Internet of Things最新文献

{"title":"Enhancing physical security in IIoMT environments","authors":"Umar Islam ,&nbsp;Mohammed Naif Alatawi ,&nbsp;Sulaiman Alamro ,&nbsp;Hathal Salamah Alwageed ,&nbsp;Hanif Ullah ,&nbsp;Naveed Khan","doi":"10.1016/j.iot.2025.101653","DOIUrl":"10.1016/j.iot.2025.101653","url":null,"abstract":"<div><div>The Industrial Internet of Medical Things (IIoMT) transforms healthcare through interconnected devices enabling real-time monitoring, diagnostics, and treatment. However, these devices often lack robust physical security, making them vulnerable to tampering, theft, and unauthorized access. This paper introduces SecureGuard-IIoMT, an innovative adaptive physical security framework designed to mitigate such vulnerabilities across diverse deployment environments. SecureGuard-IIoMT comprises three integrated components enhancing device security. The first, Adaptive Sensor-Based Intrusion Detection (ASID), utilizes vibration, proximity, and pressure sensors combined with lightweight machine learning models to detect unauthorized physical interactions in real-time. ASID maintains detection accuracy across varied conditions by dynamically adjusting its thresholds. The second component, Dynamic Tamper Evident Enclosure (DTE), is a self-healing smart enclosure equipped with a tamper detection circuit. Upon tampering detection, DTE triggers alerts, initiates self-healing to ensure continuous device operation, and logs detailed incident reports for further analysis. The third component, Blockchain-Powered Access Control System (BPACS), leverages blockchain technology to maintain decentralized, secure, and immutable access logs. Only authorized physical access requests are approved and recorded, preventing unauthorized interactions. Extensive simulations and real-world tests demonstrate that SecureGuard-IIoMT achieves an 85 % reduction in tampering risks and a 92 % decrease in unauthorized access attempts. Its lightweight, modular design ensures compatibility with various IIoMT devices without compromising performance or cost-effectiveness. SecureGuard-IIoMT effectively bridges critical security gaps in IIoMT device hardening, providing scalable solutions essential for securing healthcare infrastructures. Future work will focus on integrating quantum-resistant encryption into BPACS and employing advanced tamper-evident materials for enhanced security. Future work will focus on integrating quantum-resistant encryption into BPACS and employing advanced tamper-evident materials for enhanced security. The key contributions of this study include the design of an adaptive multi-sensor intrusion detection module (ASID), a tamper-evident self-healing enclosure (DTE), and a decentralized blockchain-based access control system (BPACS). Collectively, these components achieve an 85 % reduction in tampering risks and a 92 % decrease in unauthorized access attempts while maintaining lightweight and scalable deployment.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101653"},"PeriodicalIF":6.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279566","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":"Evaluating and enhancing intrusion detection systems in IoMT: The importance of domain-specific datasets","authors":"Jordi Doménech ,&nbsp;Olga León ,&nbsp;Muhammad Shuaib Siddiqui ,&nbsp;Josep Pegueroles","doi":"10.1016/j.iot.2025.101631","DOIUrl":"10.1016/j.iot.2025.101631","url":null,"abstract":"<div><div>The emergence of the Internet of Medical Things (IoMT) is revolutionizing healthcare delivery, but also introducing critical challenges to cybersecurity and patient safety. Intrusion Detection Systems (IDSs) enhanced by Machine Learning (ML) have emerged as a powerful solution to identify cyberattacks in these environments. However, existing studies often rely on general IoT datasets, potentially limiting their applicability in IoMT-specific scenarios. This study addresses these limitations by comparing the performance of ML models trained on a general IoT dataset (CICIoT2023) and an IoMT-specific dataset (CICIoMT2024) to demonstrate the importance of domain-specific data. Our findings reveal substantial drops of up to 66.87% in the F1-score when models trained on one dataset are tested on the other. Furthermore, the study critiques key dataset design choices in CICIoMT2024, and proposes baseline optimization techniques including uniform windowing, proper train-validation-test splits, adjustments in temporal dependencies for time series data, and improved dataset balancing. By applying these techniques, we observe significant improvements in IDS performance in comparison to other approaches, with scores of 0.9985 in model accuracy. The findings show the necessity of using IoMT-specific datasets and carefully designed preprocessing techniques to build robust IDSs tailored to the unique demands of medical IoT environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101631"},"PeriodicalIF":6.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069632","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":"Enhancing the performance of Industrial IoT LoRaWAN-enabled federated learning frameworks: A case study","authors":"Oscar Torres Sanchez ,&nbsp;Guilherme Borges ,&nbsp;Duarte Raposo ,&nbsp;André Rodrigues ,&nbsp;Fernando Boavida ,&nbsp;Jorge Sá Silva","doi":"10.1016/j.iot.2025.101632","DOIUrl":"10.1016/j.iot.2025.101632","url":null,"abstract":"<div><div>The ongoing development of Industrial Internet of Things (IIoT) smart systems is transforming industrial maintenance by improving operational efficiency. In this context, anomaly detection within IIoT architectures is crucial for early issue identification in industrial machinery. However, many systems generate vast sensor data while operating in environments with poor accessibility and network coverage, making centralized training impractical. Federated learning (FL) offers a solution by enabling distributed training on local devices, reducing bandwidth usage by transmitting models instead of raw data, and enhancing privacy. Despite these advantages, applying FL in IIoT resource-constrained devices — characterized by limited storage, processing capacity, and high-frequency heterogeneous data — remains challenging. This study showcases FL framework performance enhancement in LoRaWAN-enabled IIoT environments through optimized local machine data management. The improvements explore three key approaches: (1) techniques to manage high-variability, high frequency data from multiple sources via LoRaWAN-enabled prototypes, (2) an adaptive optimization approach addressing industrial machinery’s sensory diversity, and (3) strategies to reduce false alarms by refining the management system to categorize risk levels based on proximity to anomaly detection thresholds. The enhanced framework achieves an F1-score of 97%, TPR of 96%, and TNR of 80%, with the positive class representing normal conditions and the negative class indicating anomalies. Moreover, the false alarm reduction strategy decreases false positives by at least 72%, preventing values near the threshold from being misclassified as high risk anomalies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101632"},"PeriodicalIF":6.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089691","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":"Bioinspired small language models in edge systems for bee colony monitoring and control","authors":"Juan M. Nún̄ez V. ,&nbsp;Diana M. Giraldo ,&nbsp;Sebastián Gómez Segura ,&nbsp;Juan M. Corchado ,&nbsp;Fernando De la Prieta","doi":"10.1016/j.iot.2025.101633","DOIUrl":"10.1016/j.iot.2025.101633","url":null,"abstract":"<div><div>This paper proposes a hybrid IoT architecture based on Generative Artificial Intelligence (Gen-AIoT) for the intelligent monitoring and control of beehives, designed with processing capabilities both at the edge and in the cloud, thus adapting to environments with or without internet connectivity. Through an IoT sensor network, the system collects critical data on environmental parameters and hive conditions, such as temperature, humidity, wind speed, and hive weight, processing them locally at the edge or centrally in the cloud. The architecture incorporates a recommendation system that uses a small language model (SLM) to generate real-time alerts based on data provided by the IoT sensors. This system implements two distinct SLM models, Phi-3.5 and Tinyllama, enabling hardware performance measurement and optimizing efficiency for edge processing. To establish optimal environmental ranges, the recommendation system uses bio-inspired algorithms, such as ant colony optimization, genetic algorithms, and bee swarm algorithms. Additionally, LSTM neural networks are included to predict honey production and plan hive placement based on climate and weight projections, allowing for precise and personalized adjustments. This dual processing capability (edge and cloud) reduces the need for human intervention, optimizes hive inspection times, and minimizes false positives in monitoring, making it especially beneficial for large-scale beekeeping, where weekly inspection times can exceed 50 h. With this architecture, inspection time is reduced by 80%, significantly improving efficiency in hive management and promoting sustainable practices for bee conservation through intelligent agriculture.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101633"},"PeriodicalIF":6.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942424","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":"Memory-efficient and robust detection of Mirai botnet for future 6G-enabled IoT networks","authors":"Zainab Alwaisi","doi":"10.1016/j.iot.2025.101621","DOIUrl":"10.1016/j.iot.2025.101621","url":null,"abstract":"<div><div>The rise of 6G-enabled IoT networks has introduced significant challenges in securing resource-constrained devices against high-memory and energy-intensive cyber threats, such as the Mirai botnet. Due to their computational and memory overhead, existing Intrusion Detection Systems (IDS) and deep learning-based security mechanisms are often impractical for constrained IoT environments. This study proposes a TinyML-based real-time anomaly detection framework to classify and detect four distinct Mirai botnet attack types: Scan, UDP flooding, TCP flooding, and ACK flooding while analysing their impact on IoT device memory consumption and security.</div><div>To address the trade-off between detection accuracy, memory efficiency, and inference time, Naïve Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbours (KNN) classifiers optimized for TinyML deployment are implemented and compared. Experimental results demonstrate that KNN achieves detection accuracy above 99%, while maintaining low memory usage, making it the most suitable choice for real-time security in constrained IoT environments. Conversely, NB and RF offer superior inference speed with lower computational overhead, presenting a trade-off between detection latency and resource efficiency. Additionally, analysis reveals that Mirai botnet-induced memory consumption leads to increased fragmentation, excessive RAM usage, and higher energy consumption, highlighting the need for adaptive security mechanisms. This framework provides a lightweight, memory-efficient solution for enhancing security in 6G-enabled IoT ecosystems, with potential applications in smart cities, smart homes, and Industry 4.0. By integrating memory-aware ML models, this work contributes critical insights into developing scalable cybersecurity frameworks to ensure resilience against evolving cyber threats.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101621"},"PeriodicalIF":6.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089690","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":"Intent-based approaches for industry 4.0 applications: A systematic mapping study","authors":"Kaoutar Sadouki,&nbsp;Elena Kornyshova","doi":"10.1016/j.iot.2025.101629","DOIUrl":"10.1016/j.iot.2025.101629","url":null,"abstract":"<div><div>In the context of Industry 4.0, Intent-Based Approaches capture high-level industrial objectives, transforming them into executable tasks that align with digital workflows. An intent is defined as a desired outcome or business objective. Despite the growing importance of intent-based approaches, there is a lack of comprehensive understanding of their application to Industry 4.0. To address this, we conducted a systematic mapping study using a structured framework to examine existing intent-based approaches in the literature. Our study provides a comprehensive overview of current intent-based research in Industry 4.0 and reveals a growing interest in this field, especially in manufacturing, robotics, and networking. The study highlights the variety of intent structures, types, usage goals, and methods used. Intent-based approaches would bridge the gap between industrial goals and I4.0 components configuration, which play a key role in the digital transformation of smart industries. Our structured analysis framework and results provide essential understanding serving as a foundation for advancing intent-based approaches tailored to the needs of Industry 4.0 components.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101629"},"PeriodicalIF":6.0,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942425","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":"Web access as a service for CSA matter protocol: Bridging matter and the W3C Web of Things framework for smart home interoperability","authors":"Huy-Trung Nguyen ,&nbsp;Van-Ha Pham ,&nbsp;Viet-Thang Vu ,&nbsp;Thanh-Trung Nguyen","doi":"10.1016/j.iot.2025.101618","DOIUrl":"10.1016/j.iot.2025.101618","url":null,"abstract":"<div><div>The rapid proliferation of smart home appliances has highlighted the growing need for enhanced interoperability across diverse IoT ecosystems. The Matter protocol, emerging as a global standard for smart home devices, provides a unified communication framework, while the W3C Web of Things (WoT) framework facilitates the seamless integration of IoT devices through web technologies. Despite the potential benefits, the interworking between Matter and WoT remains an underexplored area, which, if addressed, could substantially improve the accessibility and interoperability of smart home systems. This paper introduces a novel approach for integrating Matter-enabled devices with the W3C Web of Things, ultimately enabling Web Access as a Service for Matter devices. We propose a comprehensive solution that makes Matter devices discoverable and interactable within the WoT ecosystem. The proposed solution comprises: (1) a Thing model for Matter and an adaptive translation algorithm that maps Matter device specifications to WoT concepts, (2) a Matter controller that exposes Matter devices as WoT Thing Descriptions, enabling bi-directional communication between Matter devices and WoT-based applications, and (3) an extensive evaluation to assess the effectiveness of the integration. The results indicate that the proposed solution is both feasible and practical for deployment in real-world settings. This approach lays the groundwork for a more unified and user-friendly smart home experience, thereby advancing the potential for smart home ecosystems in broader, cross-domain contexts.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101618"},"PeriodicalIF":6.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929512","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":"On-street parking space localization with deep learning using low-quality images from public cameras","authors":"José Ángel Morell,&nbsp;Gabriel Luque,&nbsp;Enrique Alba","doi":"10.1016/j.iot.2025.101619","DOIUrl":"10.1016/j.iot.2025.101619","url":null,"abstract":"<div><div>The increasing demand for new services in cities leads to challenges that need an intelligent, holistic approach (smart cities). A crucial aspect of smart city planning is effectively managing public on-street parking spaces, influencing overall urban mobility and environmental sustainability. However, detecting these spaces is complex, often requiring costly cameras or sensors, and the variability in parking space sizes, depending on the vehicles parked, adds to the difficulty. Existing city cameras for traffic monitoring could be a solution, but their low image quality and frequent movements (taking images from different angles) make accurate detection challenging. We propose a novel method for locating on-street parking spaces using low-quality images from non-static public traffic cameras. This approach is dataset-independent, applicable to various cities, and employs deep-learning models pre-trained for tasks like vehicle detection, repurposing them for the novel task of identifying on-street public parking spaces. This method avoids specific retraining and intensive manual labeling. Tested in Malaga, Spain, the pipeline includes Extraction (sourcing images from Internet traffic cameras), Matching (recognizing common features between reference and new images for detecting camera movements), Preprocessing (comparing different denoising and image-enhancing techniques for improving model inference), Detection (using models like YOLOv8 and Detectron2 for vehicle detection), and Postprocessing (transforming perspectives to estimate real-world parking space coordinates and sizes). Experimental results demonstrate that our proposal achieves accurate parking space detection even in extreme light conditions and camera movements, providing a valuable new tool for parking management and urban planning.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101619"},"PeriodicalIF":6.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936447","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":"Blockchain-enabled road vehicle emissions monitoring: A secure, scalable and private framework","authors":"Dermot O’Brien,&nbsp;Vasileios Christaras,&nbsp;Ioannis Kounelis,&nbsp;Igor Nai Fovino,&nbsp;Georgios Fontaras","doi":"10.1016/j.iot.2025.101628","DOIUrl":"10.1016/j.iot.2025.101628","url":null,"abstract":"<div><div>Accurate vehicle emissions monitoring is essential for evaluating environmental impact and ensuring regulatory compliance. However, current monitoring systems primarily rely on periodic inspections and manufacturer-provided data; approaches with inherent limitations that can impact accuracy and provide limited opportunities for real-time verification. In the evolving landscape of connected vehicles, securely transmitting emissions data to regulatory authorities is therefore vital for accurate environmental monitoring and compliance. To address these shortcomings, we propose a blockchain-enabled framework using Hyperledger Fabric, which ensures data integrity, authenticity, and auditability without relying on centralised trust. Compared to our prior setup reaching about 250 transactions per second (TPS), our revised consensus policy and improved client simulation achieve a throughput of 360 TPS representing a 44% increase under large-scale conditions involving 27 Member States (MS). We employed the Experimental Platform for Internet Contingency (EPIC) infrastructure to emulate realistic network topologies, simulating up to 5,400 simultaneous vehicle clients and handling data from 280 million vehicles reporting annually. By integrating secure vehicle identity management with GDPR-compliant off-chain data storage, our solution addresses the transparency and manipulation gaps present in current systems. These findings show blockchain’s viability for large-scale, real-time vehicular emissions reporting, contributing to more trustworthy and sustainable transport infrastructures.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101628"},"PeriodicalIF":6.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929511","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 efficient and versatile Digital Twin model implementation for autonomous connected vehicles based on distributed, low-latency working memory","authors":"Noé Zapata,&nbsp;Gerardo Pérez-González,&nbsp;Pablo Bustos,&nbsp;Sergio Barroso,&nbsp;Pedro Núñez","doi":"10.1016/j.iot.2025.101627","DOIUrl":"10.1016/j.iot.2025.101627","url":null,"abstract":"<div><div>The growing interest in Connected Autonomous Vehicles (CAVs) has led to increased focus on technologies and algorithms that improve their behaviour, comfort, and safety. Central to these advancements is the application of Digital Twin (DT) models, an evolution of Cyber–Physical Systems (CPSs) that has attracted considerable attention in the scientific community. These DTs offer many possibilities by linking real-world activities with their twin counterparts, allowing for the anticipation of scenarios to prevent or improve the handling of different situations. This paper proposes a DT model paradigm for CAVs, supported by a distributed architecture of software agents. This architecture, named CORTEX, forms the core of our DT model and is characterised by its synchronisation capabilities, shared memory, versatility, performance and scalability. The proposed solution combines this distributed architecture with CARLA as its internal simulator. It uses probabilistic models to regulate and select optimal simulations for predicting risky situations during driving, among other capabilities. To validate our proposed DT model, we also present an algorithm that facilitates early detection of potential collisions between autonomous vehicles and pedestrians on their path by generating and simulating traffic scenes unsupervised and applying a particle filter-based methodology to evaluate risk situations. The results show that the proposed DT framework can effectively apply to autonomous driving systems. The DT architecture has been tested by a real electric autonomous vehicle on a university campus, demonstrating its effectiveness in anticipation and safe real-time decision-making.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101627"},"PeriodicalIF":6.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942442","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}