Internet of Things最新文献

{"title":"Next-generation DRL empowered actor-critic schedulers for multipath QUIC in 5G vehicular IoT","authors":"Pattiwar Shravan Kumar ,&nbsp;Paresh Saxena ,&nbsp;Ozgu Alay","doi":"10.1016/j.iot.2025.101616","DOIUrl":"10.1016/j.iot.2025.101616","url":null,"abstract":"<div><div>The advent of 5G and beyond 5G (B5G) systems has led to a significant rise in bandwidth-intensive applications within the Internet of Things (IoT), particularly in vehicular IoT (V-IoT). Effective solutions like Multipath TCP (MPTCP) and Multipath QUIC (MPQUIC) have emerged to address the escalating bandwidth demands of connected vehicles. However, challenges persist for multipath schedulers in efficiently adapting to diverse network conditions typically found in vehicular environments. In this paper, we introduce two novel variants of DEAR (<strong>D</strong>eep reinforcement learning <strong>E</strong>mpowered <strong>A</strong>ctor-critic schedule<strong>R</strong>), namely, DEAR-MAC (Multiple Alternative Critics) and DEAR-CAP (Critic Associated per Path). The proposed DRL-based schedulers are tailored for multipath QUIC in 5G/B5G environments, enhancing decision-making in dynamic network scenarios often encountered by V-IoT devices. Through extensive experimentation across various network setups, including those with fluctuating bandwidth and network outages, and utilizing real-world network traces from the Lumos5G dataset, we conduct a comparative analysis against state-of-the-art learning-based schedulers like Peekaboo and rule-based schedulers like RR, ECF, BLEST, and minRTT. Our experiments show that the proposed DEAR-MAC and DEAR-CAP schedulers outperformed Peekaboo by 38.88% to 48.11%, respectively, in different heterogeneous network conditions, and the gains are much higher when compared to other rule-based schedulers. These advancements are particularly beneficial for vehicular IoT applications, ensuring more reliable and efficient data transmission, even in challenging network environments for applications such as real-time navigation, remote diagnostics, and vehicle-to-vehicle communication.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101616"},"PeriodicalIF":6.0,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070802","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":"BSCP-SG: Blockchain-enabled secure communication protocols for IoT-driven smart grid systems","authors":"Ibrahim Alrashdi ,&nbsp;Muhammad Tanveer ,&nbsp;Saud Alhajaj Aldossari ,&nbsp;Menwa Alshammeri ,&nbsp;Ammar Armghan","doi":"10.1016/j.iot.2025.101626","DOIUrl":"10.1016/j.iot.2025.101626","url":null,"abstract":"<div><div>Smart grids (SG) utilize emerging communication technologies and IoT innovations to advance power system efficiency, reliability, and sustainability. Smart meters (SM), as key components of SG, facilitate real-time monitoring and control of energy usage by supplying data to both consumers and service providers (SP). However, the open communication framework of IoT-enabled SGs introduces significant security vulnerabilities that can disrupt the smooth operation of SGs. To address these risks, secure communication protocols are crucial, ensuring confidentiality, integrity, and authentication for data transmitted between SMs and SPs, thereby safeguarding SGs from cyber-attacks and ensuring the reliability of their operations. To address security challenges, we propose a blockchain-enabled secure communication protocol for IoT-driven SGs, called BSCP-SG. The BSCP-SG protocol is developed utilizing the AEAD primitive, ECC, and SHA-256 to enable mutual authentication between SM and SP. Once authenticated, a session key (SK) is generated, enabling indecipherable communication between the SM and SP. The data obtained from the SMs is converted into secure transactions, grouped into blocks, and recorded on the blockchain by the SP, which uses a secure PBFT consensus mechanism within a peer-to-peer SP network, ensuring both data integrity and immutability. Furthermore, the resilience of SK is validated through the ROR model. The resilience and resistance of BSCP-SG against potential attacks are further confirmed through informal analysis. The proposed protocol not only strengthens security but also reduces computational and communication costs, presenting a secure and efficient solution for IoT-based SG systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101626"},"PeriodicalIF":6.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916494","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":"Virtual sensors for smart farming: An IoT- and AI-enabled approach","authors":"Athanasios Chourlias ,&nbsp;John Violos ,&nbsp;Aris Leivadeas","doi":"10.1016/j.iot.2025.101611","DOIUrl":"10.1016/j.iot.2025.101611","url":null,"abstract":"<div><div>Smart farming relies on precise environmental data to optimize agricultural practices, with key metrics such as air temperature, humidity, rain, ambient light, ultraviolet (UV) radiation and soil moisture to play a crucial role in agricultural decision-making. However, the vast spatial coverage of agricultural fields and the high cost of deploying numerous physical sensors pose significant challenges, particularly for small and medium-sized farms. To address these issues, virtual sensors – machine learning models that predict sensor values based on data from relevant physical sensors – offer a cost-effective and scalable alternative. In this research, a number of Arduino-based IoT devices are designed and deployed equipped with various physical sensors, a lithium-polymer battery which recharges continuously using a 6 W waveshare solar panel, and a Real-Time Clock (RTC) module that synchronizes data logging. The IoT devices operated across two agricultural fields over a span of almost three months. The data collected form the basis for evaluating multiple machine learning models as virtual sensors. Furthermore, the use of open weather data to develop a hardware-free solution is explored. Experimental results show that virtual sensors provide a cost-effective and accurate method for replacing physical sensors. The Light Gradient Boosting Machine emerged as the most accurate model for virtual sensors, achieving prediction errors of less than 1% in most of the cases. This makes it a valuable tool for enabling cost-effective and data-driven farming in resource-constrained IoT devices.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101611"},"PeriodicalIF":6.0,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922034","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 feedback transformer based intrusion detection system for IoMT healthcare networks","authors":"Jamshed ALi Shaikh ,&nbsp;Chengliang Wang ,&nbsp;Saifullah ,&nbsp;Muhammad Wajeeh Us Sima ,&nbsp;Muhammad Arshad ,&nbsp;Waheed Ul Asar Rathore","doi":"10.1016/j.iot.2025.101597","DOIUrl":"10.1016/j.iot.2025.101597","url":null,"abstract":"<div><div>Transformers, while effective at capturing spatial relationships through self-attention mechanisms, typically rely on LSTM networks only at the end to model sequential dependencies. This limits their ability to fully exploit temporal relationships across all layers. Such limitations impact the performance of Intrusion Detection Systems (IDS) in Internet of Medical Things (IoMT) environments , where accurate analysis of patient data is essential for detecting known attack signatures, zero-day anomalies, monitoring health trends, and securing healthcare networks. To address these challenges, we propose the Memory Feedback Transformer (MF-Transformer), which integrates Memory Feedback LSTM (MF-LSTM) throughout the entire Transformer architecture to capture and propagate temporal dependencies at every layer. The MF-Transformer first computes spatial-to-spatial relationships by analyzing correlations between features within the same time step, then incorporates spatial-to-temporal relationships by integrating the hidden state from the MF-LSTM to capture temporal dynamics via a feedback loop. By combining spatial and temporal patterns, the MF-Transformer retains long-term dependencies, tracks temporal dynamics effectively, and enhances anomaly detection, identifying both short-term deviations and long-term trends. Comprehensive evaluations on three publicly available datasets, WUSTL-EHMS-2020, ECU-IoHT, and X-IIoTID demonstrate the superior performance of the proposed MF-Transformer, achieving accuracy rates of 99.88%, 99.42%, and 99.12% for signature detection, and 99.98%, 99.71%, and 99.18% for anomaly detection, respectively.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101597"},"PeriodicalIF":6.0,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143921982","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":"Corrigendum to ‘SOLAR: Illuminating LLM Performance in API Discovery and Service Ranking for Edge AI and IoT’ [Internet of Things, Volume 32, July 2025, Article 101630]","authors":"Eyhab Al-Masri,&nbsp;Ishwarya Narayana Subramanian","doi":"10.1016/j.iot.2025.101644","DOIUrl":"10.1016/j.iot.2025.101644","url":null,"abstract":"","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101644"},"PeriodicalIF":6.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195697","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 methodology to composite fault detection and classification in wireless biosensor networks","authors":"Rajeev Agarwal ,&nbsp;Tusharkanta Samal ,&nbsp;Rakesh Ranjan Swain ,&nbsp;Sipra Swain","doi":"10.1016/j.iot.2025.101623","DOIUrl":"10.1016/j.iot.2025.101623","url":null,"abstract":"<div><div>Reliability is a critical aspect of wireless biosensor networks. In this context, an efficient methodology for fault diagnosis in wireless biosensor networks under composite fault scenarios is proposed. The methodology consists of three steps: firstly, hard fault detection in sensitive and non-sensitive regions using timeout response and Fletcher’s checksum implementation; secondly, soft fault detection through fault status generation using the Z-score test; and lastly, fault classification using a probabilistic neural network to categorize composite faults based on their behaviors. The proposed methodology is particularly well-suited for critical events in wireless biosensor networks. Hard fault detection is implemented in a biosensor network simulation setup, and its performance is evaluated in terms of packet delivery ratio and energy consumption, both before and after fault detection. For the hard fault detection, the proposed methodology improves the packet delivery ratio by <span><math><mo>∼</mo></math></span>13.04% while reducing energy consumption by <span><math><mo>∼</mo></math></span>11.96% in the sensitive region. In the non-sensitive region, the average biosensor node and link failure detection rate is <span><math><mo>∼</mo></math></span>87%. Soft fault detection and classification are evaluated through simulations using human-body biosensor data and relevant fault evaluation metrics. Compared to its existing counterparts, the proposed methodology improves the detection rate by <span><math><mo>∼</mo></math></span>8.81%, reduces the false positive rate by <span><math><mo>∼</mo></math></span>33.25%, and reduces the false negative rate by <span><math><mo>∼</mo></math></span>43.25%. For fault classification, the detection rate for permanent faults is <span><math><mo>∼</mo></math></span>4.68% higher, and the misclassification rate is <span><math><mo>∼</mo></math></span>45.09% lower as compared to other fault types. In addition, a T-score is performed to validate the statistical significance of the soft fault detection and classification results at a 95% confidence level. Experimental results demonstrate that the proposed methodology effectively detects and classifies composite fault scenarios, achieving superior performance compared to existing fault diagnosis methods.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101623"},"PeriodicalIF":6.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143903405","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 privacy-preserving LDA model training scheme based on federated learning","authors":"Hua Shen,&nbsp;Ying Cao,&nbsp;Bai Liu","doi":"10.1016/j.iot.2025.101620","DOIUrl":"10.1016/j.iot.2025.101620","url":null,"abstract":"<div><div>Latent Dirichlet Allocation (LDA) is a widely used topic modeling technique that effectively extracts the distribution of topics and their associated words from various types of textual data. However, during the iterative training of an LDA model, there is a risk of leaking sensitive text information. Additionally, many current LDA training methods rely on centralized training patterns, which pose several challenges. In this manner, it can be difficult for the training node to process large volumes of text simultaneously. This setup also makes the node a single point of failure, a potential performance bottleneck, and a target for attackers. For these issues, this paper introduces an adaptive distributed training framework (FedLDA), combining federated learning and Collapsed Gibbs Sampling (CGS) for distributed datasets. Furthermore, we present a privacy-preserving LDA model training scheme (FedLDA-DP) that combines FedLDA and differential privacy technology. Analysis and experimental results demonstrate the effectiveness and efficiency of the proposed scheme.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101620"},"PeriodicalIF":6.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891271","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":"SOLAR: Illuminating LLM performance in API discovery and service ranking for edge AI and IoT","authors":"Eyhab Al-Masri,&nbsp;Ishwarya Narayana Subramanian","doi":"10.1016/j.iot.2025.101630","DOIUrl":"10.1016/j.iot.2025.101630","url":null,"abstract":"<div><div>The growing complexity of web service and API discovery calls for robust methods to evaluate how well Large Language Models (LLMs) retrieve, rank, and assess APIs. However, current LLMs often produce inconsistent results, highlighting the need for structured, multi-dimensional evaluation. This paper introduces SOLAR (Systematic Observability of LLM API Retrieval), a framework that assesses LLM performance across three key dimensions: functional capability, implementation feasibility, and service sustainability. We evaluate four leading LLMs—GPT-4 Turbo (OpenAI), Claude 3.5 Sonnet (Anthropic), LLaMA 3.2 (Meta), and Gemini 2.0 Flash (Google)—on their ability to identify, prioritize, and evaluate APIs across varying query complexities. Results show GPT-4 Turbo and Claude 3.5 Sonnet achieve high functional alignment (FCA ≥ 0.75 for simple queries) and strong ranking consistency (Spearman’s ρ ≈ 0.95). However, all models struggle with implementation feasibility and long-term sustainability, with feasibility scores declining as complexity increases and sustainability scores remaining low (SSI ≈ 0.40), limiting deployment potential. Despite retrieving overlapping APIs, models often rank them inconsistently, raising concerns for AI-driven service selection. SOLAR identifies strong correlations between functional accuracy and ranking stability but weaker links to real-world feasibility and longevity. These findings are particularly relevant for Edge AI environments, where real-time processing, distributed intelligence, and reliable API integration are critical. SOLAR offers a comprehensive lens for evaluating LLM effectiveness in service discovery, providing actionable insights to advance robust, intelligent API integration across IoT and AI-driven systems. Our work aims to inform both future model development and deployment practices in high-stakes computing environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101630"},"PeriodicalIF":6.0,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891270","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":"Reliability-oriented dynamic task offloading for time-varying satellite IoT: A lightweight multi-agent cooperative strategy optimization method","authors":"Xin-tong Pei ,&nbsp;Zhen-jiang Zhang ,&nbsp;Qing-an Zeng ,&nbsp;Ying-si Zhao","doi":"10.1016/j.iot.2025.101603","DOIUrl":"10.1016/j.iot.2025.101603","url":null,"abstract":"<div><div>The integration of satellite Internet of Things (IoT) with Mobile Edge Computing (MEC) has revolutionized global connectivity, enabling intelligent applications in remote regions while presenting distinctive reliability challenges stemming from intermittent satellite connections and spatio-temporal workload dynamic. However, traditional centralized approaches fail to address these challenges, as their reliance on stable connections and centralized control fundamentally conflicts with the dynamic nature of satellite networks. Motivated by these challenges, we propose a decentralized cooperative task offloading framework where satellite edge servers independently manage task oddloading, inter-satellite task migration, and resource allocation. To enhance offloading reliability in bursty traffic scenarios, we leverage Stochastic Network Calculus (SNC) to integrate communication and computation failure probabilities into our optimization framework. Aiming at coordinated decision-making and global optimization, this work presents a lightweight cooperative task offloading algorithm (MA-LWCTO) utilizing multi-agent soft actor–critic, where the satellites make decisions through local state and shared neighboring policy information. In response to the challenges of increasing computational complexity and state space expansion, we develop an information extraction mechanism based on long short-term memory variational auto-encoder with attention (VLAEA), facilitating efficient information while reducing communication overhead. Extensive simulations based on pre-obtained satellite trajectory data demonstrate that the proposed algorithm significantly enhances reliability while reducing system service costs in satellite–terrestrial MEC environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101603"},"PeriodicalIF":6.0,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881291","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":"GADANN: A Virtual-to-Real knowledge transfer and adaptation method for edge devices","authors":"Suraj Kumar Pandey,&nbsp;Shivashankar B. Nair","doi":"10.1016/j.iot.2025.101615","DOIUrl":"10.1016/j.iot.2025.101615","url":null,"abstract":"<div><div>Enabling Machine Learning capabilities on edge devices is crucial for supporting several automation scenarios. Given the low availability of real-world data for training, Virtual-to-Real knowledge transfer methods are often utilised for training Machine Learning models for deployment on edge devices located in the real world. However, the difference between the virtual and the real-world data hampers the post-deployment performance of the model. While Domain Adaptation-based methods allow a model to learn features shared across the virtual and the real worlds, the resulting model is static and too big to be used in conjunction with an edge device. TinyML allows the usage of Machine Learning models on resource-constrained devices by compressing the models into small transferable files. However, most of the existing TinyML onboard operations are restricted to drawing inferences and do not facilitate onboard training. To tackle these challenges, we propose <span><math><mrow><mi>G</mi><mi>A</mi><mi>D</mi><mi>A</mi><mi>N</mi><mi>N</mi></mrow></math></span>, a TinyML-based Virtual-to-Real knowledge transfer method that facilitates onboard adaptation. <span><math><mrow><mi>G</mi><mi>A</mi><mi>D</mi><mi>A</mi><mi>N</mi><mi>N</mi></mrow></math></span> extends Machine Learning onboard the edge devices by leveraging Deep Neural Networks, Domain Adaptation, TinyML and Genetic Algorithms. The method has been tested successfully in a real-world setting by deploying it on a real robot in a warehouse prototype to identify pallets using computer vision. <span><math><mrow><mi>G</mi><mi>A</mi><mi>D</mi><mi>A</mi><mi>N</mi><mi>N</mi></mrow></math></span> can boost the accuracy of the robot by adapting to the environment in real-time.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"32 ","pages":"Article 101615"},"PeriodicalIF":6.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902273","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}