Search Results (105)

Modern vehicles are rapidly transforming into interconnected cyber–physical systems that rely on advanced sensor technologies and pervasive connectivity to support autonomous functionality. Yet, despite this evolution, standardized methods for quantifying cybersecurity vulnerabilities across critical automotive components remain scarce. This paper introduces a novel hybrid model that integrates expert-driven insights with generative AI tools to adapt and extend the Common Vulnerability Scoring System (CVSS) specifically for autonomous vehicle sensor systems. Following a three-phase methodology, the study conducted a systematic review of 16 peer-reviewed sources (2018–2024), applied CVSS version 4.0 scoring to 15 representative attack types, and evaluated four free source generative AI models—ChatGPT, DeepSeek, Gemini, and Copilot—on a dataset of 117 annotated automotive-related vulnerabilities. Expert validation from 10 domain professionals reveals that Light Detection and Ranging (LiDAR) sensors are the most vulnerable (9 distinct attack types), followed by Radio Detection And Ranging (radar) (8) and ultrasonic (6). Network-based attacks dominate (104 of 117 cases), with 92.3% of the dataset exhibiting low attack complexity and 82.9% requiring no user interaction. The most severe attack vectors, as scored by experts using CVSS, include eavesdropping (7.19), Sybil attacks (6.76), and replay attacks (6.35). Evaluation of large language models (LLMs) showed that DeepSeek achieved an F1 score of 99.07% on network-based attacks, while all models struggled with minority classes such as high complexity (e.g., ChatGPT F1 = 0%, Gemini F1 = 15.38%). The findings highlight the potential of integrating expert insight with AI efficiency to deliver more scalable and accurate vulnerability assessments for modern vehicular systems.This study offers actionable insights for vehicle manufacturers and cybersecurity practitioners, aiming to inform strategic efforts to fortify sensor integrity, optimize network resilience, and ultimately enhance the cybersecurity posture of next-generation autonomous vehicles. Full article

The evolution of Industry 4.0 and the emerging paradigm of Industry 5.0 have introduced disruptive technologies that are reshaping modern manufacturing environments. Among these, Digital Twin (DT) and Industrial Metaverse (IM) technologies are increasingly recognized for their potential to enhance Occupational Health and Safety (OHS). However, a comprehensive understanding of how these technologies integrate to support OHS in manufacturing remains limited. This study systematically explores the transformative role of DT and IM in creating immersive, intelligent, and human-centric safety ecosystems. Following the PRISMA guidelines, a Systematic Literature Review (SLR) of 75 peer-reviewed studies from the SCOPUS and Web of Science databases was conducted. The review identifies key enabling technologies such as Virtual Reality (VR), Augmented Reality (AR), Extended Reality (XR), Internet of Things (IoT), Artificial Intelligence (AI), Cyber-Physical Systems (CPS), and Collaborative Robots (COBOTS), and highlights their applications in real-time monitoring, immersive safety training, and predictive hazard mitigation. A conceptual framework is proposed, illustrating a synergistic digital ecosystem that integrates predictive analytics, real-time monitoring, and immersive training to enhance the OHS. The findings highlight both the transformative benefits and the key adoption challenges of these technologies, including technical complexities, data security, privacy, ethical concerns, and organizational resistance. This study provides a foundational framework for future research and practical implementation in Industry 5.0. Full article

In the context of Industry 4.0, Total Productive Maintenance (TPM) is undergoing a major shift driven by digital technologies such as the IoT, AI, cloud computing, and Cyber–Physical systems. This study explores how these technologies reshape traditional TPM pillars and practices through a two-phase methodology: bibliometric analysis, which reveals global research trends, key contributors, and emerging themes, and a systematic review, which discusses how core TPM practices are being transformed by advanced technologies. It also identifies key challenges of this transition, including data aggregation, a lack of skills, and resistance. However, despite the growing body of research on digital TPM, a major gap persists: the lack of a standardized model applicable across industries. Existing approaches are often fragmented or too context-specific, limiting scalability. Addressing this gap requires a structured approach that aligns technological advancements with TPM’s foundational principles. Taking a cue from these findings, this article formulates a systematic and scalable framework for TPM 4.0 deployment. The framework is based on four pillars: modular technological architecture, phased deployment, workforce integration, and standardized performance indicators. The ultimate goal is to provide a basis for a universal digital TPM standard that enhances the efficiency, resilience, and efficacy of smart maintenance systems. Full article

The global trend toward Industry 4.0 has intensified the demand for intelligent, adaptive, and energy-efficient manufacturing systems. Machine learning (ML) has emerged as a crucial enabler of this transformation, particularly in high-mix, high-precision environments. This review examines the integration of machine learning techniques, such as convolutional neural networks (CNNs), reinforcement learning (RL), and federated learning (FL), within Taiwan’s advanced manufacturing sectors, including semiconductor fabrication, smart assembly, and industrial energy optimization. The present study draws on patent data and industrial case studies from leading firms, such as TSMC, Foxconn, and Delta Electronics, to trace the evolution from classical optimization to hybrid, data-driven frameworks. A critical analysis of key challenges is provided, including data heterogeneity, limited model interpretability, and integration with legacy systems. A comprehensive framework is proposed to address these issues, incorporating data-centric learning, explainable artificial intelligence (XAI), and cyber–physical architectures. These components align with industrial standards, including the Reference Architecture Model Industrie 4.0 (RAMI 4.0) and the Industrial Internet Reference Architecture (IIRA). The paper concludes by outlining prospective research directions, with a focus on cross-factory learning, causal inference, and scalable industrial AI deployment. This work provides an in-depth examination of the potential of machine learning to transform manufacturing into a more transparent, resilient, and responsive ecosystem. Additionally, this review highlights Taiwan’s distinctive position in the global high-tech manufacturing landscape and provides an in-depth analysis of patent trends from 2015 to 2025. Notably, this study adopts a patent-centered perspective to capture practical innovation trends and technological maturity specific to Taiwan’s globally competitive high-tech sector. Full article

In response to the challenges of urbanization, digitalization, and the e-commerce surge intensified by the COVID-19 pandemic, Smart Urban Logistics (SUL) has become a key framework for addressing last-mile delivery issues, congestion, and environmental impacts. This study introduces a System Dynamics (SD)-based approach to investigate how urban logistics and access management policies may interact. At the center, there is a Causal Loop Diagram (CLD) that illustrates dynamic interdependencies among fleet composition, access regulations, logistics productivity, and environmental externalities. The CLD is a conceptual basis for future stock-and-flow simulations to support data-driven decision-making. The approach highlights the importance of route optimization, dynamic access control, and smart parking management systems as strategic tools, increasingly enabled by Industry 4.0 technologies, such as IoT, big data analytics, AI, and cyber-physical systems, which support real-time monitoring and adaptive planning. In alignment with the Industry 5.0 paradigm, this technological integration is paired with social and environmental sustainability goals. The study also emphasizes public–private collaboration in designing access policies and promoting alternative fuel vehicle adoption, supported by specific incentives. These coordinated efforts contribute to achieving the objectives of the 2030 Agenda, fostering a cleaner, more efficient, and inclusive urban logistics ecosystem. Full article

In recent decades, climate change, increasing demand, and resource scarcity have transformed the agricultural sector into a critical field of research. Farmers have been compelled to adopt innovations and new technologies to enhance production efficiency and crop resilience. This study presents a systematic literature review, supplemented by a bibliometric analysis of relevant documents, focusing on the key applications and combined techniques of artificial intelligence (AI), machine learning (ML), and digital twins (DT) in the development and implementation of cyber-physical systems (CPS) in smart agriculture and establishes whether CPS in agriculture is an attractive research topic. A total of 108 bibliographic records from the Scopus and Google Scholar databases were analyzed to construct the bibliometric study database. The findings reveal that CPS has evolved and emerged as a promising research area, largely due to its versatility and integration potential. The analysis offers researchers and practitioners a comprehensive overview of the existing literature and research trends on the dynamic relationship between CPS and its primary applications in the agricultural industry while encouraging further exploration in this field. Additionally, the main challenges associated with implementing CPS in the context of smart agriculture are discussed, contributing to a deeper understanding of this topic. Full article

As industries become increasingly dependent on cyber-physical systems (CPSs), failures within these systems can cause significant operational disruptions, underscoring the critical need for effective Prognostics and Health Management (PHM). The large volume of data generated by CPSs has made deep learning (DL) methods an attractive solution; however, imbalanced datasets and the limited availability of fault-labeled data continue to hinder their effective deployment in real-world applications. To address these challenges, this paper proposes a transfer learning approach using a pre-trained transformer architecture to enhance fault detection performance in CPSs. A streamlined transformer model is first pre-trained on a large-scale source dataset and then fine-tuned end-to-end on a smaller dataset with a differing data distribution. This approach enables the transfer of diagnostic knowledge from controlled laboratory environments to real-world operational settings, effectively addressing the domain shift challenge commonly encountered in industrial CPSs. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on publicly available datasets generated from a laboratory-scale replica of a modern industrial water purification facility. The results show that the model achieves an average F1-score of 93.38% under K-fold cross-validation, outperforming baseline models such as CNN and LSTM architectures, and demonstrating the practicality of applying transformer-based transfer learning in industrial settings with limited fault data. To enhance transparency and better understand the model’s decision process, SHAP is applied for explainable AI (XAI). Full article

The European Union (EU) is striving to achieve its goal of being climate-neutral by 2050. Aligned with the European Green Deal and in search of means to decarbonize its urban environments, the EU advocates for smart positive energy districts (PEDs). PEDs contribute to the United Nations’ (UN) sustainable development goals (SDGs) of “Sustainable Cities and Communities”, “Affordable and Clean Energy”, and “Climate Action”. PEDs are urban neighborhoods that generate renewable energy to a higher extent than they consume, mainly through the utilization of innovative technologies and renewable energy sources. In accordance with the EU 2050 aim, the PED concept is attracting growing research interest. PEDs can transform existing energy systems and aid in achieving carbon neutrality and sustainable urban development. PED is a novel concept and its implementation is challenging. This study aims to present the emerging technologies enabling the proliferation of PEDs by identifying the main challenges and potential solutions to effective adoption and implementation of PEDs. This paper examines the importance and utilization of cyber-physical systems (CPSs), digital twins (DTs), artificial intelligence (AI), the Internet of Things (IoT), edge computing, and blockchain technologies, which are all fundamental to the creation of PEDs for enhancing energy efficiency, sustainable energy, and user engagement. These systems combine physical infrastructure with digital technologies to create intelligent and autonomous systems to optimize energy production, distribution, and consumption, thus positively contributing to achieving smart and sustainable development. Full article

This study conducts a systematic bibliometric literature review to explore the conceptual and technological transition from Industry 4.0 to Industry 5.0, focusing on the roles of artificial intelligence (AI), optimization, and human values. Applying the PRISMA 2020 protocol, the analysis includes 53 peer-reviewed sources from the Scopus database, emphasizing the integration of advanced technologies such as cyber–physical systems, the Internet of Things, collaborative robotics, and explainable AI. While Industry 4.0 is marked by intelligent automation and digital connectivity, Industry 5.0 introduces a human-centric paradigm emphasizing sustainability, resilience, and co-creation. The findings underscore the significance of human–machine collaboration, process personalization, AI education, and ethical governance as foundational pillars of this new industrial era. This review highlights the emerging role of enabling technologies that reconcile technical performance with social and environmental values, promoting a more inclusive and sustainable model for industrial development. Full article

As cyber systems increasingly converge with physical infrastructure and social processes, they give rise to Complex Cyber–Physical–Social Systems (C-CPSS), whose emergent behaviors pose unique risks to security and mission assurance. Traditional cyber–physical system models often fail to address the unpredictability arising from human and organizational dynamics, leaving critical gaps in how cyber risks are assessed and managed across interconnected domains. The challenge lies in building resilient systems that not only resist disruption, but also absorb, recover, and adapt—especially in the face of complex, nonlinear, and often unintentionally emergent threats. This paper introduces the concept of ‘responsible resilience’, defined as the capacity of systems to adapt to cyber risks using trustworthy, transparent agent-based models that operate within socio-technical contexts. We identify a fundamental research gap in the treatment of social complexity and emergence in existing the cyber–physical system literature. To address this, we propose the E3R modeling paradigm—a novel framework for conceptualizing Emergent, Risk-Relevant Resilience in C-CPSS. This paradigm synthesizes human-in-the-loop diagrams, agent-based Artificial Intelligence simulations, and ontology-driven representations to model the interdependencies and feedback loops driving unpredictable cyber risk propagation more effectively. Compared to conventional cyber–physical system models, E3R accounts for adaptive risks across social, cyber, and physical layers, enabling a more accurate and ethically grounded foundation for cyber defence and mission assurance. Our analysis of the literature review reveals the underrepresentation of socio-emergent risk modeling in the literature, and our results indicate that existing models—especially those in industrial and healthcare applications of cyber–physical systems—lack the generalizability and robustness necessary for complex, cross-domain environments. The E3R framework thus marks a significant step forward in understanding and mitigating emergent threats in future digital ecosystems. Full article

As cyber–physical systems are applied not only to crucial infrastructure but also to day-to-day technologies, from industrial control systems through to smart grids and medical devices, they have become very significant. Cyber–physical systems are a target for various security attacks, too; their growing complexity and digital networking necessitate robust cybersecurity solutions. Recent research indicates that deep learning can improve CPS security through intelligent threat detection and response. We still foresee limitations to scalability, data privacy, and handling the dynamic nature of CPS environments in existing approaches. We developed the CPS ShieldNet Fusion model as a comprehensive security framework for protecting CPS from ever-evolving cyber threats. We will present a model that integrates state-of-the-art methodologies in both federated learning and optimization paradigms through the combination of the Federated Residual Convolutional Network (FedRCNet) and the EEL-Levy Fusion Optimization (ELFO) methods. This involves the incorporation of the Federated Residual Convolutional Network into an optimization method called EEL-Levy Fusion Optimization. This preserves data privacy through decentralized model training and improves complex security threat detection. We report the results of a rigorous evaluation of CICIoT-2023, Edge-IIoTset-2023, and UNSW-NB datasets containing the CPS ShieldNet Fusion model at the forefront in terms of accuracy and effectiveness against several threats in different CPS environments. Therefore, these results underline the potential of the proposed framework to improve CPS security by providing a robust and scalable solution to current problems and future threats. Full article

The increasing interconnectivity between physical and cyber-systems has led to more vulnerabilities and cyberattacks. Traditional preventive and detective measures are no longer adequate to defend against adversaries. Artificial Intelligence (AI) is used to solve complex problems, including those of cybersecurity. Adversaries also utilise AI for sophisticated and stealth attacks. This study aims to address this problem by exploring the symbiotic relationship of AI and cybersecurity to develop a new, adaptive strategic approach to defend against cyberattacks and improve global security. This paper explores different disciplines to solve security problems in real-world contexts, such as the challenges of scalability and speed in threat detection. It develops an algorithm and a detective predictive model for a Malicious Alert Detection System (MADS) that is an integration of adaptive learning and a neighbourhood-based voting alert detection framework. It evaluates the model’s performance and efficiency among different machines. The paper discusses Machine Learning (ML) and Deep Learning (DL) techniques, their applicability in cybersecurity, and the limitations of using AI. Additionally, it discusses issues, risks, vulnerabilities, and attacks against AI systems. It concludes by providing recommendations on security for AI and AI for security, paving the way for future research on enhancing AI-based systems and mitigating their risks. Full article

Amid the dual imperatives of global trade expansion and low-carbon transition, intelligent maritime shipping has emerged as a central driver for the innovation of international logistics systems, now entering a critical window period for the deep integration of Internet technologies and automated port infrastructure. While existing research predominantly focuses on isolated applications of intelligent technologies, systematic evaluations of the synergistic effects of technological integration on maritime ecosystems, policy compatibility, and contributions to global carbon emission governance remain under-explored. Leveraging bibliometric analysis, this study systematically examines 488 publications from the Web of Science (WoS) Core Collection (2000–2024), yielding three pivotal findings: firstly, China dominates the research landscape, with a 38.5% contribution share, where Artificial Intelligence (AI), the Internet of Things (IoT), and port automation constitute the technological pillars. However, critical gaps persist in cross-system protocol standardization and climate-adaptive modeling, accounting for only 2.7% and 4.2% of the literature, respectively. Secondly, international collaboration networks exhibit pronounced “Islamization”, characterized by an inter-team collaboration rate of 17.3%, while the misalignment between rapid technological iteration and existing maritime regulations exacerbates industry risks. Thirdly, a dual-track pathway integrating Cyber–Physical System (CPS)-based digital twin ports and open-source vertical domain-specific large language models is proposed. Empirical evidence demonstrates its efficacy in reducing cargo-handling energy consumption by 15% and decision-making latency by 40%. This research proposes a novel tripartite framework, encompassing technological, institutional, and data sovereignty dimensions, to resolve critical challenges in integrating multi-source maritime data and managing cross-border governance. The model provides academically validated and industry-compatible strategies for advancing sustainable maritime intelligence. Subsequent investigations should expand data sources to include regional repositories and integrate interdisciplinary approaches, ensuring the adaptability of both technical systems and international policy coordination mechanisms across diverse maritime ecosystems. Full article

Advanced as they are, DL models in cyber-physical systems remain vulnerable to attacks like the Fast Gradient Sign Method, DeepFool, and Jacobian-Based Saliency Map Attacks, rendering system trustworthiness impeccable in applications with high stakes like power systems. In power grids, DL models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are commonly utilized for tasks like state estimation, load forecasting, and fault detection, depending on their ability to learn complex, non-linear patterns in high-dimensional data such as voltage, current, and frequency measurements. Nevertheless, these models are susceptible to adversarial attacks, which could lead to inaccurate predictions and system failure. In this paper, the impact of these attacks on DL models is analyzed by employing the use of defensive countermeasures such as Adversarial Training, Gaussian Augmentation, and Feature Squeezing, to investigate vulnerabilities in industrial control systems with potentially disastrous real-world impacts. Emphasizing the inherent requirement of robust defense, this initiative lays the groundwork for follow-on initiatives to incorporate security and resilience into ML and DL algorithms and ensure mission-critical AI system dependability. Full article

This study proposes an AI-powered digital twin (DT) platform designed to support real-time traffic risk prediction, decision-making, and sustainable mobility in smart cities. The system integrates multi-source data—including static infrastructure maps, historical traffic records, telematics data, and camera feeds—into a unified cyber–physical platform. AI models are employed for data fusion, anomaly detection, and predictive analytics. In particular, the platform incorporates telematics–video fusion for enhanced trajectory accuracy and LiDAR–camera fusion for high-definition work-zone mapping. These capabilities support dynamic safety heatmaps, congestion forecasts, and scenario-based decision support. A pilot deployment on Madison’s Flex Lane corridor demonstrates real-time data processing, traffic incident reconstruction, crash-risk forecasting, and eco-driving control using a validated Vehicle-in-the-Loop setup. The modular API design enables integration with existing Advanced Traffic Management Systems (ATMSs) and supports scalable implementation. By combining predictive analytics with real-world deployment, this research offers a practical approach to improving urban traffic safety, resilience, and sustainability. Full article