increasingly complex, there is a growing need for structured methods that support multi-dimensional evaluation under uncertainty. A knowledge-driven decision support approach (KDDSA) is proposed, leveraging entropy-based interval-valued spherical fuzzy sets to assign criteria weights. Additionally, a weighted coefficient of variation is introduced to measure consensus and account for variability in judgments, strengthening decision-making reliability. The proposed approach addresses the practical challenges of integrating multiple, often conflicting criteria in supplier analysis by incorporating economic, environmental, social, and supplier-specific dimensions, structured across sixteen indicators. To assess its practical applicability, KDDSA is applied to an infrastructure project, where uncertain assessments are integrated and processed through a multi-layered decision structure. The results highlight the critical importance of consensus building and uncertainty management for achieving reliable outcomes. By integrating heterogeneous information with advanced fuzzy modeling, the proposed approach enhances industrial information integration in complex decision-making contexts. The findings reinforce the potential of structured and information-integrated evaluation methods in enhancing supplier management within infrastructure supply chains.

随着供应商分析变得越来越复杂，越来越需要结构化的方法来支持不确定性下的多维评估。提出了一种知识驱动决策支持方法（KDDSA），利用基于熵的区间值球面模糊集来分配标准权重。此外，还引入了加权变异系数来衡量共识并考虑判断中的可变性，从而增强了决策的可靠性。提议的方法通过将经济、环境、社会和供应商特定维度结合起来，跨越16个指标，解决了在供应商分析中整合多个经常相互冲突的标准的实际挑战。为了评估其实际适用性，将KDDSA应用于基础设施项目，其中不确定性评估通过多层决策结构进行集成和处理。研究结果强调了建立共识和管理不确定性对于实现可靠结果的关键重要性。该方法将异构信息与高级模糊建模相结合，增强了复杂决策环境下的产业信息集成能力。研究结果加强了结构化和信息集成评估方法在加强基础设施供应链内供应商管理方面的潜力。

{"title":"A knowledge-driven decision support architecture for sustainable supplier analysis in an infrastructure project","authors":"Song-Shun Lin , Xin-Jiang Zheng , Zhao-Yao Bao","doi":"10.1016/j.jii.2025.100994","DOIUrl":"10.1016/j.jii.2025.100994","url":null,"abstract":"<div><div>As supplier analysis becomes increasingly complex, there is a growing need for structured methods that support multi-dimensional evaluation under uncertainty. A knowledge-driven decision support approach (KDDSA) is proposed, leveraging entropy-based interval-valued spherical fuzzy sets to assign criteria weights. Additionally, a weighted coefficient of variation is introduced to measure consensus and account for variability in judgments, strengthening decision-making reliability. The proposed approach addresses the practical challenges of integrating multiple, often conflicting criteria in supplier analysis by incorporating economic, environmental, social, and supplier-specific dimensions, structured across sixteen indicators. To assess its practical applicability, KDDSA is applied to an infrastructure project, where uncertain assessments are integrated and processed through a multi-layered decision structure. The results highlight the critical importance of consensus building and uncertainty management for achieving reliable outcomes. By integrating heterogeneous information with advanced fuzzy modeling, the proposed approach enhances industrial information integration in complex decision-making contexts. The findings reinforce the potential of structured and information-integrated evaluation methods in enhancing supplier management within infrastructure supply chains.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 100994"},"PeriodicalIF":10.4,"publicationDate":"2025-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145382969","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

Agent based web service composition using Q-learning algorithm with puffer fish optimization and petri net model 基于Agent的基于Puffer鱼优化和Petri网模型的q -学习Web服务组合

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

Journal of Industrial Information Integration

Pub Date : 2025-10-25 DOI: 10.1016/j.jii.2025.100992

Pallavi Tiwari , S. Srinivasan

The proliferation of cloud computing and web-based services has led to a significant increase in the number and complexity of online web services. As a result, discovering appropriate services that meet user requirements has become a challenging task. Traditional web services discovery techniques often lack the efficiency and adaptability needed to handle user expectations in a dynamic environment. Additionally, it may struggle with limited scalability when dealing with large service sets. This results in suboptimal service selection, reduced user satisfaction, and increased latency. To address this challenge, a user requirement-oriented web services discovery approach based on Petri Nets and optimized Reinforcement (PN-ODRL) was proposed, aimed at improving the efficiency of agent-based services composition. Initially, service composition combines several atomic services related to specific tasks to fulfill user requirements. After that, a reinforcement learning-based Q-learning approach is utilized to choose the web services required by the user. Next, the Petri Net model is used to define RL actions by creating new finite action groups. A series of transitions within each action group identifies the best services, which are then recommended to the user. Then, Puffer Fish Optimization (PFO) is utilized to tune the learning rate and discount parameter present in the Q-learning algorithm, thereby enhancing the response time, cost, and reliability of the proposed approach. Experimental result for the proposed approach has an 85 % user satisfaction rate, 9ms of service discovery efficiency, 15.3Mbps of throughput, 97 % of availability, 24.6s of computational time, 18.3s of response time, 21.3s of processing time, 12.4s of mean residence time, 68.8s of execution time, and 93 % reliability. This approach reduced the response and processing time, enabling quicker service execution. Additionally, it could enhance user satisfaction with the system.

云计算和基于web的服务的激增导致在线web服务的数量和复杂性显著增加。因此，发现满足用户需求的适当服务已成为一项具有挑战性的任务。传统的web服务发现技术通常缺乏在动态环境中处理用户期望所需的效率和适应性。此外，在处理大型服务集时，它可能会与有限的可伸缩性作斗争。这将导致次优服务选择、降低用户满意度和增加延迟。为了解决这一问题，提出了一种基于Petri网和优化强化（PN-ODRL）的面向用户需求的web服务发现方法，旨在提高基于代理的服务组合的效率。最初，服务组合将几个与特定任务相关的原子服务组合在一起，以满足用户需求。然后，利用基于强化学习的Q-learning方法来选择用户所需的web服务。接下来，Petri网模型通过创建新的有限动作组来定义RL动作。每个操作组中的一系列转换确定最佳服务，然后将其推荐给用户。然后，利用河豚鱼优化（PFO）来调整q -学习算法中的学习率和折扣参数，从而提高了所提出方法的响应时间、成本和可靠性。实验结果表明，该方法的用户满意度为85%，服务发现效率为9ms，吞吐量为15.3Mbps，可用性为97%，计算时间为24.6s，响应时间为18.3s，处理时间为21.3s，平均停留时间为12.4s，执行时间为68.8s，可靠性为93%。这种方法减少了响应和处理时间，支持更快的服务执行。此外，它可以提高用户对系统的满意度。

{"title":"Agent based web service composition using Q-learning algorithm with puffer fish optimization and petri net model","authors":"Pallavi Tiwari , S. Srinivasan","doi":"10.1016/j.jii.2025.100992","DOIUrl":"10.1016/j.jii.2025.100992","url":null,"abstract":"<div><div>The proliferation of cloud computing and web-based services has led to a significant increase in the number and complexity of online web services. As a result, discovering appropriate services that meet user requirements has become a challenging task. Traditional web services discovery techniques often lack the efficiency and adaptability needed to handle user expectations in a dynamic environment. Additionally, it may struggle with limited scalability when dealing with large service sets. This results in suboptimal service selection, reduced user satisfaction, and increased latency. To address this challenge, a user requirement-oriented web services discovery approach based on Petri Nets and optimized Reinforcement (PN-ODRL) was proposed, aimed at improving the efficiency of agent-based services composition. Initially, service composition combines several atomic services related to specific tasks to fulfill user requirements. After that, a reinforcement learning-based Q-learning approach is utilized to choose the web services required by the user. Next, the Petri Net model is used to define RL actions by creating new finite action groups. A series of transitions within each action group identifies the best services, which are then recommended to the user. Then, Puffer Fish Optimization (PFO) is utilized to tune the learning rate and discount parameter present in the Q-learning algorithm, thereby enhancing the response time, cost, and reliability of the proposed approach. Experimental result for the proposed approach has an 85 % user satisfaction rate, 9ms of service discovery efficiency, 15.3Mbps of throughput, 97 % of availability, 24.6s of computational time, 18.3s of response time, 21.3s of processing time, 12.4s of mean residence time, 68.8s of execution time, and 93 % reliability. This approach reduced the response and processing time, enabling quicker service execution. Additionally, it could enhance user satisfaction with the system.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"49 ","pages":"Article 100992"},"PeriodicalIF":10.4,"publicationDate":"2025-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145383857","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

Implicit dimension measurement for automated cross-sectional inspection of multi-lumen medical catheters 多腔医用导管自动横断检测的隐式尺寸测量

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

Journal of Industrial Information Integration

Pub Date : 2025-10-24 DOI: 10.1016/j.jii.2025.100979

WooSang Shin , Jonghyeon Lee , Dong Yun Choi , Iljeok Kim , JongPil Yun

Ensuring the cross-sectional shape integrity of medical catheters is a necessity for their safe and effective clinical functionality. Although visual inspection technologies have advanced rapidly, automated inspection of catheter tubes remains challenging due to the complex, deformable structures resulting from extrusion processes and the inherent properties of the materials. In this study, we introduce the Implicit Dimension Measurement (IDiM) framework, which combines rule-based expertise with a data-driven Endpoint Alignment Model (EAM). By parameterizing cross-sectional dimensions using carefully defined endpoints and reference points, IDiM robustly infers key geometric features—even under moderate deformations. We validate its measurement accuracy on multi-lumen catheters (2-, 3-, and 4-lumen) through a high-resolution imaging setup deployed on an actual production line. Experimental results demonstrate measurement precision within five pixels of inter-annotator deviation, comparable to that of human inspectors, along with reliable detection of severe deformation cases via an anomaly detection approach. These findings highlight the practical feasibility of IDiM for high-fidelity shape inspection in medical manufacturing and suggest its broader applicability to other industries requiring precise dimensional verification.

保证医用导管的截面形状完整是保证其安全有效的临床功能的必要条件。尽管目视检测技术发展迅速，但由于导管的挤压过程和材料的固有特性导致其结构复杂、易变形，因此对导管的自动检测仍然具有挑战性。在本研究中，我们引入了隐式维度测量（IDiM）框架，该框架结合了基于规则的专业知识和数据驱动的端点对齐模型（EAM）。通过使用精心定义的端点和参考点参数化截面尺寸，即使在适度变形的情况下，IDiM也能可靠地推断出关键的几何特征。我们通过部署在实际生产线上的高分辨率成像设置验证了其在多流明导管（2流明、3流明和4流明）上的测量精度。实验结果表明，在注释器间偏差的5个像素内的测量精度与人类检查员相当，并且通过异常检测方法可靠地检测严重变形情况。这些发现突出了IDiM在医疗制造中进行高保真形状检测的实际可行性，并表明其在其他需要精确尺寸验证的行业中具有更广泛的适用性。

{"title":"Implicit dimension measurement for automated cross-sectional inspection of multi-lumen medical catheters","authors":"WooSang Shin , Jonghyeon Lee , Dong Yun Choi , Iljeok Kim , JongPil Yun","doi":"10.1016/j.jii.2025.100979","DOIUrl":"10.1016/j.jii.2025.100979","url":null,"abstract":"<div><div>Ensuring the cross-sectional shape integrity of medical catheters is a necessity for their safe and effective clinical functionality. Although visual inspection technologies have advanced rapidly, automated inspection of catheter tubes remains challenging due to the complex, deformable structures resulting from extrusion processes and the inherent properties of the materials. In this study, we introduce the Implicit Dimension Measurement (IDiM) framework, which combines rule-based expertise with a data-driven Endpoint Alignment Model (EAM). By parameterizing cross-sectional dimensions using carefully defined endpoints and reference points, IDiM robustly infers key geometric features—even under moderate deformations. We validate its measurement accuracy on multi-lumen catheters (2-, 3-, and 4-lumen) through a high-resolution imaging setup deployed on an actual production line. Experimental results demonstrate measurement precision within five pixels of inter-annotator deviation, comparable to that of human inspectors, along with reliable detection of severe deformation cases via an anomaly detection approach. These findings highlight the practical feasibility of IDiM for high-fidelity shape inspection in medical manufacturing and suggest its broader applicability to other industries requiring precise dimensional verification.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100979"},"PeriodicalIF":10.4,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362795","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

Leakage localization methodology based on time difference of arrival of sound wave for subsea manifold 基于声波到达时差的水下管汇泄漏定位方法

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

Journal of Industrial Information Integration

Pub Date : 2025-10-21 DOI: 10.1016/j.jii.2025.100982

Yi Jiang , Baoping Cai , Xuelin Liu , Guowei Ji , Yixin Zhao , Qingping Li , Lei Gao , Kaizheng Wu

Leakage is the main form of failure and safety hazard for a subsea manifold. Timely acquisition of leakage location information is the guarantee for safe subsea oil and gas transportation. The threshold detection and localization method is an important means of identifying the position of subsea leakages and is also one of the few applicable solutions. However, the fixed threshold leads to large errors in identifying leakage moments, resulting in significant time difference errors. In addition, environmental noise causes rapid attenuation of leakage sound signals, making it difficult to reduce noise. To overcome these problems, a three-dimensional localization framework for leakage sound sources is integrated using the time-difference-of-arrival of the sound wave from the hydrophone array. The combination of a polynomial regression model and the double threshold detection method is used to obtain the arrival time difference. This integrated framework greatly reduces the error of time difference. A spectral subtraction technique optimized with standardized parameters is employed to effectively reduce hydroacoustic signal noise. A simulated prototype of a subsea manifold was used to study the performance of this integrated framework. The results indicate that the integrated framework effectively reduces subsea noise and time difference errors.

泄漏是水下管汇失效和安全隐患的主要形式。及时获取泄漏位置信息是海底油气安全运输的保证。阈值检测与定位方法是识别海底泄漏位置的重要手段，也是为数不多的适用解决方案之一。但是，固定的阈值导致泄漏矩识别误差较大，导致时间差误差较大。此外，环境噪声使泄漏声信号衰减迅速，降低噪声难度较大。为了克服这些问题，利用水听器阵列的声波到达时间差集成了泄漏声源的三维定位框架。采用多项式回归模型与双阈值检测法相结合的方法获得到达时间差。这种集成框架大大降低了时差误差。采用标准化参数优化的谱减技术，有效地降低了水声信号噪声。采用海底歧管的模拟原型来研究该集成框架的性能。结果表明，集成框架能有效降低水下噪声和时差误差。

{"title":"Leakage localization methodology based on time difference of arrival of sound wave for subsea manifold","authors":"Yi Jiang , Baoping Cai , Xuelin Liu , Guowei Ji , Yixin Zhao , Qingping Li , Lei Gao , Kaizheng Wu","doi":"10.1016/j.jii.2025.100982","DOIUrl":"10.1016/j.jii.2025.100982","url":null,"abstract":"<div><div>Leakage is the main form of failure and safety hazard for a subsea manifold. Timely acquisition of leakage location information is the guarantee for safe subsea oil and gas transportation. The threshold detection and localization method is an important means of identifying the position of subsea leakages and is also one of the few applicable solutions. However, the fixed threshold leads to large errors in identifying leakage moments, resulting in significant time difference errors. In addition, environmental noise causes rapid attenuation of leakage sound signals, making it difficult to reduce noise. To overcome these problems, a three-dimensional localization framework for leakage sound sources is integrated using the time-difference-of-arrival of the sound wave from the hydrophone array. The combination of a polynomial regression model and the double threshold detection method is used to obtain the arrival time difference. This integrated framework greatly reduces the error of time difference. A spectral subtraction technique optimized with standardized parameters is employed to effectively reduce hydroacoustic signal noise. A simulated prototype of a subsea manifold was used to study the performance of this integrated framework. The results indicate that the integrated framework effectively reduces subsea noise and time difference errors.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100982"},"PeriodicalIF":10.4,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362799","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 hybrid HEART framework integrating EPC identification model and extended Z-polar coordinate for HRA: An application of robot-assisted rehabilitation 集成EPC识别模型和扩展z极坐标的HRA混合HEART框架：在机器人辅助康复中的应用

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

Journal of Industrial Information Integration

Pub Date : 2025-10-19 DOI: 10.1016/j.jii.2025.100981

Duojin Wang , Yue Dong , Mingyue Zhou , Xin Li

Amidst growing demands for rehabilitation, robot-assisted therapy has rapidly evolved as a crucial treatment modality. Despite its potential to enhance outcomes and efficiency, increased adverse events due to human errors remains a significant challenge. To address this issue, we present a novel hybrid Human Error Assessment and Reduction Technique (HEART) that integrates the SHELL model, extended Z-polar coordinate (E-ZPC), and the Decision-Making Trial and Evaluation Laboratory (DEMATEL) to enhance system reliability in robot-assisted rehabilitation. SHELL model is used to comprehensively identify and analyze error-producing conditions (EPCs) across diverse domains. Expert weight allocation is taken into consideration. The integration of ZPC facilitates the management of uncertainty and enhances the credibility of expert assessments, which are further refined with the innovative ZPC-PA operator that combines Z-numbers with the Power Average (PA) operator for robust data aggregation. Two case studies demonstrate the effectiveness and generalizability of the proposed method, and a comparative analysis confirms its advantage in mitigating result errors. Sensibility analysis validates the robustness of our approach. This research aims to enhance the safety and effectiveness of robot-assisted rehabilitation, thereby facilitating better outcomes for patients and advancing the reliability research in this evolving field.

在日益增长的康复需求中，机器人辅助治疗已迅速发展成为一种关键的治疗方式。尽管它有可能提高结果和效率，但由于人为错误导致的不良事件增加仍然是一个重大挑战。为了解决这一问题，我们提出了一种新的混合人为错误评估和减少技术（HEART），该技术集成了SHELL模型、扩展z极坐标（E-ZPC）和决策试验和评估实验室（DEMATEL），以提高机器人辅助康复系统的可靠性。壳牌模型用于综合识别和分析不同领域的产错条件（epc）。考虑了专家权重分配。ZPC的集成简化了不确定性管理，提高了专家评估的可信度，创新的ZPC-PA算子将z数与功率平均（PA）算子相结合，进一步完善了不确定性管理。两个算例验证了该方法的有效性和可泛化性，对比分析证实了该方法在减小结果误差方面的优势。敏感性分析验证了我们方法的稳健性。本研究旨在提高机器人辅助康复的安全性和有效性，从而为患者提供更好的治疗效果，并推进这一不断发展的领域的可靠性研究。

{"title":"A hybrid HEART framework integrating EPC identification model and extended Z-polar coordinate for HRA: An application of robot-assisted rehabilitation","authors":"Duojin Wang , Yue Dong , Mingyue Zhou , Xin Li","doi":"10.1016/j.jii.2025.100981","DOIUrl":"10.1016/j.jii.2025.100981","url":null,"abstract":"<div><div>Amidst growing demands for rehabilitation, robot-assisted therapy has rapidly evolved as a crucial treatment modality. Despite its potential to enhance outcomes and efficiency, increased adverse events due to human errors remains a significant challenge. To address this issue, we present a novel hybrid Human Error Assessment and Reduction Technique (HEART) that integrates the SHELL model, extended Z-polar coordinate (E-ZPC), and the Decision-Making Trial and Evaluation Laboratory (DEMATEL) to enhance system reliability in robot-assisted rehabilitation. SHELL model is used to comprehensively identify and analyze error-producing conditions (EPCs) across diverse domains. Expert weight allocation is taken into consideration. The integration of ZPC facilitates the management of uncertainty and enhances the credibility of expert assessments, which are further refined with the innovative ZPC-PA operator that combines Z-numbers with the Power Average (PA) operator for robust data aggregation. Two case studies demonstrate the effectiveness and generalizability of the proposed method, and a comparative analysis confirms its advantage in mitigating result errors. Sensibility analysis validates the robustness of our approach. This research aims to enhance the safety and effectiveness of robot-assisted rehabilitation, thereby facilitating better outcomes for patients and advancing the reliability research in this evolving field.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100981"},"PeriodicalIF":10.4,"publicationDate":"2025-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362798","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

Surfing twin transition in agri-food supply chains: The role of iot and data analytics in sustainable decision-making 农业食品供应链的双重转型：物联网和数据分析在可持续决策中的作用

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

Journal of Industrial Information Integration

Pub Date : 2025-10-18 DOI: 10.1016/j.jii.2025.100983

Maria Elena Latino, Marta Menegoli, Angelo Corallo, Maria Grazia Gnoni

The agri-food industry faces complex challenges that impact operational efficiency, profitability, and the ability to meet evolving consumer expectations for transparency and sustainability. Industry 4.0 technologies, particularly the Internet of Things and data analytics, offer substantial potential to enhance performance and support sustainability goals across the supply chain. This study investigates the application of Internet of Things and analytics through a multiple case study approach, illustrating how agri-food companies can transform operational and product data into actionable insights to inform decision-making and implement effective sustainability practices. The research adopts a four-phase methodology - Digitalization & Sustainability Case stud* Guideline- identifying market needs, mapping product information, elaborating data analysis, and collecting stakeholder feedback, thus providing a replicable guideline for conducting case studies in the intersection of digitalization and sustainability. A practical roadmap is presented for leveraging technological assets to generate meaningful sustainability indicators and rankings, supporting both operational managers and end consumers in accessing transparent, data-driven information. The study contributes to theory by advancing methodological rigor in multiple case studies and highlighting how data integration facilitates sustainable decision-making in agri-food supply chains. Practically, it offers actionable insights for managers aiming to enhance operational efficiency, improve communication of sustainability performance, and build consumer trust. The findings underscore the value of Internet of Things and analytics in enabling data-driven innovation and supporting future research on generalizing these approaches across diverse agri-food contexts.

农业食品行业面临着复杂的挑战，这些挑战影响着运营效率、盈利能力以及满足消费者对透明度和可持续性不断变化的期望的能力。工业4.0技术，特别是物联网和数据分析，为提高整个供应链的绩效和支持可持续发展目标提供了巨大的潜力。本研究通过多案例研究的方法研究了物联网和分析的应用，说明了农业食品公司如何将运营和产品数据转化为可操作的见解，为决策提供信息并实施有效的可持续性实践。本研究采用四阶段方法——数字化与可持续发展案例研究指南——确定市场需求，绘制产品信息，详细分析数据，收集利益相关者反馈，从而为在数字化与可持续发展的交叉领域进行案例研究提供可复制的指南。本文提出了一个实用的路线图，用于利用技术资产生成有意义的可持续性指标和排名，支持运营经理和最终消费者访问透明的、数据驱动的信息。该研究通过在多个案例研究中推进方法的严谨性，并强调数据集成如何促进农业食品供应链中的可持续决策，从而为理论做出贡献。实际上，它为管理者提供了可操作的见解，旨在提高运营效率，改善可持续发展绩效的沟通，并建立消费者信任。研究结果强调了物联网和分析在实现数据驱动创新方面的价值，并支持未来在不同农业食品环境中推广这些方法的研究。

{"title":"Surfing twin transition in agri-food supply chains: The role of iot and data analytics in sustainable decision-making","authors":"Maria Elena Latino, Marta Menegoli, Angelo Corallo, Maria Grazia Gnoni","doi":"10.1016/j.jii.2025.100983","DOIUrl":"10.1016/j.jii.2025.100983","url":null,"abstract":"<div><div>The agri-food industry faces complex challenges that impact operational efficiency, profitability, and the ability to meet evolving consumer expectations for transparency and sustainability. Industry 4.0 technologies, particularly the Internet of Things and data analytics, offer substantial potential to enhance performance and support sustainability goals across the supply chain. This study investigates the application of Internet of Things and analytics through a multiple case study approach, illustrating how agri-food companies can transform operational and product data into actionable insights to inform decision-making and implement effective sustainability practices. The research adopts a four-phase methodology - <em>Digitalization & Sustainability Case stud* Guideline</em>- identifying market needs, mapping product information, elaborating data analysis, and collecting stakeholder feedback, thus providing a replicable guideline for conducting case studies in the intersection of digitalization and sustainability. A practical roadmap is presented for leveraging technological assets to generate meaningful sustainability indicators and rankings, supporting both operational managers and end consumers in accessing transparent, data-driven information. The study contributes to theory by advancing methodological rigor in multiple case studies and highlighting how data integration facilitates sustainable decision-making in agri-food supply chains. Practically, it offers actionable insights for managers aiming to enhance operational efficiency, improve communication of sustainability performance, and build consumer trust. The findings underscore the value of Internet of Things and analytics in enabling data-driven innovation and supporting future research on generalizing these approaches across diverse agri-food contexts.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100983"},"PeriodicalIF":10.4,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362797","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 ontology-based digital thread framework to support early concurrent engineering in the aerospace industry 一种支持航空航天工业早期并发工程的基于本体的数字线程框架

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

Journal of Industrial Information Integration

Pub Date : 2025-10-18 DOI: 10.1016/j.jii.2025.100984

Eliott Duverger , Alexis Aubry , Rebeca Arista , Eric Levrat

The increasing complexity of the aerospace industry has highlighted the need to anticipate issues from the entire lifecycle of aircrafts. Identified too late, issues originating from the manufacturing or the maintenance phases can have considerable consequences on the overall development costs, time and quality of aircraft development. Concurrent Engineering (CE) is an approach that aims to improve the design process of a system by considering all lifecycle phases from the initial conceptualization. However, this way of working demands a high degree of collaboration and extensive knowledge sharing among the involved stakeholders. The digitization of the industry has provided new opportunities addressing such challenges. Approaches based on Model-Based Systems Engineering (MBSE), Knowledge-Based Engineering (KBE) and Artificial Intelligence (AI) are providing compelling ways to foster cross-domain collaboration while incorporating knowledge supporting design decisions. This paper leverages an ontology-based digital thread framework as a bridge between aircraft and manufacturing engineering activities. With enriched insights and global perspectives, this framework aims to enable early cross-domain trade-offs analysis to support knowledge-driven concurrent and collaborative engineering during the conceptual design phase.

航空航天业日益复杂，这凸显了从飞机的整个生命周期预测问题的必要性。由于发现得太晚，制造或维护阶段产生的问题可能会对飞机开发的总体成本、时间和质量产生相当大的影响。并行工程（CE）是一种旨在通过考虑从初始概念化开始的所有生命周期阶段来改进系统设计过程的方法。然而，这种工作方式需要参与的利益相关者之间的高度协作和广泛的知识共享。行业的数字化为应对这些挑战提供了新的机遇。基于模型的系统工程（MBSE）、基于知识的工程（KBE）和人工智能（AI）的方法提供了令人信服的方法来促进跨领域协作，同时结合支持设计决策的知识。本文利用基于本体的数字线程框架作为飞机和制造工程活动之间的桥梁。通过丰富的洞察力和全局视角，该框架旨在支持早期的跨领域权衡分析，从而在概念设计阶段支持知识驱动的并发和协作工程。

{"title":"An ontology-based digital thread framework to support early concurrent engineering in the aerospace industry","authors":"Eliott Duverger , Alexis Aubry , Rebeca Arista , Eric Levrat","doi":"10.1016/j.jii.2025.100984","DOIUrl":"10.1016/j.jii.2025.100984","url":null,"abstract":"<div><div>The increasing complexity of the aerospace industry has highlighted the need to anticipate issues from the entire lifecycle of aircrafts. Identified too late, issues originating from the manufacturing or the maintenance phases can have considerable consequences on the overall development costs, time and quality of aircraft development. Concurrent Engineering (CE) is an approach that aims to improve the design process of a system by considering all lifecycle phases from the initial conceptualization. However, this way of working demands a high degree of collaboration and extensive knowledge sharing among the involved stakeholders. The digitization of the industry has provided new opportunities addressing such challenges. Approaches based on Model-Based Systems Engineering (MBSE), Knowledge-Based Engineering (KBE) and Artificial Intelligence (AI) are providing compelling ways to foster cross-domain collaboration while incorporating knowledge supporting design decisions. This paper leverages an ontology-based digital thread framework as a bridge between aircraft and manufacturing engineering activities. With enriched insights and global perspectives, this framework aims to enable early cross-domain trade-offs analysis to support knowledge-driven concurrent and collaborative engineering during the conceptual design phase.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100984"},"PeriodicalIF":10.4,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362789","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

Enhancing precision in window to the brain modeling: Methodology and implementation of hybrid digital twins 提高窗口对大脑建模的精度：混合数字孪生的方法和实现

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

Journal of Industrial Information Integration

Pub Date : 2025-10-16 DOI: 10.1016/j.jii.2025.100973

Marcos Llamazares López , Macarena Trujillo Guillén , Juan-Carlos Cortés , Rafael-J. Villanueva

The Window to the Brain (WttB) is a novel cranial implant designed to enhance therapeutic procedures involving brain tissue. Previous computational models studying the effectiveness of the WttB exhibited some discrepancies with experimental results and inconsistencies in certain parameter values. To overcome these drawbacks, the following steps are followed. We first perform a domain reduction where the model is solved via the finite element method. Then, model parameters are calibrated using asynchronous random Particle Swarm Optimization (arPSO) algorithm. A statistical identifiability analysis is performed to evaluate how accurately model parameters are estimated based on the quantity and quality of experimental data. Afterward, we implement Hybrid Digital Twins (HDT) using Grammatical Evolution and Lexicase Selection to improve the model fitting keeping the model complexity. The outcomes demonstrate a complete alignment between experimental and computational results, as well as reasonable values for all model parameters. The final optimized model achieved a mean absolute error of 0.1871, with a standard deviation of 0.0013 and a 95% confidence interval (CI) of [0.1866, 0.1876], indicating a very low residual error and high stability across simulations. Our computational approach enhances the results from previous studies, which can be more useful for improving clinical practice.

脑窗（WttB）是一种新型颅骨植入物，旨在加强涉及脑组织的治疗程序。以往研究WttB有效性的计算模型与实验结果存在一定的差异，在某些参数值上也存在不一致性。要克服这些缺点，需要遵循以下步骤。我们首先执行一个域约简，其中模型通过有限元方法求解。然后，采用异步随机粒子群优化（arPSO）算法对模型参数进行标定。进行统计可识别性分析，以评估基于实验数据的数量和质量估计模型参数的准确性。然后，我们使用语法进化和词法选择来实现混合数字双胞胎（HDT），以提高模型拟合，保持模型的复杂性。结果表明，实验结果与计算结果完全一致，所有模型参数的值都是合理的。最终优化模型的平均绝对误差为0.1871，标准差为0.0013,95%置信区间（CI）为[0.1866,0.1876]，表明残差非常低，跨模拟的稳定性很高。我们的计算方法增强了先前研究的结果，这对改善临床实践更有用。

{"title":"Enhancing precision in window to the brain modeling: Methodology and implementation of hybrid digital twins","authors":"Marcos Llamazares López , Macarena Trujillo Guillén , Juan-Carlos Cortés , Rafael-J. Villanueva","doi":"10.1016/j.jii.2025.100973","DOIUrl":"10.1016/j.jii.2025.100973","url":null,"abstract":"<div><div>The Window to the Brain (WttB) is a novel cranial implant designed to enhance therapeutic procedures involving brain tissue. Previous computational models studying the effectiveness of the WttB exhibited some discrepancies with experimental results and inconsistencies in certain parameter values. To overcome these drawbacks, the following steps are followed. We first perform a domain reduction where the model is solved via the finite element method. Then, model parameters are calibrated using asynchronous random Particle Swarm Optimization (arPSO) algorithm. A statistical identifiability analysis is performed to evaluate how accurately model parameters are estimated based on the quantity and quality of experimental data. Afterward, we implement Hybrid Digital Twins (HDT) using Grammatical Evolution and Lexicase Selection to improve the model fitting keeping the model complexity. The outcomes demonstrate a complete alignment between experimental and computational results, as well as reasonable values for all model parameters. The final optimized model achieved a mean absolute error of 0.1871, with a standard deviation of 0.0013 and a 95% confidence interval (CI) of [0.1866, 0.1876], indicating a very low residual error and high stability across simulations. Our computational approach enhances the results from previous studies, which can be more useful for improving clinical practice.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100973"},"PeriodicalIF":10.4,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315004","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

AI-based cybersecurity for a sustainable digital industry: Systematic literature review and future research directions 基于人工智能的可持续数字产业网络安全：系统文献综述及未来研究方向

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

Journal of Industrial Information Integration

Pub Date : 2025-10-15 DOI: 10.1016/j.jii.2025.100980

Marianna Lezzi, Pierluigi Montefusco, Mariangela Lazoi, Angelo Corallo

The adoption of artificial intelligence (AI) to ensure sustainable cybersecurity practices is a major challenge in the era of Industry 4.0. AI techniques can classify and detect the huge number of cyber-attacks affecting modern industrial systems due to their adaptability and predictability, offering speed of classification, discovery of hidden patterns, and increased accuracy. However, the current literature shows a significant gap in analysing the relationship between AI-based cyber risk assessment and sustainability pillars (i.e., economic, social, and environmental) in modern industrial contexts. To fill this gap, this study explores the opportunities that AI techniques applied to cyber risk assessment can offer in terms of sustainability in the context of Industrial Internet of Things (IIoT). Specifically, a Systematic Literature Review (SLR) is conducted for the purpose of exploring the following four areas: (i) the definitions of sustainable cybersecurity and green cybersecurity in the industrial context; (ii) the AI techniques adopted for risk assessment, from a sustainability perspective; (iii) the industries involved; and (iv) the sustainability benefits of implementing AI technologies for cyber risk assessment. Following this analysis, an original tabular outline is created and validated by domain experts. It brings together evidence from the literature to facilitate understanding of the interplay between sustainability and cybersecurity and highlight the contribution that AI can bring not only to cyber risk assessment, but also to sustainability pillars, laying the groundwork for interesting future research directions.

采用人工智能（AI）来确保可持续的网络安全实践是工业4.0时代的主要挑战。由于其适应性和可预测性，人工智能技术可以分类和检测影响现代工业系统的大量网络攻击，提供分类速度，发现隐藏模式和提高准确性。然而，目前的文献显示，在分析现代工业背景下基于人工智能的网络风险评估与可持续性支柱（即经济、社会和环境）之间的关系方面存在重大差距。为了填补这一空白，本研究探讨了应用于网络风险评估的人工智能技术在工业物联网（IIoT）背景下的可持续性方面可以提供的机会。具体而言，本文进行了系统文献综述（SLR），旨在探索以下四个领域：(i)产业背景下可持续网络安全和绿色网络安全的定义；（ii）从可持续性角度进行风险评估所采用的人工智能技术；（三）涉及的行业；（iv）在网络风险评估中实施人工智能技术的可持续性效益。在此分析之后，将创建原始的表格大纲，并由领域专家进行验证。它汇集了文献中的证据，以促进对可持续性与网络安全之间相互作用的理解，并强调人工智能不仅可以为网络风险评估带来贡献，还可以为可持续性支柱带来贡献，为未来有趣的研究方向奠定基础。

{"title":"AI-based cybersecurity for a sustainable digital industry: Systematic literature review and future research directions","authors":"Marianna Lezzi, Pierluigi Montefusco, Mariangela Lazoi, Angelo Corallo","doi":"10.1016/j.jii.2025.100980","DOIUrl":"10.1016/j.jii.2025.100980","url":null,"abstract":"<div><div>The adoption of artificial intelligence (AI) to ensure sustainable cybersecurity practices is a major challenge in the era of Industry 4.0. AI techniques can classify and detect the huge number of cyber-attacks affecting modern industrial systems due to their adaptability and predictability, offering speed of classification, discovery of hidden patterns, and increased accuracy. However, the current literature shows a significant gap in analysing the relationship between AI-based cyber risk assessment and sustainability pillars (i.e., economic, social, and environmental) in modern industrial contexts. To fill this gap, this study explores the opportunities that AI techniques applied to cyber risk assessment can offer in terms of sustainability in the context of Industrial Internet of Things (IIoT). Specifically, a Systematic Literature Review (SLR) is conducted for the purpose of exploring the following four areas: (i) the definitions of sustainable cybersecurity and green cybersecurity in the industrial context; (ii) the AI techniques adopted for risk assessment, from a sustainability perspective; (iii) the industries involved; and (iv) the sustainability benefits of implementing AI technologies for cyber risk assessment. Following this analysis, an original tabular outline is created and validated by domain experts. It brings together evidence from the literature to facilitate understanding of the interplay between sustainability and cybersecurity and highlight the contribution that AI can bring not only to cyber risk assessment, but also to sustainability pillars, laying the groundwork for interesting future research directions.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100980"},"PeriodicalIF":10.4,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362791","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

Region-Aware Guidance Training for pipeline segmentation in complex outdoor industrial environments 复杂户外工业环境下管道分割的区域感知指导训练

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

Journal of Industrial Information Integration

Pub Date : 2025-10-15 DOI: 10.1016/j.jii.2025.100978

P. Mentesidis, V. Mygdalis, I. Pitas

Accurate segmentation of insulated pipelines is essential for automated inspection and structural analysis in complex industrial environments. While UAV-based visual inspection is increasingly adopted, current systems often struggle with cluttered scenes and rely heavily on manual interpretation. This paper proposes Region-Aware Guidance Training (RAGT) for pipeline segmentation, a novel and modular deep neural network (DNN) training framework designed to enhance the performance and deployment readiness of state-of-the-art (SOTA) real-time region segmentation models in cluttered industrial settings. RAGT integrates two complementary components: Region-Augmented Knowledge Distillation (RAKD), which guides the model to focus on task-relevant regions, and Background-Aware Augmentation (BAUG), which improves generalization by increasing background diversity during training. Both modules can operate independently or jointly within the unified RAGT framework. Experiments demonstrate that RAGT achieves improvements of up to 8 units in challenging segmentation tasks.

在复杂的工业环境中，绝缘管道的精确分割对于自动化检测和结构分析至关重要。虽然越来越多地采用基于无人机的视觉检测，但目前的系统往往难以处理杂乱的场景，并且严重依赖人工解释。本文提出了用于管道分割的区域感知制导训练（RAGT），这是一种新颖的模块化深度神经网络（DNN）训练框架，旨在提高最先进（SOTA）实时区域分割模型在混乱工业环境中的性能和部署准备程度。RAGT集成了两个互补的组件：区域增强知识蒸馏（RAKD）和背景感知增强（BAUG），前者引导模型关注任务相关区域，后者通过增加训练过程中的背景多样性来提高泛化能力。两个模块可以独立运行，也可以在统一的RAGT框架内联合运行。实验表明，RAGT在具有挑战性的分割任务中实现了高达8个单位的改进。

引用次数: 0