Internet of Things最新文献

{"title":"Enhancing big data analysis in IoT applications and optimizing the performance of machine learning models using hybrid dimensionality optimization approach","authors":"Ihab Nassra, Juan V. Capella","doi":"10.1016/j.iot.2025.101764","DOIUrl":"10.1016/j.iot.2025.101764","url":null,"abstract":"<div><div>The proliferation of Internet of Things (IoT) applications generates high-dimensional datasets characterized by substantial velocity, variety, and complexity, imposing severe computational constraints on machine learning systems. Such data's high dimensionality complicates identifying meaningful correlations among features. Thus, high-dimensional datasets pose substantial challenges for machine learning, as the abundance of variables tends to obscure meaningful correlations and hinder practical data analysis, particularly regarding computational resource consumption (e.g., memory usage), processing time, and machine learning models' training efficiency and performance. Dimensionality reduction techniques address these challenges by decreasing the number of input variables and preserving the intrinsic structure of the data while alleviating computational burdens. Nevertheless, most contemporary methods are optimized for either linear or nonlinear data patterns, but rarely both. Hybrid strategies integrating linear and nonlinear reduction techniques have increasingly addressed these constraints. Specifically, the combination of Principal Component Analysis (PCA) as a preprocessing stage with Restricted Boltzmann Machines (RBMs) offers a complementary solution, wherein PCA condenses the feature space into a lower-dimensional representation, thereby improving training efficiency and enabling RBMs to capture complex nonlinear dependencies with enhanced convergence and generalization. While this combination can theoretically exploit the data's linear and nonlinear characteristics, conventional PCA-RBM frameworks often struggle to retain essential local manifold structures, limiting their effectiveness in capturing the full complexity of real-world datasets. This study addresses these challenges by proposing a novel hybrid dimensionality reduction framework that integrates PCA's global linear projection capabilities with RBMs' nonlinear feature learning strengths through an adaptive graph regularization mechanism that preserves critical local manifold properties, which address the limitations of conventional PCA-RBM combinations. The adaptive regularization mechanism ensures that proximate data points in input space retain similarity in the reduced feature space, effectively bridging global and local structure preservation. Compared to conventional methods, experimental validation demonstrates superior performance across multiple evaluation metrics, including data reduction efficiency, classification accuracy, precision, recall, and F-score. The framework addresses critical limitations in high-dimensional data processing while maintaining model performance, establishing a methodologically significant contribution to dimensionality reduction techniques applicable across scientific disciplines handling complex IoT-generated datasets. Our findings indicate that dimensionality reduction constitutes a viable and efficacious approach to simplifying ","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101764"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158239","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":"DCATCN: A temporal convolutional network and cross-attention based UAV sensor anomaly detection method","authors":"Bo Wu ,&nbsp;Chengzi Zhou ,&nbsp;Yanxi Liu ,&nbsp;Peng Xiao ,&nbsp;Wei Zheng","doi":"10.1016/j.iot.2025.101760","DOIUrl":"10.1016/j.iot.2025.101760","url":null,"abstract":"<div><div>To address the issues of severe high-dimensional redundancy and interference in UAV sensor data, insufficient ability to model temporal dependencies, and anomaly decisions relying on fixed empirical thresholds, this paper proposes a lightweight anomaly detection framework called DCATCN (Dual Cross-Attention Temporal Convolutional Network) based on a bidirectional temporal convolutional network (BiTCN) and a Cross-Attention mechanism. First, the method uses the Maximal Information Coefficient (MIC) to adaptively select a feature subset that is highly correlated with target anomalies, effectively reducing data redundancy; then it constructs a bidirectional temporal convolutional network to extract forward and backward features of the time series data in parallel, introducing a Cross-Attention mechanism to dynamically integrate bidirectional information and enhance the model’s representation of temporal dependencies; finally, it employs Extreme Value Theory to statistically model the prediction residuals and determine the anomaly decision threshold, achieving robust and reliable anomaly detection. Comprehensive experiments on the public ThorFlight93 dataset demonstrate that this method outperforms various mainstream models in both detection accuracy and computational efficiency, showcasing strong potential for engineering applications. Code release: <span><span>https://github.com/ZCchou/DCATCN.git</span><svg><path></path></svg></span></div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101760"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158446","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":"Role of artificial intelligence in health monitoring using IoT based wearable sensors: A survey","authors":"Laxmi Shaw,&nbsp;Hardik A. Gohel","doi":"10.1016/j.iot.2025.101761","DOIUrl":"10.1016/j.iot.2025.101761","url":null,"abstract":"<div><div>With the rising demand for rapid and accurate medical diagnosis and the widespread adoption of Internet of Things (IoT) technologies, healthcare delivery is undergoing a major transformation in patient monitoring, diagnosis, and prognosis. The growth of virtual healthcare providers and remote consultations further increases the need for efficient systems that can process large volumes of real-time health data. In this context, integrating artificial intelligence (AI) with IoT-based healthcare systems plays an essential role in enabling predictive analytics, early anomaly detection, and real-time clinical decision-making. This paper examines the role of AI in enhancing the performance of IoT-enabled wearable health monitoring devices, with a focus on data transmission efficiency, energy consumption, communication protocols, and overall system reliability. Our analysis highlights that AI integration significantly improves accuracy, adaptability, and patient-centric outcomes. The paper concludes by outlining the current challenges such as energy limitations, data privacy, and interoperability and discusses future research directions for developing next-generation IoT-based wearable healthcare systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101761"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096289","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":"Agri-farming with computer vision, IoT and blockchain towards climate smart cultivation","authors":"Sajid Safeer ,&nbsp;Pierluigi Gallo ,&nbsp;Cataldo Pulvento","doi":"10.1016/j.iot.2025.101749","DOIUrl":"10.1016/j.iot.2025.101749","url":null,"abstract":"<div><div>Modern agriculture faces critical challenges such as climate change, food security and supply chain inefficiencies, which demand innovative solutions. Traditional farming systems often lack real time monitoring, data security and transparency, leading to wastefulness and quality concerns. To address these, we present a comprehensive precision agriculture framework that integrates Internet of Things (IoT) sensors, Raspberry Pi (R-Pi) edge computing, blockchain based data management and computer vision (CV) assisted statistical modeling. The system collects environmental data via a sensor network, processes it at the edge using R-Pi, and records summarized outputs on a secure Ethereum based blockchain using smart contracts. Simultaneously, CV modules perform real time quality assessment and anomaly detection. A Markov chain based stochastic model is employed to track quality degradation in high value crops. The methodology is validated through a saffron use case, demonstrating effectiveness in monitoring filament degradation and detecting potential fraud. This integration enhances real time decision making, ensures traceability and promotes sustainability in climate smart agriculture.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101749"},"PeriodicalIF":7.6,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096287","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 dynamic anonymous authentication protocol with membership privacy in cloud-fog-assisted IIoT","authors":"Guojun Wang ,&nbsp;Guixin Jiang ,&nbsp;Yushuai Zhao","doi":"10.1016/j.iot.2025.101742","DOIUrl":"10.1016/j.iot.2025.101742","url":null,"abstract":"<div><div>The cloud-fog computing infrastructure flexibly deploys resources in the Industrial Internet of Things (IIoT), adjusting the computing and storage capabilities of cloud and fog nodes based on specific needs to optimize costs and performance. However, the frequent transmission and sharing of data between terminal entities and the cloud-fog infrastructure can easily lead to privacy leaks of terminals or fog nodes. Positioned at the edge of the data source, fog nodes manage and process the needs of various local industrial sensors in real time. When sensors dynamically join or leave the group, frequent authentication with fog nodes can compromise identity privacy. To protect node identity privacy and reduce computational costs, the group signature technology is introduced in this paper. It is usually employed to build anonymous authentication protocols because of its natural properties. Backes et al. proposed a novel practical property called membership privacy for dynamic group signatures, which provides stronger anonymity. In this paper, we employ the BBS+ signature, signature proof of knowledge (SPK), ElGamal scheme, etc., to design a novel verifier local revocation (VLR) dynamic group signature with membership privacy. The proposed group signature has a smaller signature size and less computational overhead. Afterward, the framework of the cloud-fog-assisted IIoT scheme based on the proposed group signature is constructed, capturing full anonymity to preserve the privacy of patients. Formal security proofs are presented to show that the proposed group signature satisfies both general and specific security requirements. Finally, the overhead of the group signature scheme is tested on type d159 curves in the Java pairing-based cryptography (JPBC) library. The results demonstrate that our scheme is more suitable for resource-restrained devices.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101742"},"PeriodicalIF":7.6,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158237","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 comprehensive review of IoT device fingerprinting: Insights into techniques, trends, challenges, and future directions","authors":"Mariam Munsif Mir,&nbsp;Wee Lum Tan,&nbsp;Mohammad Awrangjeb","doi":"10.1016/j.iot.2025.101758","DOIUrl":"10.1016/j.iot.2025.101758","url":null,"abstract":"<div><div>The Internet of Things (IoT) connects billions of devices, ranging from household appliances to industrial systems, enabling intelligent automation, real-time monitoring, and seamless communication. However, the rapid expansion in the IoT ecosystem introduces significant security and management challenges, particularly in device identification and authentication. IoT device fingerprinting has emerged as a critical research area for enhancing security and management in interconnected ecosystems.</div><div>The article at hand provides a comprehensive review and analysis of existing IoT device fingerprinting methods from 2017 to 2025. It categorizes these methods based on their underlying approaches across the Physical, Network, and Application communication layers. Each study is critically examined, with a focus on its characteristics, strengths, and limitations. The article also reviews publicly available datasets and explores trends in feature selection, including the use of statistical, radio frequency, and network packet features. Moreover, it also examines the adoption of machine learning and deep learning models in this context. Finally, the article addresses existing challenges, use cases, and outlines future research directions to support the development of more effective and scalable solutions in this domain.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101758"},"PeriodicalIF":7.6,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118704","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":"LoRa-SPaaS: Spectrum sensing as a service using LoRaWAN: Resources management and practical considerations","authors":"Abbass Nasser ,&nbsp;Hussein Al Haj Hassan ,&nbsp;Alaaeddine Ramadan ,&nbsp;Chamseddine Zaki ,&nbsp;Nada Sarkis ,&nbsp;Jad Abou Chaaya ,&nbsp;Ali Mansour","doi":"10.1016/j.iot.2025.101750","DOIUrl":"10.1016/j.iot.2025.101750","url":null,"abstract":"<div><div>This paper investigates the feasibility of using LoRaWAN as the communication protocol for a Spectrum Sensing Provider (SSP) in Cognitive Radio (CR) networks. We evaluate LoRaWAN capability to deliver reliable spectrum detection services by analyzing the impact of key protocol parameters such as duty cycle restrictions, gateway capacity, and network interference on delivering the sensing outcome in Cooperative Spectrum Sensing (CSS) scenarios. Additionally, we propose a novel cost function for selecting CSS groups, optimizing the trade-off between energy consumption and channel availability, along with a greedy scheduling algorithm to enhance sensing timeliness. Numerical analysis shows that our cost function may improve spectral and energy efficiency by 50% compared to classical SNR-based approaches, while the greedy algorithm effectively balances the SSP’s response to service requests. Our findings highlight that despite LoRaWAN constraints, increasing the number of users and detected channels significantly enhances SSP performance, enabling it to meet diverse spectrum sensing demands more efficiently.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101750"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096255","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":"STREAMLINE: Dynamic and Resource-Efficient Auto-Tuning of Stream Processing Data Pipeline Ensembles","authors":"Stefan Pedratscher ,&nbsp;Zahra Najafabadi Samani ,&nbsp;Juan Aznar Poveda ,&nbsp;Thomas Fahringer ,&nbsp;Marlon Etheredge ,&nbsp;Abolfazl Younesi ,&nbsp;Juan Jose Durillo Barrionuevo ,&nbsp;Peter Thoman","doi":"10.1016/j.iot.2025.101731","DOIUrl":"10.1016/j.iot.2025.101731","url":null,"abstract":"<div><div>With the growing volume of data generated by IoT devices and user-driven services, stream processing has become essential for handling continuous, real-time data. However, fluctuating workloads and the dynamic nature of data streams make it difficult to maintain consistent performance over time, requiring adaptive resource allocation and frequent configuration tuning. Running multiple data stream processing pipelines on shared resources further exacerbates the problem by increasing contention, leading to higher end-to-end latency and reduced performance stability. Most existing approaches focus on tuning individual configuration parameters in isolation and overlook interactions between concurrently running data pipelines. To address these limitations, we present STREAMLINE, a dynamic multi-layer auto-tuning framework designed for stream processing environments. STREAMLINE uses transformers to predict future workloads and an evolutionary algorithm to automatically tune configuration parameters. It also includes a resource-efficient scheduler that efficiently assigns operators to resources across a compute cluster. Our dynamic update mechanism minimizes downtime and preserves state during configuration parameter and scheduling changes. We evaluate STREAMLINE on the Grid’5000 testbed using real-time IoT and streaming benchmarks. Results show that STREAMLINE outperforms state-of-the-art methods, improving throughput, end-to-end latency, and CPU utilization by up to 4<span><math><mo>×</mo></math></span> , 10<span><math><mo>×</mo></math></span> , and 9<span><math><mo>×</mo></math></span> , respectively, while reducing costs by up to 10<span><math><mo>×</mo></math></span> .</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101731"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096256","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":"Integration of Hardware Security Modules into BLE Beacons: Fundamentals and Use in a Secure and Private Geofencing Application","authors":"Miguel Mesa-Simón ,&nbsp;Antonio Escobar-Molero ,&nbsp;Luis Parrilla ,&nbsp;Diego P. Morales ,&nbsp;José Antonio Álvarez-Bermejo ,&nbsp;Francisco J. Romero","doi":"10.1016/j.iot.2025.101762","DOIUrl":"10.1016/j.iot.2025.101762","url":null,"abstract":"<div><div>Bluetooth Low Energy (BLE) is a wireless technology designed for creating personal area networks in low-power applications. In the context of BLE, Beacon devices are widely used to transmit small packets of data with unique identifiers at regular intervals to be detected by surrounding devices. These devices enable a wide range of applications, including indoor navigation, marketing, and asset tracking. However, BLE Beacons suffer from multiple security issues and privacy concerns since the transmissions are unencrypted and do not include authentication mechanisms. While many implementations try to provide security to the Beacons packet, they often rely on external servers, static keys, synchronization for key derivation, or use difficult to maintain and to operate Public Key Infrastructure (PKI). In this work, we propose a solution to enhance Beacon security through the integration of Secure Elements (SEs), establishing a Root of Trust. Our approach is based on the over-the-air activation of the BLE beacons incorporating an authentication mechanism and a key derivation technique to safeguard privacy and data integrity in the communication. We demonstrate that this implementation incurs minimal delays and power consumption compared to traditional Beacons while avoiding the added complexity of solutions based on Certificates and Public Key Infrastructure (PKI). The feasibility of the proposed approach is also illustrated through a secure and privacy-preserving geofencing application. In summary, this method supports a low-power and secure point-to-point communication suitable not only for BLE beacon networks, but also for other IoT scenarios where data privacy is critical.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101762"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109703","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":"Intelligent UAV swarm key agreement survey: Systematic taxonomy, cryptographic automaton and quantum resistance","authors":"Guangyue Kou ,&nbsp;Qing Ye ,&nbsp;Mingwu Zhang ,&nbsp;XuAn Wang ,&nbsp;Wei Fu ,&nbsp;Qian Zhou ,&nbsp;Zhimin Yuan ,&nbsp;Renji Huang ,&nbsp;Xiong Zhang","doi":"10.1016/j.iot.2025.101720","DOIUrl":"10.1016/j.iot.2025.101720","url":null,"abstract":"<div><div>Unmanned Aerial Vehicle (UAV) swarms are vital for intelligent applications that require robust key agreement protocols to address dynamic network security challenges. This paper systematically reviews protocols for intelligent UAV swarms, addressing the gaps in existing research. It classifies UAV and embedded protocols based on autonomy and computational capabilities, defines security requirements, and establishes threat models for swarm dynamics. Protocols are categorized into three architectures: end-to-end for ground-UAV communication, planar multi-UAV for decentralized peer-to-peer management, and hybrid hierarchical systems for large swarms. A core contribution is the cryptographic automaton, an adaptive framework for autonomous security management that integrates dynamic key generation, context-aware adjustments, and quantum resistance to handle real-time topology changes and emerging threats. The paper merges structural classifications with threat analysis to identify solution gaps and propose scalable, cryptographic automaton-based, and quantum-resistant directions. It establishes a foundation for secure UAV swarm key agreement, with future research focusing on refining the automaton for practical applications.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101720"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096288","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}