Internet of Things最新文献

{"title":"Real-time efficiency of YOLOv5 and YOLOv8 in human intrusion detection across diverse environments and recommendation","authors":"Ali Hassan Sodhro,&nbsp;Sathwik Kannam,&nbsp;Michel Jensen","doi":"10.1016/j.iot.2025.101707","DOIUrl":"10.1016/j.iot.2025.101707","url":null,"abstract":"<div><div>Intrusion Detection Systems (IDS) are essential for securing areas such as industrial and construction sites. However, when implementing IDS as a service, confidence scores (confidence) provided by YOLOv8 are the most reliable metric as compared to the YOLOv5 available to take appropriate actions to secure these sites and prevent intruders. However, prior research has focused on YOLO’s human detection capabilities (whether it can detect or not), neglecting real-time performance in IDS. To address this gap, we propose and present comparative analysis of YOLOv5 and YOLOv8 in a real-time across diverse environmental conditions (luminance, indoor/outdoor, simulated weather). Our findings reveal an average performance of YOLOv5 (outdoor: 90.5%, indoor: 79.1%), YOLOv8 (outdoor: 99.1%, Indoor: 77.2%) confidence in real-time, with a logarithmic relationship between luminance and confidence. Outdoor environments perform better then indoor for both YOLOv5 and YOLOv8, while adverse weather conditions significantly reduce YOLOv8’s effectiveness and increase the efficiency of YOLOv5. Therefore, this enables IDS integrators to adjust minimum confidence thresholds to minimize the risk of preventing potential intruders. However, the consistent and inconsistent confidence scores by both YOLOv8 and YOLOv5 respectively, and impact of weather remains inconclusive due to simulated fog.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101707"},"PeriodicalIF":6.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711350","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 secure and efficient task allocation for IoT networks using enhanced fuzzy reptile search algorithm","authors":"Vinay Maurya ,&nbsp;Vinay Rishiwal ,&nbsp;Mano Yadav ,&nbsp;Preeti Yadav ,&nbsp;Rashmi Chaudhry","doi":"10.1016/j.iot.2025.101708","DOIUrl":"10.1016/j.iot.2025.101708","url":null,"abstract":"<div><div>The Internet of Things(IoT) network is rapidly expanding, and the authentication and task allocation challenges between IoT devices, sensors, nodes, and gateways are highly complex. Traditional authentication schemes and task allocation methods frequently require increased scalability to address the resource constraints inherent in IoT devices. This paper presents a blockchain-based framework for secure and efficient task allocation in IoT networks that employs the Enhanced Fuzzy Reptile Search Algorithm (EFRSA<span><math><mo>−</mo></math></span>TA). The proposed framework uses Blockchain Technology to authenticate IoT devices via Smart contracts and Blockchain cryptography digital signatures (BCDS), ensuring task allocation security and integrity. Once authenticated via blockchain, tasks are distributed to devices and sensors using EFRSA<span><math><mo>−</mo></math></span>TA, which optimizes distribution based on resource availability, device location, and task priority. EFRSA<span><math><mo>−</mo></math></span>TA operates in two phases. First, it uses fuzzy logic to categorize task priorities, improving scheduling adaptability and responsiveness. In the second phase, an Enhanced Fuzzy Reptile Search Algorithm (EFRSA) and a novel validation function are used to offload tasks that exceed a device’s processing power and current workload. Blockchain Cryptography Digital Signature (BCDS) is compared to the existing ECC, HMAC, KCDH, LAKA and JWT algorithms to assess the framework’s effectiveness. On the other hand, EFRSA<span><math><mo>−</mo></math></span>TA is compared with several state-of-the-art optimization algorithms. Simulation results show that BCDS and EFRSA-TA significantly outperform these algorithms regarding Authentication time, false acceptance rate (FAR), Uptime &amp; error rate, blockchain overhead, framework scalability analysis, task allocation rate, throughput, energy consumption, and CPU utilization, confirming its superiority in authentication and optimizing task allocation within IoT networks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101708"},"PeriodicalIF":6.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711352","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":"Survey of IoT multi-protocol gateways: Architectures, protocols and cybersecurity","authors":"Salma H. Abdelwahed ,&nbsp;Ibrahim M. Hefny ,&nbsp;Mohamed Hegazy ,&nbsp;Lobna A. Said ,&nbsp;Ahmed Soltan","doi":"10.1016/j.iot.2025.101703","DOIUrl":"10.1016/j.iot.2025.101703","url":null,"abstract":"<div><div>The Internet of Things (IoT) is expanding rapidly, and IoT gateways are essential for connecting various devices and networks. Multi-protocol IoT gateways support multiple communication technologies, enabling interoperability across diverse IoT ecosystems. This survey paper investigates the hardware design, software components, and key functions of multi-protocol gateways. It provides an overview of their communication protocols, focusing on wireless technologies such as Wi-Fi, Bluetooth, Zigbee, LoRa, and 4G. Additionally, the paper discusses cybersecurity measures, including encryption, authentication, and protection against cyber threats. Both academic research and commercial IoT gateways are reviewed to present a comprehensive picture. This study identifies gaps in current research, highlighting the need for stronger cybersecurity implementation, improved energy management, and the integration of smarter systems using artificial intelligence (AI). The paper discusses challenges such as scalability, standardization, evaluation, and compatibility among various technologies. It highlights important areas for enhancing IoT gateway design by summarizing recent developments. The findings will assist researchers, developers, and industry professionals in creating more secure, efficient, and adaptable IoT gateways for the future.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101703"},"PeriodicalIF":7.6,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144756920","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":"Dynamic transmission adaptation algorithms for battery-free LoRaWAN networks","authors":"Fabrizio Giuliano ,&nbsp;Antonino Pagano ,&nbsp;Daniele Croce ,&nbsp;Gianpaolo Vitale ,&nbsp;Ilenia Tinnirello","doi":"10.1016/j.iot.2025.101706","DOIUrl":"10.1016/j.iot.2025.101706","url":null,"abstract":"<div><div>Demand for sustainable IoT solutions has increased over the years, with energy-harvesting technologies coming to the fore, and environmental-powered sensors gaining much importance. Indeed, the benefits can be outstanding for batteryless sensors in terms of increased durability, reduced maintenance (no need for battery replacement), and higher resistance to environmental factors. However, such batteryless devices must be accurately designed to cope with time-varying energy sources, such as solar or wind power. In particular, this work investigates adaptive transmission algorithms to optimize the performance and lifetime of LoRa-based batteryless IoT sensors. First, a thorough characterization is carried out concerning the device’s power consumption, focusing on both sensor measurement and data transmission operations. The performed analysis takes into account also different network scenarios, considering possible changes of the device parameters. Second, a transmission adaptation scheme for the optimizing data transmission intervals, named <em>Uniform Transmission Adaptation</em> (UTA), is proposed. Finally, tailored energy storage solutions are developed, depending on the available energy capacity and considering direct coupling and the use of renewable sources, like photovoltaic cells. Through large-scale simulations in a massive IoT scenario, we quantitatively assess network performance, energy consumption and network efficiency. Simulations show that in massive network conditions, the Packet Delivery Ratio (PDR) reaches 87% with UTA, compared to about 70% achieved with fixed interval transmission strategies. Furthermore, the loss of energy productivity (LoEP) in the fixed transmission scenario is around 3.75% during winter, whereas with UTA it is reduced to near 0%, demonstrating a reduction in energy losses. The findings provide a basis for the design of sensor devices with optimal energy management, in order to meet given reliability requirements, and tackling important challenges of batteryless IoT networks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101706"},"PeriodicalIF":6.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687258","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 novel fragment duplication attacker identification scheme using Discrete Event System based intrusion detection","authors":"Dipojjwal Ray ,&nbsp;Pradeepkumar Bhale ,&nbsp;Santosh Biswas ,&nbsp;Pinaki Mitra ,&nbsp;Sukumar Nandi","doi":"10.1016/j.iot.2025.101699","DOIUrl":"10.1016/j.iot.2025.101699","url":null,"abstract":"<div><div>Secure mechanisms protect IoT-6LoWPAN from external attackers, yet, lack of authentication capabilities and the scarcity of resources render the 6LoWPAN susceptible to various design-level internal attacks. Especially, the fragmentation mechanism is easily exploited by replaying spoofed fragments, timely slipped in by an eavesdropping attacker. Neither the original fragment nor the sender node authenticity is differentiable here, making most solution techniques challenging given the resource constrained environment. Current techniques have mostly employed mitigation methods like buffer quarantine and logical node isolation. However they are either incomplete or incur high computational overhead, since the duplicate fragment is replayed. In this paper, a probing based mechanism for attack node localization is proposed. Attack node is differentiable from normal nodes using the probing technique. Our proposed scheme is decentralized, utilizing a set of DES based IDS. Moreover, we eliminate the localized node using the kill switch mechanism to secure the 6LoWPAN. Completeness and correctness of our approach is proved and we implement it in simulation as well as real testbed. The results are observed to be superior to existing works. Minimum false positives and an accuracy over 99.8% is shown to be achieved while identifying the malicious nodes. Nonetheless, our scheme is energy efficient and takes lower detection time.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101699"},"PeriodicalIF":7.6,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886660","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":"Fast and low cost FPGA-based architecture for arrhythmia detection with CNN","authors":"Luca Greco,&nbsp;Francesco Moscato,&nbsp;Pierluigi Ritrovato,&nbsp;Mario Vento","doi":"10.1016/j.iot.2025.101705","DOIUrl":"10.1016/j.iot.2025.101705","url":null,"abstract":"<div><div>Deep Neural Networks have been applied in many fields and have exhibited extraordinary abilities. However, many challenges arise when dealing with embedded or low-resource computing architectures in different contexts like healthcare or IoT in Industry 4.0. In recent years, rapid growth has been seen in using machine learning techniques to interpret sensor data in healthcare applications. Convolutional Neural Networks (CNNs) are highly effective, but they have a significant drawback: they require large amounts of computational resources, usually available only “on the Cloud”. Edge and Fog nodes in healthcare applications (e.g. wearable sensors) are generally ill-suited to running CNN models with requirements like low computational resources, real-time execution, (very) low power consumption or low intrusiveness. In order to get through these difficulties, we propose a solution based on novel data-flow architectures and layer partitioning that enables fast classification in CNNs even when dealing with low resources. We apply our approach in developing a classifier (based on CNNs) for arrhythmia detection, which maintains good precision on low-power and low-cost FPGAs. We prove that the presented approach is general enough to distribute computation on parallel FPGAs too. Results show interesting performance improvements even when using low-resource hardware to implement the classifier.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101705"},"PeriodicalIF":6.0,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704548","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":"Threat detection in the 6G enabled Industrial IoT Networks using Deep Learning: A review on the state-of-the-art solutions, challenges and future research directions","authors":"Gaoyang Guo ,&nbsp;Faizan Qamar ,&nbsp;Syed Hussain Ali Kazmi ,&nbsp;Muhammad Habib ur Rehman","doi":"10.1016/j.iot.2025.101686","DOIUrl":"10.1016/j.iot.2025.101686","url":null,"abstract":"<div><div>The integration of the Industrial Internet of Things (IIoT) with sixth-generation (6G) communication technology is a critical foundation for the next generation of intelligent manufacturing and industrial automation. However, this advancement introduces significant security challenges, particularly in threat detection for IIoT systems. This paper systematically reviews existing research on threat detection in 6G-IIoT environments using Deep Learning (DL) techniques. It examines key challenges related to data processing, privacy protection, and model performance. The study first outlines the security requirements of IIoT within a 6G network environment and evaluates the application of various DL models for threat detection. It then identifies key limitations in current research, including dataset imbalance and the limited generalization capability of existing models. Finally, potential future research directions are discussed to advance the development of more intelligent and efficient threat detection mechanisms, ensuring the security and stability of IIoT systems in the 6G era.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101686"},"PeriodicalIF":6.0,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144665833","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":"Exploiting usage control for implementation and enforcement of security by contract","authors":"Marco Rasori ,&nbsp;Paolo Mori ,&nbsp;Andrea Saracino ,&nbsp;Alessandro Aldini","doi":"10.1016/j.iot.2025.101697","DOIUrl":"10.1016/j.iot.2025.101697","url":null,"abstract":"<div><div>The widespread adoption of IoT-based smart home technologies has transformed how people interact with their living spaces, offering greater control over everyday tasks. However, this increased connectivity introduces significant security challenges, particularly in managing applications that can control devices within the smart home. Users need effective ways to define and enforce security policies that permit or deny specific behaviors of these applications. Such policies should allow users to control what actions applications can perform, ensuring that they comply with security and privacy preferences. This paper proposes a hybrid framework that combines Security by Contract (S<span><math><mo>×</mo></math></span>C) and Usage Control (UCON) to address these challenges and provide a comprehensive security solution with low impact on system performance. S<span><math><mo>×</mo></math></span>C ensures verification of the application behavior, described formally as a contract, against predefined XACML-based policies. UCON enables continuous monitoring and enforcement of security policies during application execution. The theoretical foundations of the methodology combining these frameworks are based on labeled state/transition systems and their model-checking-based verification. Through experimental validation on a real testbed, we explore the feasibility of the proposed approach by evaluating its performance across various test campaigns, offering insights into its ability to manage policy enforcement and revocation processes with low overhead.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101697"},"PeriodicalIF":6.0,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713787","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 Variational Quantum Classifier for predictive analysis in industrial production","authors":"Antimo Angelino ,&nbsp;Enrico Landolfi ,&nbsp;Alfredo Massa ,&nbsp;Alfredo Troiano","doi":"10.1016/j.iot.2025.101695","DOIUrl":"10.1016/j.iot.2025.101695","url":null,"abstract":"<div><div>Quantum Computing (QC) is a novel and disruptive paradigm of computation that leverages the properties of quantum mechanical systems to represent and process information. The interest in this emerging technology and its applications has been growing in recent years, especially regarding Quantum Machine Learning (QML). In QML, QC and Machine Learning (ML) techniques are combined to build more powerful and accurate learning models. Industries and research centers worldwide have been devoting significant efforts to find use cases of practical interest for which QML may be a suitable approach. In this work, one of the most common QML algorithms, namely a Variational Quantum Classifier (VQC), has been adopted for a supervised classification task in defence industry. The goal is to predict the failures that may happen during the final acceptance test of a finished product, based on the knowledge of test data related to its subassemblies. The test data have been collected using advanced IoT systems and the prediction has been made before the final product was assembled, so to improve the efficiency in the testing process. The VQC has been applied to a problem already approached with classical ML techniques, and then the classical and quantum performances have been compared. The results indicate promising performances and highlight the potential of QML algorithms in the industrial sector for predictive analysis use.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101695"},"PeriodicalIF":6.0,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704549","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":"Deep Learning based Payload Optimization for Image Transmission over LoRa with HARQ","authors":"Khondoker Ziaul Islam ,&nbsp;David Murray ,&nbsp;Dean Diepeveen ,&nbsp;Michael G.K. Jones ,&nbsp;Ferdous Sohel","doi":"10.1016/j.iot.2025.101701","DOIUrl":"10.1016/j.iot.2025.101701","url":null,"abstract":"<div><div>LoRa is a wireless technology suited for long-range IoT applications. Leveraging LoRa technology for image transmission could revolutionize many applications, such as surveillance and monitoring, at low costs. However, transmitting images, through LoRa is challenging due to LoRa’s limited data rate and bandwidth. To address this, we propose a pipeline to prepare a reduced image payload for transmission captured by a camera in a reasonably static background, which is common in surveillance settings. The main goal is to minimize the uplink payload while maintaining image quality. We use a selective transmission approach where dissimilar images are divided into patches, and a deep learning Siamese network determines if an image or patch has new content compared to previously transmitted ones. The data is then compressed and sent in constant packets via HARQ to reduce downlink requirements. Enhanced super-resolution generative adversarial networks and principal component analysis are used to reconstruct the images/patches. We tested our approach with two surveillance videos at two sites using LoRaWAN gateways, end devices, and a ChirpStack server. Assuming no duty cycle restrictions, our pipeline can transmit videos—converted to 1616 and 584 frames—in 7 and 26 min, respectively. Increased duty cycle restrictions and significant image changes extend the transmission time. At Murdoch Oval, we achieved 100% throughput with no retransmissions required for both sets. At Whitby Falls Farm, throughput was 98.3%, with approximately 71 and 266 packets needing retransmission for Sets 1 and 2, respectively.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101701"},"PeriodicalIF":6.0,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653445","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}