Internet of Things最新文献

{"title":"Enhancing IEEE 1588 PTP security for IIoT networks: A lightweight attack detection and mitigation framework","authors":"Zeba Idrees ,&nbsp;Shahid Latif ,&nbsp;Hira Tahir ,&nbsp;Lirong Zheng","doi":"10.1016/j.iot.2025.101669","DOIUrl":"10.1016/j.iot.2025.101669","url":null,"abstract":"<div><div>Highly precise clock synchronization is an important aspect of the Industrial Internet of Things (IIoT) network because desynchronized clocks among nodes in IIoT can degrade system performance and even lead to system failure. IEEE 1588 Precision Time Protocol (PTP) is widely used in such time-sensitive networks. Resource efficiency and security have become the most important concerns in designing PTP for IIoT applications. PTP provides unified and high-precision time, whereas it is resource inefficient and insecure in its current form, particularly for resource-constrained IoT devices, such as battery powered sensing nodes. To this end, this paper aims to advance the existing PTP to improve security for IIoT networks without involving complex and power-consuming cryptographic algorithms. We study and analyze the potential cyber-attacks that can affect the security and synchronization of the PTP network. Considering the limitations of the PTP security defined by IEEE 1588 in its Annex K, we propose a security extension to the PTP algorithm. This security model covers the full PTP attack surface and allows the detection of attacks on all the PTP nodes in a timely manner. Along with the attack detection, we establish an attack mitigation model to mitigate the attack effects on Master PTP nodes. The proposed secure PTP model was evaluated under different network conditions and with varying important parameters. It was observed that newly introduced functions do not compromise synchronization accuracy. All the experimental evaluations demonstrate that the proposed approach is more secure and robust to cyber-attacks and does not affect the operation of PTP devices in all considered network configurations.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101669"},"PeriodicalIF":6.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330968","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":"LT-YOLOv10n: A lightweight IoT-integrated deep learning model for real-time tomato leaf disease detection and management","authors":"Abdelaaziz Bellout ,&nbsp;Mohamed Zarboubi ,&nbsp;Mohamed Elhoseny ,&nbsp;Azzedine Dliou ,&nbsp;Rachid Latif ,&nbsp;Amine Saddik","doi":"10.1016/j.iot.2025.101663","DOIUrl":"10.1016/j.iot.2025.101663","url":null,"abstract":"<div><div>The challenges posed by a growing global population and the impacts of climate change have intensified concerns about food security, particularly in agriculture. This study introduces LT-YOLOv10n, a lightweight and efficient deep learning model tailored for detecting and localizing tomato leaf diseases. The model incorporates advanced architectural features, such as Convolutional Block Attention Modules (CBAM) and C3f layers, to improve feature extraction and emphasize disease-relevant areas. By adopting a reduced depth and width scaling approach, LT-YOLOv10n achieves high detection accuracy while ensuring computational efficiency, making it ideal for use on devices with limited resources.</div><div>The LT-YOLOv10n model was thoroughly tested against leading models, showcasing competitive performance in key areas like accuracy, inference speed, and parameter efficiency. It achieved an mAP50 of 98.7% on the test dataset and an inference speed of 87.28 FPS on the Jetson Orin Nano, demonstrating its effectiveness for real-time applications. Furthermore, the model was deployed in a mobile application, enabling real-time disease detection and offering actionable pesticide recommendations. The application integrates with ThingsBoard, an open-source IoT platform, to centralize prediction data and support remote monitoring through an intuitive dashboard. Features such as disease mapping, image-based predictions, and customized pesticide suggestions provide a comprehensive farm management solution.</div><div>This integrated system equips farmers with accessible, cost-effective tools for timely disease management, enhancing crop health and productivity while supporting sustainable agricultural practices. LT-YOLOv10n represents a significant step forward in agricultural AI, offering a scalable and efficient solution for precision farming.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101663"},"PeriodicalIF":6.0,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313885","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 integrated IDS for the Internet of Vehicles using a Large Language Model framework","authors":"Aishwarya R.,&nbsp;Vetriselvi V.,&nbsp;Naveen Srinivas,&nbsp;Ashwin Muthuraman A.","doi":"10.1016/j.iot.2025.101666","DOIUrl":"10.1016/j.iot.2025.101666","url":null,"abstract":"<div><div>The Internet of Vehicles (IoV) has expanded through the integration of VANET (Vehicular Ad hoc Network) and IoT (Internet of Things) technologies within the Intelligent Transportation System domain, facilitated by the advancement of Beyond 5G communication technology. Recently, smart vehicles, such as connected vehicles, have become increasingly prevalent due to technological advancements. These vehicles engage in communication with other IoV components, rendering them susceptible to various attacks. Ensuring the security of connected vehicles is crucial to mitigate vulnerabilities within the IoV environment, as cyber–physical threats could pose life-threatening consequences. Therefore, anomaly and attack detection mechanisms are imperative to safeguard the IoV environment. This paper proposes a Generative AI-based Intelligent Integrated Intrusion Detection System tailored for IoV, considering multiple communication dimensions. Typically, attackers may target both the in-vehicle network such as CAN (Controller Area Network) BUS, and various external networks such as DSRC (Dedicated Short-Range Communication), CV2X (Cellular Vehicle-to-Everything) of smart connected vehicles. Thus, an Intrusion Detection System (IDS) focusing on multi-communication dimension attacks on smart vehicles is developed to enhance safety, thereby preventing collisions and chaos. The TON_IoT dataset and CICIoV2024 dataset are used in this study to assess the proposed approach for detecting intra and inter-vehicular network attacks. The proposed work achieves promising results, having a high accuracy of 98% with a 96% detection rate and a high F1 score of 0.97.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101666"},"PeriodicalIF":6.0,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364854","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":"Smart systems: A review of theory, applications, and recent advances","authors":"Naseem Alsadi ,&nbsp;Waleed Hilal ,&nbsp;Alex McCafferty-Leroux ,&nbsp;S.A. Gadsden ,&nbsp;John Yawney","doi":"10.1016/j.iot.2025.101667","DOIUrl":"10.1016/j.iot.2025.101667","url":null,"abstract":"<div><div>Rapid technological advancements have permeated numerous professional fields, transforming mundane tasks and complex operations alike, with examples evident in smart cities, healthcare, and various industries. As a result, a significant surge in the literature concerning smart systems is observed, as is the rise of pragmatic implementations of such systems. In this comprehensive survey paper, we decompose the cumulative smart system architecture into five fundamental components, namely: control, perception, knowledge, communication, and security. Inspired by the underlying notions of cognitive dynamics theory, each component is discussed in detail and categorized, thoroughly detailing necessary concepts and functionality. To add, we discuss the state of the art with respect to each of these components and the most impactful applications of smart systems. From this, gaps in smart systems literature can be identified, where future work is proposed to rectify shortcomings in published methods. This work therefore has foremost utility to those investigating smart systems from an academic standpoint, with the goal of examining the smart system taxonomy and the most modern methods. In addition to further defining the smart system framework, our analysis concluded that the most increasingly researched, and most important components in advancing smart systems applications are knowledge and security. Primarily, this is motivated by aspirations towards safe, adaptive, and robust data-driven autonomy in large scale systems. We conclude that blockchain, IoT, and machine learning protocols and technologies are continuously developing topics that will be essential in smart system advancement.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101667"},"PeriodicalIF":6.0,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321703","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 rendezvous of computing and communication services at the optical layer in optical computing–communication integrated network","authors":"Dao Thanh Hai ,&nbsp;Isaac Woungang","doi":"10.1016/j.iot.2025.101668","DOIUrl":"10.1016/j.iot.2025.101668","url":null,"abstract":"<div><div>With the significant advancements in optical computing platforms recently capable of performing various primitive operations, a seamless integration of optical computing into very fabric of optical communication links is envisioned, paving the way for the advent of <em>optical computing–communication integrated network</em>, which provides computing services at the ligthpath scale, alongside the traditional high-capacity communication ones. This necessitates a paradigm shift in optical node architecture, moving away from the conventional optical-bypass design that avoids lightpath interference crossing the same node, toward leveraging such interference for computation. Such new computing capability at the optical layer appears to be a good match with the growing needs of geo-distributed machine learning, where the training of large-scale models and datasets spans geographically diverse nodes, and intermediate results require further aggregation/computation to produce the desired outcomes for the destination node. To address this potential use case, an illustrative example is presented, which highlights the merit of providing in-network optical computing services in comparison with the traditional optical-bypass mode in the context of distributed learning scenarios taking place at two source nodes, and partial results are then optically aggregated to the destination. We then formulate the new <em>routing, wavelength and computing assignment problem</em> arisen in serving computing requests, which could be considered as an extension of the traditional routing and wavelength assignment, that is used to accommodate the transmission requests. Simulation results performed on the realistic COST239 topology demonstrate the promising spectral efficiency gains achieved through the <em>optical computing–communication integrated network</em> compared to the optical-bypass model.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101668"},"PeriodicalIF":6.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297096","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":"UoCAD2: An unsupervised online contextual anomaly detection approach using optimized hyperparameters of RNNs for multivariate time series","authors":"Aafan Ahmad Toor,&nbsp;Jia-Chun Lin,&nbsp;Ernst Gunnar Gran","doi":"10.1016/j.iot.2025.101664","DOIUrl":"10.1016/j.iot.2025.101664","url":null,"abstract":"<div><div>Internet of Things (IoT) based smart devices are gradually becoming part of daily lives through their increasing usage in industry, healthcare, agriculture, environmental monitoring, energy, transportation, and smart cities, buildings, and homes. IoT devices generate fast-paced time-bound data known as time series. Time series often contain anomalies, i.e., unusual patterns or deviations from the norm, that can disrupt services and must be detected quickly. Many researchers have tried to detect unlabeled anomalies by employing unsupervised online anomaly detection approaches based on Recurrent Neural Networks (RNN). RNNs are specially designed to process sequential data. However, selecting the right type of RNN and appropriate hyperparameters for a specific data domain is challenging. Another challenge in the online processing of time series is to pick out an appropriate sliding window size, that is small enough to process the incoming data in a limited time and large enough to capture the underlying deviations in the data. This study extends the Unsupervised Online Contextual Anomaly Detection (UoCAD) approach to overcome these challenges by proposing UoCAD2. UoCAD2 conducts hyperparameter optimization on six RNN variants in an offline phase and uses fine-tuned hyperparameters to detect anomalies during the online phase. The experiments evaluate the proposed framework on three IoT datasets containing contextual anomalies. Precision, Recall, F1 score, and detection time are the evaluation metrics used in this study. This study recommends selecting the best combination of RNN-based models, optimal hyperparameters, and window sizes for contextual anomaly detection in multivariate time series data.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101664"},"PeriodicalIF":6.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313910","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 face recognition attendance system utilizing real-time face tracking","authors":"Emmanuel Bugingo ,&nbsp;Obed Imbahafi ,&nbsp;Athnatius Caius Umeonyirioha ,&nbsp;Tohari Ahmad ,&nbsp;Ntivuguruzwa Jean De La Croix ,&nbsp;Anne Marie Uwumuremyi","doi":"10.1016/j.iot.2025.101660","DOIUrl":"10.1016/j.iot.2025.101660","url":null,"abstract":"<div><div>Manual roll calls and existing biometric attendance systems, which capture attendance only at the start or end of class, are prone to inaccuracies such as proxy attendance and fail to monitor students’ presence throughout the sessions in Schools. This study proposes an enhanced face recognition attendance system utilizing real-time face tracking to ensure accuracy and reliability in attendance tracking. The system captures facial data using OpenCV for detection and a CNN-based library for recognition, logging attendance at 30 min intervals. A minimum presence of 80% of the session must be marked present. Attendance records are synchronized in real time using Firebase, and insights are generated using Plotly for visual analytics. The system achieves a recognition accuracy of 94% under optimal conditions and demonstrates robustness under varying environments. Comparative analysis with existing algorithms highlights its improved scalability and usability, significantly advancing over traditional methods.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101660"},"PeriodicalIF":6.0,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313911","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":"IoT-based system for individual dairy cow feeding behavior monitoring using cow face recognition and edge computing","authors":"Yueh-Shao Chen ,&nbsp;Dan Jeric Arcega Rustia ,&nbsp;Shao-Zheng Huang ,&nbsp;Jih-Tay Hsu ,&nbsp;Ta-Te Lin","doi":"10.1016/j.iot.2025.101674","DOIUrl":"10.1016/j.iot.2025.101674","url":null,"abstract":"<div><div>This study presents an IoT-enabled cow face recognition system leveraging edge computing to enable real-time, automated monitoring of individual cow feeding behavior. The system integrates a lightweight YOLOv4-tiny model for cow face detection with MobileNetV2 for feature extraction, optimized for embedded devices with limited computational power. A key innovation is the incorporation of few-shot learning (FSL), allowing the system to adapt efficiently to newly introduced cows with minimal training data. The algorithm achieved robust performance, with an F1-score of 0.98 for detection and a recognition accuracy of 0.97 using FSL. Feeding times estimated by the system were validated against manually observed data, demonstrating high precision with a mean absolute error (MAE) of 1.7 min per cow. Long-term experiments conducted under varying seasonal conditions showcased the system's effectiveness in monitoring feeding behavior year-round. Results revealed significant seasonal differences, with cows feeding longer in winter (197.0 min/day) than in summer (115.5 min/day), likely due to the effects of heat stress during warmer months. This IoT-driven system offers scalable, non-invasive monitoring solutions for dairy farm environments, enabling real-time insights to support herd management, early health issue detection, and individualized feeding strategies. By integrating advanced IoT technologies with agricultural practices, this system provides a pathway to enhancing productivity and animal welfare in precision dairy farming.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101674"},"PeriodicalIF":6.0,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262799","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 deep transfer learning-based blockchain-assisted cooperative network architecture for internet of unmanned any vehicle things","authors":"Anik Islam ,&nbsp;Md Masuduzzaman ,&nbsp;Soo Young Shin","doi":"10.1016/j.iot.2025.101659","DOIUrl":"10.1016/j.iot.2025.101659","url":null,"abstract":"<div><div>An Internet of Unmanned Any Vehicle Things (IUxVTs) enables cooperative operations among different unmanned vehicles, providing enhanced mission efficiency such as extended coverage, especially with the support of Internet of Things (IoT) sensors, edge computing, and dew computing. However, IUxVT communication encounters significant security and connectivity challenges. Conventional deep learning models are difficult to deploy effectively in dynamic mission environments due to their inability to adapt rapidly without extensive retraining, especially in remote areas with limited connectivity. To address these issues, this paper proposes a novel deep transfer learning (DTL)-based cooperative network architecture integrated with blockchain technology. Specifically, a lightweight blockchain and nonce-based authentication scheme were adopted to enhance protection against security threats, including spoofing, tampering, and unauthorized access. The DTL approach facilitates real-time model adaptation for IUxVTs without the need for extensive retraining, leveraging a dew computing-based delay-tolerant network for secure data storage and transmission. Experimental validation through a practical disaster rehabilitation and recovery scenario demonstrates that the proposed scheme significantly outperforms conventional methods, achieving over 97% model accuracy within fewer training epochs and reducing the training time by more than 30%. Additionally, the scheme effectively counters cybersecurity threats, showcasing robust resilience against unauthorized access and ensuring secure, low-latency data processing in dynamic and resource-constrained environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101659"},"PeriodicalIF":6.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253540","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":"CRYSTALS-Dilithium post-quantum cyber-secure SoC for wired communications in critical systems","authors":"Armando Astarloa,&nbsp;Jesús Lázaro,&nbsp;José Ignacio Gárate","doi":"10.1016/j.iot.2025.101656","DOIUrl":"10.1016/j.iot.2025.101656","url":null,"abstract":"<div><div>Critical systems in the energy industry and aerospace are the backbone of modern society and national defense. These systems are becoming heterogeneous computing and networking infrastructures composed of Edge located, Fog, and Cloud control devices. Strict coordination and reliable networking are required to orchestrate the tasks and actions controlled by multiple devices. The well-known Ethernet standard for inter and intra sub-system networking is evolving to Time-Sensitive Networking (TSN). Regarding the security at the link level in this networking, the industry has selected MACsec as the technology to protect hard-real time traffic, in general and TSN, in particular.</div><div>The extensive application of TSN will intersect with the post-quantum attack landscape in the future. As a result, it becomes imperative to conduct research on security solutions capable of effectively addressing these emerging threats. A quantum attack represents a novel and significant threat to network security. And, to operate MACsec in a post-quantum scenario, it is necessary to analyze the cipher suites for symmetric and asymmetric cryptography and used in MACsec (standard IEEE 802.1AE) and MKA (IEEE 802.1X).</div><div>In the Post-Quantum Cryptography Standardization process, The National Institute of Standards and Technology has selected for public-key encryption and key-establishment algorithm CRYSTALS–KYBER. Additionally, the selected digital signature algorithms for standardization include CRYSTALS-Dilithium.</div><div>This work contributes with a novel concept-proof semiconductor implementation that fulfill the requirements in terms of power-consumption, resources utilization and PQC security level for Industrial IoT applications. The presented research analyzes the resources required by a high-performance CRYSTALS-Dilithium implementation on IIoT SoC devices. Firstly, the architecture and implementation of RTL-based CRYSTALS-Dilithium IP are presented and discussed. Secondly, a System-on-Chip semiconductor device composed of a RISC-V CPU subsystem and the CRYSTALS-Dilithium IP is developed in the scope of this research as a concept-prof to evaluate the viability of integrating PQC on resource-constrained devices for IIoT.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101656"},"PeriodicalIF":6.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279172","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}