{"title":"Optimizing co-simulation with the age of information in intelligent cyber physical systems","authors":"Yu Zhang , Sijie Xu , Ben Wei , Zihui Chen , Uzair Aslam Bhatti , Mengxing Huang","doi":"10.1016/j.iot.2025.101550","DOIUrl":"10.1016/j.iot.2025.101550","url":null,"abstract":"<div><div>Intelligent Cyber-Physical Systems (ICPS) integrate technologies from physics, information science, and artificial intelligence. Due to the specificity of application domains, these systems often demand higher standards for their quality. Utilizing co-simulation as one of the crucial techniques for system validation can effectively enhance system quality. However, due to the complexity of application scenarios, traditional co-simulation methods often lack precise descriptions of the temporal semantics in the interaction models, thereby overlooking the intricate temporal relationships among different components, resulting in the inability to flexibly, accurately analyze and evaluate system behavior based on different application scenarios. This paper introduces an ICPS co-simulation method that uses the Age of Information (AoI) mechanism to resolve identified problems. The co-simulation framework consists of physical simulation models together with information simulation models and interaction models which we designed first. We establish Age of Information-based temporal interaction types to precisely measure information freshness during decision-making processes. Three time synchronization protocols (time-stepping, global event-driven and variable-stepping) have been proposed to enhance simulator synchronization with an emphasis on operational efficiency and accuracy levels. Our approach validation includes running multiple simulation tests which examine different interaction types together with synchronization protocols. The modeling of information age of interaction results in enhanced decision-making accuracy according to experimental results. The proposed co-simulation method shows its practical feasibility based on RoboMaster EP experimental assessments which demonstrate similar behaviors between simulated and actual physical systems. The research enhances ICPS co-simulation techniques through information aging and synchronization solutions which lead to better system validation prior to deployment.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101550"},"PeriodicalIF":6.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143534113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance comparison of explainable DQN and DDPG models for cooperative lane change decision-making in multi-intelligent industrial IoT vehicles","authors":"Hao-bai ZHAN","doi":"10.1016/j.iot.2025.101552","DOIUrl":"10.1016/j.iot.2025.101552","url":null,"abstract":"<div><div>With the rapid advancement of intelligent connected vehicles (ICVs) technology, efficient and safe vehicular lane-changing decisions have become a focal point of interest for intelligent transportation systems (ITS). This paper investigates the application of explainable artificial intelligence (XAI) techniques to deep reinforcement learning algorithms, specifically deep Q-networks (DQN) and deep deterministic policy gradient (DDPG), for lane-changing decisions in industrial internet of things (IIoT) vehicles. By integrating innovative reward functions, the study assesses the performance differences between these models under various traffic densities and ICV counts in a three-lane highway scenario. The use of XAI feature representations enhances the transparency and interpretability of the models, providing insights into the decision-making process. XAI helps to elucidate how the models arrive at their decisions, improving trust and reliability in automated systems. The research reveals that although the DQN model demonstrates initial superior performance in the early phases of experimentation, the DDPG model outperforms in crucial performance metrics such as average fleet speed, headway, and stability during later stages of training. The DDPG model maintains better control over fleet speed and vehicle spacing in both low-density and high-density traffic environments, showcasing its superior adaptability and efficiency. These findings highlight the DDPG model's enhanced capability to manage dynamic and complex driving environments, attributed to its refined policy learning approach which adeptly balances exploration and exploitation. The novel reward function significantly promotes cooperative lane-changing behaviors among ICVs, optimizing lane change decisions and improving overall traffic flow efficiency. This study not only provides valuable technical support for lane-changing decisions in smart vehicular networks but also lays a theoretical and empirical foundation for the advancement of future ITS. The insights gained from comparing DQN and DDPG models contribute to the ongoing discussion on effective deep learning strategies for real-world ITS applications, potentially guiding future developments in autonomous driving technologies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101552"},"PeriodicalIF":6.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Formal verification and security analysis of FastDFS using process algebra","authors":"Zhiru Hou, Huibiao Zhu","doi":"10.1016/j.iot.2025.101543","DOIUrl":"10.1016/j.iot.2025.101543","url":null,"abstract":"<div><div>FastDFS is a lightweight distributed file system that fully incorporates redundant backup, load balancing, linear expansion and other mechanisms. It is easy to build a high-performance file server cluster using FastDFS. Given the widespread usage of FastDFS, carrying out its analysis within a formal framework is highly significant. In this paper, we first model and analyze FastDFS using process algebra CSP. The three key functions that we concentrate on are uploading, downloading, and deleting files. Additionally, we pay attention to the security of FastDFS from a deterministic point of view. Utilizing the Process Analysis Toolkit (PAT) as a model checker, we employ the constructed model to validate several internal properties and security properties, including Deadlock Freedom, Divergence Freedom, Reachability, Robustness, Consistency, Eagerly Secure, Lazily Secure and Mixed Secure. Our final verification results demonstrate that the model effectively fulfills the internal properties, indicating that the system can well guarantee the management of files. However, it cannot cater to the security properties, which means the model implies some potential security vulnerabilities from a deterministic point of view.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101543"},"PeriodicalIF":6.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sabah Suhail , Mubashar Iqbal , Kieran McLaughlin , Brian Lee , Babar Imtiaz
{"title":"A framework for enhancing cyber incident response with Security-Enhancing Digital Twins in Cyber–Physical Systems","authors":"Sabah Suhail , Mubashar Iqbal , Kieran McLaughlin , Brian Lee , Babar Imtiaz","doi":"10.1016/j.iot.2025.101547","DOIUrl":"10.1016/j.iot.2025.101547","url":null,"abstract":"<div><div>Standalone traditional cybersecurity solutions and tools often fall short in covering the lifecycle of critical assets, conducting vulnerability identification, and correlating cyber incidents with adversary knowledge bases. This limitation can lead to fragmented incident response (IR) strategies. Security-enhancing digital twins (SEDTs) can act as complementary security solutions alongside existing solutions to support various IR lifecycle phases in cyber–physical systems (CPSs). In this work, we propose a framework that can serve as a guide for plant operators on how to design, develop, deploy, and manage SEDT-based IR solutions across four key phases, including prerequisites, design-and-engineering, operation-and-maintenance, and end-of-life. With the automotive manufacturing industry as a cyber–physical production system (CPPS) use case, we thoroughly examine the applicability of the proposed framework. Furthermore, we evaluate the proposed framework in both industry and academic settings, covering various aspects, including the design and operation requirements of SEDTs. This evaluation helps identify gaps between academic findings and practical industry solutions, such as in SEDT objectives, architecture, integration with existing security solutions, and lifecycle.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101547"},"PeriodicalIF":6.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Programming IoT systems: A focused conceptual framework and survey of approaches","authors":"Roberto Casadei , Fabrizio Fornari , Stefano Mariani , Claudio Savaglio","doi":"10.1016/j.iot.2025.101548","DOIUrl":"10.1016/j.iot.2025.101548","url":null,"abstract":"<div><div>Any software engineer of Internet of Things (IoT) systems deals with three macro issues: how to perceive the properties of interest through sensors (<em>sensing</em> facet), how to process such information to decide what to do to achieve the system goals (<em>processing</em> facet), and how to enact such decisions by affecting the IoT system itself and its deployment environment accordingly (<em>actuation</em> facet). For each, one can either develop ad-hoc solutions from scratch, with mainstream programming languages, or build on top of existing IoT-specific software libraries, frameworks, and platforms. Here, we survey the broad state of the art of “IoT programming”, with a focus on clarifying which and how <em>programming paradigms and platforms</em> deal with four key features demanded by modern IoT systems: <em>scale-independence</em>, <em>situatedness</em>, <em>adaptiveness</em>, and <em>opportunistic deployment</em>, along the aforementioned three facets. We motivate such needs by describing compelling contemporary and near future scenarios. Then, we propose a reference <em>conceptual framework of programming IoT systems</em> with the goal of <em>(i)</em> uncovering which research areas are mostly active in IoT programming, and <em>(ii)</em> placing the state of the art at the intersection between the appropriate features and facets, to both <em>(iii)</em> clarify which approaches are most suited for different kinds of tasks, and <em>(iv)</em> emphasising open challenges. This conceptual framework is a novel contribution in the landscape of IoT programming surveys, and is intended to be a practical aid for researchers and practitioners that are deciding which computational tools (e.g. languages and platforms) to adopt while building their own IoT systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101548"},"PeriodicalIF":6.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"OASIS: Online adaptive ensembles for drift adaptation on evolving IoT data streams","authors":"T. Anithakumari, Sanket Mishra","doi":"10.1016/j.iot.2025.101545","DOIUrl":"10.1016/j.iot.2025.101545","url":null,"abstract":"<div><div>In this work, our proposed OASIS framework utilizes adaptive ensembles to accommodate IoT data drift. In this work, we introduce an innovative sliding window approach using periodograms, engineered to efficiently feed models with data input. Six distinct online learners, alongside three drift adaptation algorithms: EDDM, HDDM-A and ADWIN have been tested using various feature selection methods, such as particle swarm optimization (PSO), dragonfly optimization (DA), grey wolf optimization (GWO), genetic algorithm (GA), and whale optimization algorithm (WOA), which have been carried out to validate the efficacy of the OASIS framework. We introduce a weighted probability approach derived from multiclass outcomes to ascertain the most suitable learners for leverage bagging or voting ensemble application. This is followed by an optimal scoring mechanism to determine the best training set based on accuracy and execution time criteria. The selection of models is guided by a probability-based algorithm coupled with a scoring system. Furthermore, we benchmark three state-of-the-art drift adaptation frameworks to evaluate their performance relative to our proposed framework. Evaluations in the context of EDGE-IIoT demonstrated outstanding accuracies of 98.98% in binary scenarios and 99.92% in multiclass scenarios, with the IoTID20 datasets achieving notable accuracies of 99.94% in binary and 100% in multiclass scenarios, thus surpassing previous methodologies. The framework undergoes extensive experiments with two recent multiclass datasets, namely the Aalto and RT-IoT 2022 datasets, in which OASIS achieved 99.99% accuracy on the Aalto dataset and 96.52% on the RT-IoT 2022 dataset. Additionally, we compare our framework with various concept drift datasets and leading drift ensemble frameworks for performance comparison.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101545"},"PeriodicalIF":6.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A predictive maintenance architecture for TFT-LCD manufacturing using machine learning on the cloud service","authors":"Chih-Hung Chang , Hsin-Ta Chiao , Hsiang-Ching Chang , Endah Kristiani , Chao-Tung Yang","doi":"10.1016/j.iot.2025.101541","DOIUrl":"10.1016/j.iot.2025.101541","url":null,"abstract":"<div><div>The rise of Industry 4.0 has brought the world to intelligent manufacturing. The manufacturing industry combines technologies such as the Internet of Things, big data, and AI. Recent developments can further analyze equipment maintenance work by collecting real-time machine statuses, such as temperature and other parameter information. To achieve predictive machine maintenance, perform device maintenance and repair in advance to avoid unexpected downtime and affect production line operation. This paper will take the industry of TFT LCD panel component manufacturing as an experimental field and implement the predictive maintenance system of the TFT LCD machine through the Azure cloud service platform. First, the Pearson correlation was run to find a strong correlation for parameter training. In this case, Spark was used to reduce the processing time that initially took 2 h to 43 s and increase the speed by 99.4%. An optimization of the partition of the data table increased the operating cost, the IO cost, and the CPU cost by 98.77%, 98.78%, and 98.74%, respectively. Different training data and nodes are also compared to find excellent results. KNN, RF, XGBoost and SVM were compared to select a model that would be most suitable for use in the TFT LCD case. Finally, the results of the data and model analysis were visualized in real-time Azure Kubernetes scoring.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101541"},"PeriodicalIF":6.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fingerprinting chipless RFID with a MIMO system for tag authentication in Internet of Things","authors":"Shahed Khan , Biplob Ray , Nemai Karmakar","doi":"10.1016/j.iot.2025.101542","DOIUrl":"10.1016/j.iot.2025.101542","url":null,"abstract":"<div><div>This paper presents a new method to tackle the security issues of chipless tag systems in Internet of Things (IoT) applications. The strategy aims to prevent the cloning of tags by utilizing the intrinsic natural randomness in the manufacturing process. This research presents a novel approach to generate fingerprints for chipless Radio Frequency Identification (RFID) tags using the unique backscattered electromagnetic (EM) responses, caused by inherent natural variations in resonator geometry, captured by a portable Multiple Input Multiple Output (MIMO) reader. Using twenty-two tags, one authentic and twenty-one counterfeits, two separate sets of fingerprints were generated using both Frequency Domain (FD) and Time Domain (TD) data, respectively. The clone detection model achieved an accuracy of 98.41% in a 35 dB noisy environment using fingerprints generated from FD data and 92.07% in a 50 dB noisy environment using fingerprints derived from TD data. This was obtained by utilizing similarity metrics such as Mean Squared Error (MSE) and Structural Similarity Index (SSI), offering a robust alternative to traditional tag authentication methods. The portability and affordability of the MIMO reader, combined with new opportunities for image-based identification, position this approach as a substantial advancement in the realm of authenticity verification for chipless RFID tags in the realm of IoT.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101542"},"PeriodicalIF":6.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Artificial intelligence and internet of things to improve smart hospitality services","authors":"Kuo Cheng Chung , Paul Juinn Bing Tan","doi":"10.1016/j.iot.2025.101544","DOIUrl":"10.1016/j.iot.2025.101544","url":null,"abstract":"<div><div>Advances in artificial intelligence (AI) and the Internet of Things (IoT) have significantly reshaped the hospitality sector by introducing intelligent operations and tailored services. This research explores how the AIoT-enabled service robots influence hotel employees’ psychological and operational dynamics. Specifically, it examines the interplay among job demands, resources, cognitive trust, and perceived behavioral control within the context of job demands and resources theory. The study analyzes employees’ job-related factors and establishes a conceptual framework that highlights how these elements shape employees’ experiences with service robots. Data were analyzed using SPSS 21 and SmartPLS software. The analysis revealed that self-efficacy enhances cognitive trust and perceived behavioral control, thus boosting employees’ confidence in working alongside robots and streamlining operations. Conversely, threat appraisals were found to undermine these benefits by exacerbating feelings of job insecurity. Responsiveness and interactivity positively influenced cognitive trust and perceived behavioral control, while anthropomorphic traits influenced only the latter. Familiarity with technology further amplified these effects. The findings underscore the necessity of cognitive trust, confidence, and technology familiarity among employees, thus offering actionable insights for hoteliers to optimize human–machine collaboration, harmonize innovation with employee welfare, and achieve sustainable, intelligent development.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101544"},"PeriodicalIF":6.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143526920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammad Ali Raayatpanah , Atefeh Abdolah Abyaneh , Jocelyne Elias , Fabio Martignon
{"title":"Two-stage robust wireless body area network design","authors":"Mohammad Ali Raayatpanah , Atefeh Abdolah Abyaneh , Jocelyne Elias , Fabio Martignon","doi":"10.1016/j.iot.2025.101540","DOIUrl":"10.1016/j.iot.2025.101540","url":null,"abstract":"<div><div>The Internet of Things (IoT) has reshaped technology paradigms through the integration of intelligent components like sensors, paving the way to the development of Wireless Body Area Networks (WBANs) specifically tailored for healthcare applications. However, designing an efficient WBAN requires addressing several challenges, including energy-efficient routing and data rate uncertainty. In response to these challenges, this paper proposes a novel approach — a two-stage robust programming formulation — for WBAN design. The primary aim is to minimize both energy consumption and relay placement costs, all while accounting for the inherent uncertainty in data rates. The proposed formulation explicitly addresses data rate uncertainties, leveraging robust optimization techniques to handle this uncertainty. We prove that efficiently solving an approximation of this robust formulation is achievable. Numerical results, measured in a set of realistic WBAN scenarios, demonstrate the effectiveness of the introduced two-stage robust programming formulation in achieving notable reductions in energy consumption and relay placement costs within the context of WBANs.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101540"},"PeriodicalIF":6.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}