Yan Zhang , Guojiang Shen , Huan Li , Zhenhui Xu , Xiangjie Kong
{"title":"Federated differentially private framework for risky driving behaviour assessment","authors":"Yan Zhang , Guojiang Shen , Huan Li , Zhenhui Xu , Xiangjie Kong","doi":"10.1016/j.iot.2025.101726","DOIUrl":"10.1016/j.iot.2025.101726","url":null,"abstract":"<div><div>Connected and Automated Vehicles (CAVs) offer a transformative opportunity to enhance road safety by identifying and mitigating risky driving behaviours. However, current methods for assessing these behaviours in CAVs overlook privacy concerns, as all terminal devices are required to upload original data directly to a central server for analysis. This data often includes sensitive personal information, raising the risk of potential privacy breaches. To address this challenge, we introduce Federated Learning (FL), a privacy-preserving machine learning technique, and propose a Federated Differentially Private based Risk Assessment Network (FedDPRAN) for risky driving behaviour assessment. In particular, we begin by extracting driving behaviour characteristics for each client using the Risk Assessment Network (RAN), following the adversarial principle of minimizing the difference in driving behaviour features while maximizing the difference in privacy features of the driver. Then, a new FL solution that utilizes the local RAN model is proposed to collaborate and exchange learned parameters with a cloud server without sharing actual data. To enhance privacy in the FL framework, we integrate a Differential Privacy (DP) solution for each client. Comprehensive experiments are conducted based on two real-world datasets. The results demonstrate that our approach to assessing risky driving behaviour in CAVs protects privacy while being superior to state-of-the-art schemes.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101726"},"PeriodicalIF":7.6,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840719","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}
Luis Freitas , Marco Silva , Gabriel Vale , Camelia Avram , Helena Lopes , Filipe Pereira , Nuno Leal , José Machado
{"title":"OPC UA and MQTT performance analysis within a unified namespace context","authors":"Luis Freitas , Marco Silva , Gabriel Vale , Camelia Avram , Helena Lopes , Filipe Pereira , Nuno Leal , José Machado","doi":"10.1016/j.iot.2025.101734","DOIUrl":"10.1016/j.iot.2025.101734","url":null,"abstract":"<div><div>One of the main obstacles to fully adopting and implementing Industry 4.0 concept and achieving effective digital transformation is interoperability. Various communication protocols, aligned with different architectures, present themselves as potential solutions. The Unified Namespace (UNS) has emerged as a promising approach for data-centric architectures aligned with reference frameworks like Reference Architectural Model Industrie 4.0 (RAMI 4.0) and The Industrial Internet Reference Architecture (IIRA). Open Platform Communications Unified Architecture (OPC UA) and Message Queuing Telemetry Transport (MQTT) are among the most widely used communication protocols applicable in a UNS. Determining which of these is most suitable for specific applications requires further exploration. This paper provides an in-depth comparison of these protocols across several key Industry 4.0 metrics, based on data from an industrial-like case study and qualitative insights from the research team. Findings indicate that a lightweight protocol like MQTT offers advantages in raw performance metrics in its efficiency and scalability; however, depending on the application and organizational philosophy, OPC UA may offer a more comprehensive solution, mainly in terms of security and interoperability. The study’s results are limited by reliance on a single case study and lack of failure or cyber-attack scenarios. Future work will expand testing with more clients, simulate network faults and attacks, and include OPC UA Pub/Sub for broader comparison.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101734"},"PeriodicalIF":7.6,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827131","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}
Giuseppe Del Fiore, Teodoro Montanaro, Ilaria Sergi, Luigi Patrono
{"title":"Adaptive IoT architecture with incremental learning for on-line solar production forecasting","authors":"Giuseppe Del Fiore, Teodoro Montanaro, Ilaria Sergi, Luigi Patrono","doi":"10.1016/j.iot.2025.101724","DOIUrl":"10.1016/j.iot.2025.101724","url":null,"abstract":"<div><div>Smart homes play a pivotal role in advancing energy sustainability by incorporating renewable energy sources, like photovoltaic systems. Their effectiveness depends on the closer alignment between energy production and consumption. However, forecasting solar energy remains challenging due to variability from meteorological and seasonal factors. Traditional forecasting methods primarily rely on complex models and static datasets, lacking on-line estimation based on dynamic inputs like live weather and actual production data from Internet of Things (IoT) devices. While IoT-based data acquisition has begun to enhance forecasting, the heterogeneity of these devices poses interoperability challenges, limiting their full potential. Moreover, existing models often fail to leverage incremental learning, which is essential for continuously adapting predictions as new data becomes available. To mitigate these constraints, this paper proposes a modular, interoperable, and scalable IoT architecture for solar energy forecasting. It incorporates modules to: (a) integrate heterogeneous IoT devices and external services, such as weather forecasting, to obtain real-time data; (b) incorporate a baseline model, informed by domain knowledge of photovoltaic systems, to provide initial production estimations in the absence of historical data; and (c) exploit incremental hybrid forecasting techniques able to combine a batch model for long-term trend prediction based on historical data and with a progressive refined integrated baseline for on-line short-term forecasting. The proposed architecture has been implemented and evaluated in a real-world smart home scenario. Results demonstrate its ability to predict photovoltaic energy production with over 90% accuracy while maintaining low computational complexity, underscoring its practical applicability in smart home environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101724"},"PeriodicalIF":7.6,"publicationDate":"2025-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827130","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":"From lab to field: Real-world evaluation of an AI-driven Smart Video Solution to enhance community safety","authors":"Shanle Yao , Babak Rahimi Ardabili , Armin Danesh Pazho , Ghazal Alinezhad Noghre , Christopher Neff , Lauren Bourque , Hamed Tabkhi","doi":"10.1016/j.iot.2025.101716","DOIUrl":"10.1016/j.iot.2025.101716","url":null,"abstract":"<div><div>This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose-based data is used for downstream AI tasks such as anomaly detection. A Cloud-based infrastructure and a mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird’s Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment with 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system’s robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-h period and an average end-to-end latency of 26.76 s between anomaly detection and alert issuance.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101716"},"PeriodicalIF":7.6,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865691","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}
José A.López Pastor , Alejandro Gil-Martínez , Antonio Hernández Mateos , Astrid Algaba-Brazález , José Luis Gómez Tornero
{"title":"Bluetooth Low Energy separate-channel fingerprinting with frequency-scanned antennas","authors":"José A.López Pastor , Alejandro Gil-Martínez , Antonio Hernández Mateos , Astrid Algaba-Brazález , José Luis Gómez Tornero","doi":"10.1016/j.iot.2025.101732","DOIUrl":"10.1016/j.iot.2025.101732","url":null,"abstract":"<div><div>A novel Bluetooth Low Energy (BLE) positioning system for IoT devices that employs frequency-scanned leaky-wave antennas (FSLWAs) and the fingerprinting technique is proposed in this work. This system is based on the Received Signal Strength Indicator (RSSI) fingerprinting acquired separately from each one of the three BLE advertising channels. As a main novelty, the Separate-Channel Fingerprinting (SCFP) technique is combined with FSLWAs, specifically tuned to multiplex each BLE advertising channel in a distinct direction. In this way, FSLWAs produce increased spatial resolution in separate-channel radiomaps, which results in greater localization accuracy when compared to the use of conventional monopole antennas installed usually in BLE IoT equipment. This is demonstrated with a practical example involving four BLE beacons distributed in an indoor area of 7 m x 5 m, simulating a practical environment. The proposed system combining SCFP and FSLWAs improves the mean localization error by 39 % compared to conventional monopole antennas without SCFP and 23 % compared to the use of monopoles and SCFP. The system's performance over time and its robustness to the presence of obstacles after calibration are also analyzed, showing the benefits of using SCFP with FSLWAs.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101732"},"PeriodicalIF":7.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827129","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}
Abdennabi Morchid , Abdulla Ismail , Haris M. Khalid , Hassan Qjidaa , Rachid El Alami
{"title":"Blockchain and IoT technologies in smart farming to enhance the efficiency of the agri-food supply chain: A review of applications, benefits, and challenges","authors":"Abdennabi Morchid , Abdulla Ismail , Haris M. Khalid , Hassan Qjidaa , Rachid El Alami","doi":"10.1016/j.iot.2025.101733","DOIUrl":"10.1016/j.iot.2025.101733","url":null,"abstract":"<div><div>Innovative and sustainable agriculture encounters significant challenges due to the extensive variation in farming practices. This is also crucial for the agri-food supply chain and, therefore, for food security. To enhance the efficiency of the agri-food supply chain, it is essential to optimize the farming systems. The combination of blockchain and Internet of Things (IoT) technologies aims to revolutionize agriculture by optimizing traditional practices into more efficient, transparent, and sustainable systems. This proposed article offers an in-depth examination of this integration while addressing the global challenges of food security, resource efficiency, and environmental sustainability. This proposed article begins with an analysis of the size of the global blockchain and IoT market, focusing on their specific application in agriculture. It then presents the fundamentals of these technologies, providing an overview of IoT in smart agriculture, the basics of blockchain technology, and their convergence in this sector. The proposed article examines several key applications of these technologies, including supply chain transparency and traceability, irrigation and resource optimization, livestock monitoring and disease prevention, as well as agricultural finance and smart contracts. Finally, it examines the benefits of integrating IoT and blockchain in agriculture, including enhanced traceability, optimized resource management, and improved data security, while also highlighting the challenges associated with their implementation, such as high costs, scalability issues, energy consumption, data privacy concerns, and regulatory hurdles. This proposed study also highlights the opportunities presented by these technologies while examining the challenges to their widespread adoption in the agricultural sector.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101733"},"PeriodicalIF":7.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144851981","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}
Maria Frontera-Bergas , Miguel Vinaixa-Fernández , Bartomeu Oliver-Riera , Jaume Ramis-Bibiloni , Eugeni Isern , Bartomeu Alorda-Ladaria
{"title":"A Multi-Sensor IoT Platform for monitoring medicine storage beyond the hospital","authors":"Maria Frontera-Bergas , Miguel Vinaixa-Fernández , Bartomeu Oliver-Riera , Jaume Ramis-Bibiloni , Eugeni Isern , Bartomeu Alorda-Ladaria","doi":"10.1016/j.iot.2025.101711","DOIUrl":"10.1016/j.iot.2025.101711","url":null,"abstract":"<div><div>Ambient-sensitive pharmaceutical products degrade when they are exposed to unsuitable environmental conditions such as inappropriate temperature, humidity, light, or mechanical stress. While hospitals ensure proper storage, these conditions are often compromised once medications reach ambulatory patients. This paper presents a novel Internet of Things (IoT)-based platform architecture to monitor drug conservation beyond hospital facilities, extending into patients’ homes. The proposed system comprises a <em>monitoring network</em> and a <em>servers system</em>. The <em>monitoring network</em> includes sensor nodes placed within the original outer packaging of the medication, capturing key environmental variables, and patient-installed gateways that locally process and transmit data to the <em>servers system</em> for near real-time storage and analysis. The <em>servers system</em> detects preservation issues and generates alerts, notifying both patients and hospital pharmacy professionals to enable timely corrective actions. Locally, the gateway warns patients of suboptimal storage conditions, allowing immediate intervention. This platform fosters collaboration between patients and pharmacists, ensuring effective follow-up on drug conservation and administration. Special consideration has been given to energy efficiency to extend sensor node battery life, making the system practical for real-world deployments. The implemented sensor node collects data every 10 s to be transmitted to the gateway, resulting in an estimated battery life of 17.5 months—sufficient for long-term operation, without frequent maintenance. By enabling continuous drug quality monitoring beyond hospitals, including at patients’ homes, this platform supports safer and more effective drug therapies. This work represents a significant advancement in leveraging IoT technologies to improve medicine conservation in decentralized healthcare settings.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101711"},"PeriodicalIF":7.6,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738565","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":"Cyber resilience in e-governance: A review of strategies, challenges, and directions","authors":"Pardeep Singh , Seema Sirpal , Om Pal","doi":"10.1016/j.iot.2025.101702","DOIUrl":"10.1016/j.iot.2025.101702","url":null,"abstract":"<div><div>As governments worldwide increasingly use digital platforms to deliver services, integrated security strategies within electronic governance (e-governance) systems are now imperative. This study provides a comprehensive review of the cybersecurity methods in e-governance focused on improving resilience and ensuring secure functioning in digital government services. It evaluates the challenges in cybersecurity frameworks, focusing on data breaches, illegal access, and emerging threats from sophisticated cyberattacks. In addition, it provides an overview of the prevailing security methods used in various global e-governance systems. Furthermore, it identifies the gaps in the literature and provides scope for further research by reviewing the current practices for enhancing e-governance security. This research highlights the persistent challenges of law-enforcing, implementing policies, and addressing underlying issues that hinder the adoption of cybersecurity measures. This work combines a wide range of global strategies and scholarly initiatives to give a unified view of present challenges and future work directions, especially when using AI and blockchain and being ready for developments after quantum computing. This study aims to enhance understanding of the development of resilient e-governance systems that are secure, adaptive, and capable of withstanding the evolving cyberthreat landscape.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101702"},"PeriodicalIF":7.6,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721804","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}
Ali Hassan , Rizwan Ahmad , Sadaf Javed , Waqas Ahmed , Muhammad Sohaib J. Solaija , Mohsen Guizani
{"title":"Energy-efficient altitude optimization in multi-UAV search and rescue: A hybrid swarm approach","authors":"Ali Hassan , Rizwan Ahmad , Sadaf Javed , Waqas Ahmed , Muhammad Sohaib J. Solaija , Mohsen Guizani","doi":"10.1016/j.iot.2025.101712","DOIUrl":"10.1016/j.iot.2025.101712","url":null,"abstract":"<div><div>The Internet of Things (IoT) has revolutionized disaster response by enabling real-time data acquisition, processing, and communication through edge devices that significantly improve the efficiency of Urban Search and Rescue (USAR) operations. This work presents a novel hybrid optimization approach by integrating Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) to solve the NP-hard problem of minimizing the number of UAVs required for efficient area coverage. The performance of the proposed algorithm is evaluated by providing a comparison with GA-based, PSO-based, and fixed-altitude approaches. UAV altitude, energy capacity, and coverage radius are considered as key optimization parameters. Four navigation techniques including Uniform Grid Omni Navigation, Uniform Vesica Omni Navigation, Boundary Intersect Grid Omni Navigation, and Boundary Intersect Vesica Omni Navigation are used to reduce redundant waypoints and improve energy efficiency. In addition, a comprehensive energy model is considered that links UAV altitude to coverage area and waypoint distribution, providing a critical trade-off between coverage area and energy consumption. Simulation results is validated through case studies in NUST and Masdar City which show that the hybrid grid-based approach is highly effective for both regular and irregular area coverage, offering improved efficiency and minimizing UAV deployment. The proposed approach outperforms other methods, providing an efficient sub-optimal solution for real-world USAR UAV operations.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101712"},"PeriodicalIF":7.6,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144756919","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":"SFIX:Scalable Financial-oriented Interpretable eXplanation","authors":"Abdullah Emir Cil , Kazim Yildiz","doi":"10.1016/j.iot.2025.101713","DOIUrl":"10.1016/j.iot.2025.101713","url":null,"abstract":"<div><div>The use of artificial intelligence in finance undoubtedly has a significant contribution in providing financial services to customers in a more efficient and secure manner. However, black box artificial intelligence algorithms can pose challenges in ensuring the safe functioning of financial services and monitoring desired outcomes. In this study, we have tried to design an explainable artificial intelligence method called Scalable Financial-oriented Interpretable eXplanation (SFIX) specific to the finance sector. While designing the SFIX method, time-based approaches such as fraud detection, credit scoring, customer profiling and other applications used in finance were taken into account. The accuracy and consistency of the dataset are also included in the calculations to support explainability. Finally, a simplified version of the SFIX method is also designed for quick testing of the model in case of problems in finding the real dataset.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101713"},"PeriodicalIF":7.6,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144756918","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}