Internet of Things最新文献

{"title":"Survey of smartphone-based datasets for indoor localization: A machine learning perspective","authors":"Gaetano Carmelo La Delfa ,&nbsp;Javier Prieto ,&nbsp;Salvatore Monteleone ,&nbsp;Hamaad Rafique ,&nbsp;Maurizio Palesi ,&nbsp;Davide Patti","doi":"10.1016/j.iot.2025.101753","DOIUrl":"10.1016/j.iot.2025.101753","url":null,"abstract":"<div><div>Indoor localization has gained significant attention in recent years due to its applications across sectors such as healthcare, logistics, manufacturing, and retail. However, while outdoor localization has been effectively addressed with GPS, indoor localization remains challenging despite significant research progress. Many studies have explored the capabilities of modern smartphones, equipped with a variety of sensors, to develop machine-learning methods for indoor localization, ranging from classical fingerprinting to deep sequence models and transformers. Nevertheless, most rely on small, proprietary datasets that are not publicly available. Large, high-quality public datasets are essential for researchers to efficiently test, refine, and validate algorithms, enable comparisons between different approaches and develop robust and accurate localization solutions. To reduce data collection time and costs and help researchers find the most appropriate datasets for their needs, this paper surveys 20 publicly available high-quality indoor localization datasets suitable for Machine Learning, released between 2014 and 2024, that cover various sensing technologies. The survey reveals a shift toward multi-sensor data collection, extending beyond Wi-Fi and Bluetooth signals to include inertial sensors such as accelerometers and gyroscopes, as well as magnetic fields. It also highlights that while over 75% of datasets cover multi-floor structures or multiple buildings, there is a scarcity of datasets covering diverse types of indoor environments, with most focused on office or academic settings. Moreover, the temporal dimension, crucial in dynamic indoor scenarios, remains largely underrepresented, limiting the development of ML models for tracking dynamic trajectories or adapting to evolving signal patterns.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101753"},"PeriodicalIF":7.6,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010496","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":"Exploring healthcare in the 6G and AI era: Opportunities and challenges","authors":"Houssein Taleb ,&nbsp;Guillaume Andrieux ,&nbsp;Daniele Khalife ,&nbsp;Alain Ajami ,&nbsp;Abbass Nasser","doi":"10.1016/j.iot.2025.101744","DOIUrl":"10.1016/j.iot.2025.101744","url":null,"abstract":"<div><div>The integration of AI with emerging 6G wireless communications promises to revolutionize healthcare delivery by providing ultra-fast, reliable, and intelligent medical services. Unlike previous generations of mobile phones, 6G is expected to offer sub-millisecond latency, data rates up to terabits per second, and connectivity for more than 10 million devices per square kilometer. Together, these technologies will enable unprecedented healthcare applications, such as real-time remote robotic surgery, holographic telemedicine, and continuous monitoring using bio-nanosensors within the bio-nano-internet of things.</div><div>This survey systematically analyzes the integration of AI and 6G technologies, focusing on how their convergence will enable enhanced edge computing, federated and generative AI models, low-latency analytics for personalized treatment, predictive diagnostics, and efficient resource utilization. We present a comprehensive comparison of 5G and 6G architectures, highlighting the limitations of current systems and demonstrating how 6G advancements can address critical healthcare needs, including data throughput, mobility, and security.</div><div>Furthermore, this work identifies detailed opportunities, such as AI-powered virtual nurse assistants, AI-enhanced drug discovery accelerated by hyper-responsive 6G infrastructures, and digital twin-enabled patient simulation. Alongside these opportunities, we critically examine the technical challenges related to spectrum management in the terahertz band, the design of energy-efficient IoT devices, robust data privacy frameworks that integrate federated learning and blockchain technology, ethical considerations surrounding AI explainability, and equitable access to healthcare.</div><div>By filling gaps in the existing literature, this paper presents a comprehensive framework that combines AI and 6G, specifically designed for healthcare systems. Our findings underscore the transformative potential of this combination for achieving proactive and accessible healthcare, while outlining a roadmap for overcoming prevailing technical, ethical, and infrastructural barriers.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101744"},"PeriodicalIF":7.6,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933364","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":"Hybrid CNN-LSTM model for predicting nitrogen, phosphorus, and potassium (NPK) fertilization requirements: Integrating satellite spectral indices with field microclimate data","authors":"Abdellatif Moussaid,&nbsp;Yousra Gamoussi,&nbsp;Hamza Briak","doi":"10.1016/j.iot.2025.101746","DOIUrl":"10.1016/j.iot.2025.101746","url":null,"abstract":"<div><div>This study presents a deep learning approach to predict nitrogen (N), phosphorus (P), and potassium (K) fertilization requirements using satellite and climate data. A hybrid CNN-LSTM model was developed to combine spatial features of Sentinel-2 vegetation indices (NDVI, NDRE, MSAVI, RECI) with temporal daily climate variables, including temperature, humidity, precipitation, wind speed, and solar radiation.</div><div>The model was trained on 3,208 samples integrating spectral, climatic, and field information such as parcel size and observation dates, and tested on a fully separated five-month period. The evaluation on the normalized scale demonstrated strong performance, with test results as follows: for nitrogen, MSE <span><math><mo>=</mo></math></span> 0.0208, MAE <span><math><mo>=</mo></math></span> 0.1132, and <span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>9542</mn></mrow></math></span>; for phosphorus, MSE <span><math><mo>=</mo></math></span> 0.0281, MAE <span><math><mo>=</mo></math></span> 0.1313, and <span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>9480</mn></mrow></math></span>; and for potassium, MSE <span><math><mo>=</mo></math></span> 0.0225, MAE <span><math><mo>=</mo></math></span> 0.1154, and <span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>9474</mn></mrow></math></span>. The model’s stability was further confirmed by consistent predictions across four individual months. This approach effectively integrates multimodal data for robust nutrient forecasting and can assist farmers in optimizing fertilization strategies. The outcomes support improved crop management, reduced environmental impact, and increased yields, especially in regions with limited ground data.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101746"},"PeriodicalIF":7.6,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920293","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":"The role of Large Language Models in IoT security: A systematic review of advances, challenges, and opportunities","authors":"Saeid Jamshidi ,&nbsp;Negar Shahabi ,&nbsp;Amin Nikanjam ,&nbsp;Kawser Wazed Nafi ,&nbsp;Foutse Khomh ,&nbsp;Carol Fung","doi":"10.1016/j.iot.2025.101735","DOIUrl":"10.1016/j.iot.2025.101735","url":null,"abstract":"<div><div>The Internet of Things (IoT) has revolutionized digital ecosystems by interconnecting billions of devices across various industries, enabling enhanced automation, real-time monitoring, and data-driven decision-making. However, this expansion has introduced significant security and privacy challenges due to the heterogeneous nature of IoT devices, resource constraints, and the decentralized nature of their architectures. Large Language Models (LLMs) have recently shown promise in improving cybersecurity by enabling automated threat intelligence, anomaly detection, malware classification, and privacy-aware security enforcement. Therefore, this systematic review investigates research published between 2015 and 2025 to examine the intersection of LLMs, IoT security, and privacy. We evaluate state-of-the-art LLM-based security frameworks, highlighting their effectiveness, limitations, and impact on IoT cybersecurity. In addition, this review identifies key research gaps and challenges, providing insight into the scalability, efficiency, and adaptability of LLM-driven security solutions. This work aims to contribute to the advancement of AI-driven IoT security frameworks, supporting the development of resilient and privacy-preserving cybersecurity architectures.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101735"},"PeriodicalIF":7.6,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920294","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":"Characterizing time-critical internet of things","authors":"Sebastian Leclerc ,&nbsp;Alessio Bucaioni ,&nbsp;Mohammad Ashjaei","doi":"10.1016/j.iot.2025.101721","DOIUrl":"10.1016/j.iot.2025.101721","url":null,"abstract":"<div><div>The Internet of Things (IoT) is increasingly being adopted in diverse domains, many of which require strict timing constraints and predictable behavior. Despite the growing importance of timing characteristics in IoT applications, current approaches to address timing requirements are often fragmented, context-specific, and lack a unified understanding. Consequently, addressing timing aspects in IoT remains largely ad hoc and dependent on individual applications, making it challenging to generalize findings or systematically apply established solutions. The goal of this study is to provide a comprehensive understanding of how timing is defined, characterized, and measured within the IoT community. We conducted this study through a systematic and structured mix methods research approach. First, we performed a systematic review of the literature, extracting and analyzing information from 38 primary studies, selected from a rigorous process involving 1176 studies. Second, to complement the literature findings, we conducted an expert survey involving 28 respondents from academia and industry, representing a variety of roles with specialized expertise in IoT systems and timing-related issues. We identified two primary characterizations of timing within the IoT: time-criticality and predictability. Additionally, we collected and categorized 113 distinct timing metrics from literature into commonly found layers of an IoT system. The majority of the surveyed practitioners and researchers (75%) agree with our categorization and consider this research useful and relevant (71.5%). We believe that our study provides practitioners and researchers with insights into timing characteristics and metrics in IoT applications, towards the ultimate goal of standardization.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101721"},"PeriodicalIF":7.6,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144906799","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":"Resource-efficient fog computing vision system for occupancy monitoring: A real-world deployment in university libraries","authors":"Alejandro S. Martínez-Sala,&nbsp;Lucio Hernando-Cánovas,&nbsp;Juan C. Sánchez-Aarnoutse,&nbsp;Juan J. Alcaraz","doi":"10.1016/j.iot.2025.101748","DOIUrl":"10.1016/j.iot.2025.101748","url":null,"abstract":"<div><div>This paper presents a fog computing system for real-time occupancy monitoring across three university libraries, using ceiling-mounted, top-view cameras positioned above each entrance. Video streams from low-cost cameras are securely transmitted to a fog server deployed within the university’s intranet. Top-view person tracking ensures privacy compliance by inherently eliminating facial recognition, but introduces challenges such as non-standard human appearance, occlusions, and lighting variations. For person detection, we employ a YOLOv5 model initially trained on top-view human annotations, further refined through transfer learning using a curated dataset from the three libraries. The system features a two-stage processing pipeline. First, a lightweight background subtraction algorithm filters frames with potential motion, which are queued via RabbitMQ for sequential processing. Second, a People Flow Counting module applies the optimized YOLOv5 model to detect and count individuals in each frame, followed by a custom tracking algorithm and virtual line-crossing logic to ensure accurate flow tracking. Each library is handled independently through a batch processing approach, updating occupancy estimates with bounded delay using a single CPU-only fog server. This architecture maintains low latency while avoiding server overload and minimizing energy use. The system has been in continuous production for over twelve months, demonstrating reliable performance across all three libraries on commodity hardware. Quantitative evaluation confirms 94 % accuracy in people flow detection, validating the system’s robustness, scalability, and practical utility for long-term, privacy-preserving deployment in smart campus environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101748"},"PeriodicalIF":7.6,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144989076","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":"Visualisation of movement patterns supporting teacher reflection - qualitative analysis of educational benefits of IoT in the classroom","authors":"Patrik Hernwall,&nbsp;Robert Ramberg","doi":"10.1016/j.iot.2025.101743","DOIUrl":"10.1016/j.iot.2025.101743","url":null,"abstract":"<div><div>Research on IoT in educational contexts indicates a need for qualitative studies evaluating IoT technology use in schools. In this article, results from a qualitative study of the use of IoT technology to register and visualise teachers’ movements in the classroom, where visualisations of teachers’ movements are used to support teacher reflection on their practice, is reported. Data were collected through iterative conversations with 18 participating teachers from 9 different schools. In total 72 conversations of between 15 to 40 minutes each were carried out. In a thematic analysis, four themes emerged reflecting the benefits experienced by the teachers; movement, memory support, pupil perspective, collegial use and benefit. The results in sum indicate that visualisation of teachers’ movements support teachers to reflect on their classroom practice by providing an objective representation of movement, as a complement to subjective memory and experience.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101743"},"PeriodicalIF":7.6,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144906798","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":"Soil moisture estimation using continuous wave radar","authors":"Hui Huang ,&nbsp;Kiyoshy Nakamura ,&nbsp;Patricia Becerra ,&nbsp;Jin Zhang ,&nbsp;Tong Hao ,&nbsp;Radu State","doi":"10.1016/j.iot.2025.101718","DOIUrl":"10.1016/j.iot.2025.101718","url":null,"abstract":"<div><div>This work introduces SoilCW, a low maintenance and cost-effective soil moisture monitoring system that uses compact and affordable continuous wave (CW) radar technology. By employing passive metal reflectors to eliminate the need for battery-powered underground sensors, SoilCW helps reduce deployment costs and minimizes the risk of soil contamination. SoilCW operates on the principle that the phase change of radar echoes is related to the moisture content of the soil through which the electromagnetic (EM) wave propagates. To accurately capture the phase changes caused by soil moisture, the SoilCW uses two auxiliary frequencies close to the main radar frequency to eliminate the impact of ground reflection and addresses the phase ambiguity that can occur due to significant variations in signal propagation velocity within the soil. This design utilizes only a narrow bandwidth and does not require an antenna array, commonly needed in existing works. The prototype of SoilCW was developed using a software-defined radio (SDR) board, and extensive evaluations were conducted in laboratory environments, with sandy soil and potting mix loam, as well as field environments with clay soil, and considered various surface coverings such as mulches and rocks. The results show that CW radars are promising for low-cost and accurate soil moisture monitoring. The overall mean absolute error is approximately 1.91% under laboratory conditions, and the results obtained from the field experiments are comparable to those of dedicated industrial grade soil sensors.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101718"},"PeriodicalIF":7.6,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903995","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":"SEACount: Semantic-driven Exemplar query Attention framework for image boosting class-agnostic Counting in Internet of Things","authors":"Xinhui Lin ,&nbsp;Mingzhu Shi ,&nbsp;Yuhao Su ,&nbsp;Wenxin Zhang ,&nbsp;Yujiao Cai ,&nbsp;Lei Liu ,&nbsp;Zhaowei Liu","doi":"10.1016/j.iot.2025.101741","DOIUrl":"10.1016/j.iot.2025.101741","url":null,"abstract":"<div><div>In the Internet of Things (IoT) environment, large amounts of visual data are continuously collected, providing a rich resource for intelligent surveillance and management. For the task of class-agnostic counting in images, this paper proposes the Semantic-driven Exemplar query Attention Counting (SEACount) framework, which aims to quickly adapt and count unseen classes of objects using a few-shot exemplars. This is critical for real-time monitoring and analyzing visual semantic information in IoT. Specifically, we introduce two new components to extend Object Detection with Transformers (DETR): the Exemplar Query Attention (EQA) and the Dynamic Reshaping Module (DRM). EQA injects exemplar queries with rich semantic information into the decoder, facilitating the global image response to exemplar targets and enhancing the exemplar-to-image similarity metrics. The DRM, instead of only utilizing decoder features, fuses them with image features to enhance local details, reduce noise interference, and reshape the feature maps required for predicting density maps. This approach efficiently captures exemplar-relevant targets in images and quickly adapts to new categories without fine-tuning. Experimental results demonstrate that our proposed SEACount framework significantly outperforms other state-of-the-art methods on the latest FSC-147 dataset. We release the code at <span><span>https://github.com/lxinhui1109/SEACount.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"34 ","pages":"Article 101741"},"PeriodicalIF":7.6,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144906797","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":"PQ-BCDA: A post-quantum blockchain based cross-domain authentication scheme for Internet of Things","authors":"Shuanggen Liu ,&nbsp;Siyuan Rao ,&nbsp;Xu An Wang ,&nbsp;Kexin Tian ,&nbsp;Yue Wang","doi":"10.1016/j.iot.2025.101737","DOIUrl":"10.1016/j.iot.2025.101737","url":null,"abstract":"<div><div>The growing deployment of Internet of Things (IoT) devices across heterogeneous trust domains raises critical concerns for secure and efficient cross-domain authentication, especially under the emerging threat of quantum computing. Existing approaches often rely on centralized authorities or classical cryptographic primitives, making them vulnerable to single points of failure and future cryptanalytic advances. To address these challenges, this paper proposes PQ-BCDA, a novel post-quantum cross-domain authentication scheme that combines the Extended Merkle Signature Scheme (XMSS) with a consortium blockchain framework. Our scheme introduces an automated signature lifecycle management mechanism via smart contracts, enabling decentralized trust management and secure authentication without relying on centralized anchors. We formalize a tailored security model based on established frameworks and provide a detailed proof in the random oracle model, ensuring session key secrecy, mutual authentication, and resistance to common attacks. Experimental evaluations on real hardware platforms, demonstrate that PQ-BCDA reduces computational and storage costs by 46% and 33%, respectively.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101737"},"PeriodicalIF":7.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890106","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}