{"title":"Deep Belief-MobileNet1D: A novel deep learning approach for anomaly detection in industrial big data","authors":"Tzu-Chia Chen","doi":"10.1016/j.iot.2025.101593","DOIUrl":"10.1016/j.iot.2025.101593","url":null,"abstract":"<div><div>Early fault or unusual behavior detection can reduce the risk of equipment failure improve performance and increase safety. Anomaly detection in industrial big data involves identifying deviations from normal patterns in large-scale datasets. This method assists in preventing equipment failures optimizing maintenance schedules and raising overall operational efficiency in industrial settings by identifying anomalous behaviors or outliers. Through the utilization of deep learning procedures, this investigation endeavours to apply are fined procedure for anomaly detection in industrial big data. Pre-processing, feature selection and Anomaly detection are three steps of a process that are used. The input data is first fed into MapReduce framework where it is divided and pre-processed. Imputation of missing data and Yeo-Jhonson transformation are then applied to eliminate noise from data. After pre-processed data is generated, it is put through a feature selection phase using Serial Exponential Lotus Effect Optimization Algorithm (SELOA). The algorithm is created newly by combining Lotus Effect Optimization Algorithm (LOA) with Exponential Weighted Moving Average (EWMA). Finally, anomaly detection is done using the features that are selected by means of Deep Belief-MobileNet1D, which combines MobileNet1D and Deep Belief Network (DBN). With a recall of 96.2 %, precision of 92.8 %, F1 score of 94.5 % and accuracy of 95.9 %, results show that the proposed strategy surpasses standard approaches. These findings demonstrate Deep Belief-MobileNet1D model's ability to detect anomalies in industrial big data.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101593"},"PeriodicalIF":6.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792333","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":"Edge-based physical asset and digital twin virtualization framework to support cognitive digital twins","authors":"Rolando Herrero , Mallesham Dasari","doi":"10.1016/j.iot.2025.101601","DOIUrl":"10.1016/j.iot.2025.101601","url":null,"abstract":"<div><div>In <em>Cyber-Physical Systems</em> (CPSs), devices interact with smart applications by relying on <em>Internet of Things</em> (IoT) protocols to transmit sensor readings from monitoring <em>Physical Assets</em> (PAs). The applications support mapping mechanisms that constitute <em>Digital Twins</em> (DTs) to mimic the behavior of the actual PAs. Changes in PAs are mirrored in the DTs, and vice versa. This duality enables the creation of <em>Cognitive Digital Twins</em> (CDTs), where the readings generated by PAs enable the extraction of knowledge to support actuation through AI models on the PAs. This paper introduces a generic <em>PA and DT Virtualization</em> (PDV) framework that leverages the Internet Engineering Task Force layered architecture through an application layer smart sublayer that learns from the interaction between PAs and DTs to enable edge-based CDT support. Although this framework is agnostic of the CPS under consideration, its focus in this paper is on Industry 5.0 applications. In this context, a new IoT protocol is proposed to enable a PDV scheme that provides the reliable automation of the interaction between PAs and DTs even in the presence of different levels of wireless network layer impairments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101601"},"PeriodicalIF":6.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808220","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}
Ozlem Ceviz , Pinar Sadioglu , Sevil Sen , Vassilios G. Vassilakis
{"title":"A novel federated learning-based IDS for enhancing UAVs privacy and security","authors":"Ozlem Ceviz , Pinar Sadioglu , Sevil Sen , Vassilios G. Vassilakis","doi":"10.1016/j.iot.2025.101592","DOIUrl":"10.1016/j.iot.2025.101592","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) operating within Flying Ad-hoc Networks (FANETs) encounter security challenges due to the dynamic and distributed nature of these networks. Previous studies focused predominantly on centralized intrusion detection, assuming a central entity responsible for storing and analyzing data from all devices. However, these approaches face challenges including computation and storage costs, along with a single point of failure risk, threatening data privacy and availability. The widespread dispersion of data across interconnected devices underscores the need for decentralized approaches. This paper introduces the Federated Learning-based Intrusion Detection System (FL-IDS), addressing challenges encountered by centralized systems in FANETs. FL-IDS reduces computation and storage costs for both clients and the central server, which is crucial for resource-constrained UAVs. Operating in a decentralized manner, FL-IDS enables UAVs to collaboratively train a global intrusion detection model without sharing raw data, thus avoiding delay in decisions based on collected data, as is often the case with traditional methods. Experimental results demonstrate FL-IDS’s competitive performance with Central IDS (C-IDS) while mitigating privacy concerns, with the Bias Towards Specific Clients (BTSC) method further enhancing FL-IDS performance even at lower attacker ratios. Comparative analysis with traditional intrusion detection methods, including Local IDS (L-IDS), sheds light on the strengths of FL-IDS. This study significantly contributes to UAV security by introducing a privacy-aware, decentralized intrusion detection approach tailored to UAV networks. Moreover, by introducing a realistic dataset for FANETs and federated learning, our approach differs from others lacking high dynamism and 3D node movements or accurate federated data federations.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101592"},"PeriodicalIF":6.0,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792332","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}
Yu-Sheng Su , Jun-qing Wang , Shou-Hsi Tu , Kuo-Ti Liao , Chien-Liang Lin
{"title":"Detecting latent topics and trends in IoT and e-commerce using BERTopic modeling","authors":"Yu-Sheng Su , Jun-qing Wang , Shou-Hsi Tu , Kuo-Ti Liao , Chien-Liang Lin","doi":"10.1016/j.iot.2025.101604","DOIUrl":"10.1016/j.iot.2025.101604","url":null,"abstract":"<div><div>The rapid development of the Internet of Things (IoT) is reshaping e-commerce, driving business model innovation and enhancing operational efficiency. However, existing research primarily focuses on specific application scenarios of IoT, while lacking a systematic exploration of its overall development trends, core research topics, and challenges. To address this gap, this study employed BERTopic topic modeling to systematically analyze key research themes and evolutionary trends of IoT in the e-commerce domain, based on 169 highly relevant papers from the Web of Science database (2010–2024). The findings revealed four core themes: (1) the transformation of e-commerce business models driven by IoT technologies, (2) the role of blockchain in data security and trust mechanisms, (3) the synergy between smart logistics and e-commerce, and (4) privacy protection and personal data management in the IoT ecosystem. Additionally, this study identified a shift in IoT applications from an initial focus on supply chain optimization to an increasing emphasis on data-driven decision-making, intelligent business models, and data privacy protection. By conducting an in-depth analysis of the dynamic evolution of these themes, this research not only fills the knowledge gap regarding the current state and trends of IoT research in e-commerce, but also provides the academic community with an innovative method applicable to large-scale text data analysis. Furthermore, for businesses and policymakers, strengthening cross-sectoral technological integration, improving privacy protection mechanisms, and enhancing policy support are suggested to promote the sustainable development of IoT and e-commerce. This research enriches the academic discourse on the synergy between IoT and e-commerce in the context of digital transformation, and provides strategic guidance for practitioners.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101604"},"PeriodicalIF":6.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842803","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":"Explainable AI-based intrusion detection in IoT systems","authors":"Sarah Bin hulayyil , Shancang Li , Neetesh Saxena","doi":"10.1016/j.iot.2025.101589","DOIUrl":"10.1016/j.iot.2025.101589","url":null,"abstract":"<div><div>The Internet of Things (IoT) systems are highly vulnerable to cyber attacks due to limited and/or default security measurements. Machine learning (ML) techniques bring a powerful weapon against the insecurities of IoT systems, such as intelligent intrusion detection systems (IDSs), vulnerability/threats detection, and behavioral analysis. ML-based IDSs offer a significant improvement in IoT security, but they also bring technical challenges, e.g., false positives, evolving attacks, data quality and bias, explainability and transparency, etc. Explainable Artificial Intelligence (XAI) can address these challenges by offering interpretable and comprehensible insights into the ML-based IDS decision-making process. A novel framework for an explainable IDS-based vulnerable IoT devices related to the Ripple20 vulnerability and its associated attacks. The framework integrates ML classifiers and XAI techniques to provide comprehensive and interpretable explanations for the IDS decisions. We evaluated this framework on various datasets, including a dataset collected from the labs and other public datasets, using binary and multi-classification models. The experimental results demonstrate the efficiency and accuracy of the framework in detecting and categorizing IoT vulnerabilities. The framework also offers benefits over conventional IDS systems, such as facilitating comprehension and confidence among security experts, enhancing the precision and efficiency of the detection procedure, and adapting to the dynamic IoT environment.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101589"},"PeriodicalIF":6.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785143","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":"An approach to assess robustness of MQTT-based IoT systems","authors":"Bruno Jesus , Fernando Lins , Nuno Laranjeiro","doi":"10.1016/j.iot.2025.101590","DOIUrl":"10.1016/j.iot.2025.101590","url":null,"abstract":"<div><div>The Internet of Things (IoT) has become vital in modern life, connecting a wide range of devices, sensors, and other computing objects. As the number of devices and interconnections grows, IoT systems are also increasingly exposed to unexpected conditions. Thus, it becomes critical that they operate in a robust manner (i.e., they are able to deliver correct service, even in the presence of invalid inputs or stressful conditions). Despite this, the literature shows that practical robustness evaluation techniques have been mostly disregarded in this domain, with developers also tending to focus on core functionality, driven by reasons such as the pressure to time-to-market. This paper describes an approach for assessing the robustness of MQTT-based IoT systems, i.e., systems that use MQTT to exchange messages between devices. The proposed approach is based on injecting faults into messages carried by MQTT between IoT elements with the goal of activating residual application-level faults that may have escaped during the system development. To illustrate our approach, we applied it to two real case studies, Smart Rural and MInA, in which we were able to trigger several different types of failures. Overall, the results highlight the usefulness of the proposed approach and demonstrate the potential of a dedicated robustness assessment approach particularly tailored for IoT systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101590"},"PeriodicalIF":6.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776661","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}
Zahra Hamoony Haghighat , Anik Islam , Hadis Karimipour , Behnam Miripour Fard
{"title":"An explainable big transfer learning approach for IoT-based safety management in smart factories","authors":"Zahra Hamoony Haghighat , Anik Islam , Hadis Karimipour , Behnam Miripour Fard","doi":"10.1016/j.iot.2025.101600","DOIUrl":"10.1016/j.iot.2025.101600","url":null,"abstract":"<div><div>The integration of the Internet of Things (IoT) in smart factories enhances management through real-time monitoring and data analytics, while Artificial Intelligence (AI) automates processes and boosts efficiency. However, AI systems require vast amounts of data and substantial training time, facing challenges such as domain discrepancies, limited labeled data, negative transfer, sample selection bias, and computational complexity. Additionally, the opaque nature of AI models raises transparency issues, making it difficult for human operators to trust and interpret AI decisions. To address these challenges, this paper proposes an IoT-based safety management scheme for smart factories, utilizing advanced technologies to enhance safety and operational efficiency. The proposed approach integrates robust deep learning (DL) models developed through big transfer learning (BiTL) and is augmented with explainable AI (XAI) to ensure transparency and reliability in safety management. The major contributions of this work include designing a comprehensive IoT-based safety framework, conducting a detailed case study to optimize DL model performance using BiTL, and establishing an experimental environment for thorough validation. The findings demonstrate that the proposed system not only meets but also exceeds the performance of existing safety management solutions, offering a transparent, trustworthy, and highly effective AI-driven safety management system for modern smart factories.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101600"},"PeriodicalIF":6.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785142","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":"SemChain : A Blockchain-based semantic discovery on distributed resource directories for the Internet of Things","authors":"Kheireddine Zaghouani , Badis Djamaa , Ali Yachir , Saïd Mahmoudi","doi":"10.1016/j.iot.2025.101591","DOIUrl":"10.1016/j.iot.2025.101591","url":null,"abstract":"<div><div>As the Web evolves towards Web 3.0, integrating the Internet of Things (IoT), the Semantic Web, and Blockchain (BC) technology, managing the growing number of IoT devices and ensuring their interoperability and trust becomes increasingly critical. Centralized solutions are prone to single points of failure, while distributed systems face synchronization and consensus issues. Although integrating BC into IoT has shown promise in addressing these challenges, existing approaches often overlook the resource limitations of IoT devices, the importance of standardized IoT protocols, and the impact of BC consensus mechanisms on network performance. To bridge these gaps, this paper presents SemChain: a framework integrating BC within the semantic web of things in a robust, resource-friendly, and trustworthy manner. Leveraging the CoAP standard, a distributed network of resource directories, and a permissioned BC with Smart Contracts (SC), SemChain strengthens the security and trust of semantic resource registration and discovery in IoT environments. Other key contributions include proposing two data storage approaches, namely SemChain-Full and SemChain-Hash, devising multiple SC transactions, and providing a detailed description of a prototype implementation. The framework’s performance is evaluated against state-of-the-art approaches within a smart hospital use case, demonstrating notable improvements, including an average precision of 92<span><math><mtext>%</mtext></math></span> and a recall of 88<span><math><mtext>%</mtext></math></span> in resource discovery.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101591"},"PeriodicalIF":6.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785141","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}
Muhammad Umar Farooq , Haris Ghafoor , Azka Rehman , Muhammad Usman , Dong-Kyu Chae
{"title":"GDSSA-Net: A gradually deeply supervised self-ensemble attention network for IoMT-integrated thyroid nodule segmentation","authors":"Muhammad Umar Farooq , Haris Ghafoor , Azka Rehman , Muhammad Usman , Dong-Kyu Chae","doi":"10.1016/j.iot.2025.101598","DOIUrl":"10.1016/j.iot.2025.101598","url":null,"abstract":"<div><div>The integration of deep learning techniques in the <em>Internet of Medical Things</em> (IoMT) has significantly advanced the early detection of life-threatening diseases such as thyroid cancer, one of the most lethal tumors. Accurate delineation of thyroid nodules in ultrasound images is essential for timely diagnosis and for effective treatment. This research introduces a novel deep-learning framework tailored for IoMT environments, aimed at the automatic segmentation of thyroid nodules in ultrasound images. We propose a <em>Gradually Deeply Supervised Self-ensemble Attention Network</em> (GDSSA-Net), which employs encoder to extract features from sonographic scans and integrates a gated attention mechanism within the decoder to refine features while filtering out irrelevant information. To enhance the learning process, we developed a novel Gradual Deep Supervision (GDS) strategy, utilizing three variations of ground truth to deeply supervise the network. Additionally, our approach employs self-ensembling mechanisms by ensembling outputs of the shallower branches alongside the main branch to improve the thyroid nodule segmentation. To validate the superiority and generalizability of GDSSA-Net, we conducted extensive evaluations on two publicly available datasets, DDTI and TN3K. Experimental results demonstrate that our method surpasses its simplified variants and existing state-of-the-art models in terms of quantitative metrics and qualitative assessments. Specifically, our model achieves a Dice coefficient of 79.85% and 84.27% on DDTI and TN3K, respectively. The source code for our proposed model is publicly available at <span><span>https://github.com/harisghafoor/GDSSA-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101598"},"PeriodicalIF":6.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759776","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}
Jordan Rey-Jouanchicot , Eric Campo , Jean-Léon Bouraoui , André Bottaro , Nadine Vigouroux , Frédéric Vella
{"title":"Adaptation in Smart Home Automation Systems: A systematic review of decision-making and interaction","authors":"Jordan Rey-Jouanchicot , Eric Campo , Jean-Léon Bouraoui , André Bottaro , Nadine Vigouroux , Frédéric Vella","doi":"10.1016/j.iot.2025.101588","DOIUrl":"10.1016/j.iot.2025.101588","url":null,"abstract":"<div><div>Smart home automation systems have gained in popularity recently due to the advent of the Internet of Things. These systems offer homeowners convenience, comfort, and energy efficiency using various devices such as thermostats and voice assistants. A key factor in the success of these systems in the future will be their ability to make effective decisions and seamlessly interact with users and their surroundings. However, as technology continues to advance, it is essential to investigate how these systems can adapt, especially in terms of decision-making and interaction. This work presents a systematic review of the literature on adaptivity in smart home automation systems, focusing on general-purpose and comfort use cases.</div><div>The review explores and discusses various proposals and approaches to adaptation, with a specific emphasis on the use of artificial intelligence. The aim is to provide an overview of existing approaches and highlight recent research contributions. It also discusses limitations, challenges, and emerging trends in decision-making systems for smart homes. Finally, it suggests future research directions to improve their adaptivity.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101588"},"PeriodicalIF":6.0,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768043","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}