Internet of Things最新文献

{"title":"GDSSA-Net: A gradually deeply supervised self-ensemble attention network for IoMT-integrated thyroid nodule segmentation","authors":"Muhammad Umar Farooq ,&nbsp;Haris Ghafoor ,&nbsp;Azka Rehman ,&nbsp;Muhammad Usman ,&nbsp;Dong-Kyu Chae","doi":"10.1016/j.iot.2025.101598","DOIUrl":"10.1016/j.iot.2025.101598","url":null,"abstract":"<div><div>The integration of deep learning techniques in the <em>Internet of Medical Things</em> (IoMT) has significantly advanced the early detection of life-threatening diseases such as thyroid cancer, one of the most lethal tumors. Accurate delineation of thyroid nodules in ultrasound images is essential for timely diagnosis and for effective treatment. This research introduces a novel deep-learning framework tailored for IoMT environments, aimed at the automatic segmentation of thyroid nodules in ultrasound images. We propose a <em>Gradually Deeply Supervised Self-ensemble Attention Network</em> (GDSSA-Net), which employs encoder to extract features from sonographic scans and integrates a gated attention mechanism within the decoder to refine features while filtering out irrelevant information. To enhance the learning process, we developed a novel Gradual Deep Supervision (GDS) strategy, utilizing three variations of ground truth to deeply supervise the network. Additionally, our approach employs self-ensembling mechanisms by ensembling outputs of the shallower branches alongside the main branch to improve the thyroid nodule segmentation. To validate the superiority and generalizability of GDSSA-Net, we conducted extensive evaluations on two publicly available datasets, DDTI and TN3K. Experimental results demonstrate that our method surpasses its simplified variants and existing state-of-the-art models in terms of quantitative metrics and qualitative assessments. Specifically, our model achieves a Dice coefficient of 79.85% and 84.27% on DDTI and TN3K, respectively. The source code for our proposed model is publicly available at <span><span>https://github.com/harisghafoor/GDSSA-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101598"},"PeriodicalIF":6.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759776","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":"Optimizing waste management with integrated AIoT, edge computing, and LoRaWAN communication technologies","authors":"Abdelaziz Daas ,&nbsp;Bilal Sari ,&nbsp;Fouzi Semchedine ,&nbsp;Mourad Amad","doi":"10.1016/j.iot.2025.101546","DOIUrl":"10.1016/j.iot.2025.101546","url":null,"abstract":"<div><div>This work presents <strong>Smart EcoRecycler Manager</strong>, an integrated waste management system designed to address inefficiencies in traditional recycling through automation and user engagement. The system combines a smart bin with AI-driven waste sorting, low-power wireless communication (LoRaWAN), and a user-friendly mobile app to incentivize recycling. Key innovations include: <strong>AI-powered waste classification</strong> achieving 99% accuracy for plastic and metal sorting, enabled by machine learning on low-cost edge devices (ESP32-CAM), <strong>Real-time optimization</strong> of waste collection routes, reducing operational costs compared to conventional methods, A <strong>gamified rewards system</strong> that boosts user participation through redeemable points, addressing low recycling rates.</div><div>The system uniquely integrates edge computing for real-time processing, LoRaWAN for long-range communication, and cloud platforms (Firebase) for scalable data management. Performance testing demonstrates significant improvements in waste segregation accuracy, cost efficiency, and user engagement. By combining these features, our solution addresses critical gaps in existing systems, such as limited scalability, high energy consumption, and poor user incentives. This work advances smart waste management by providing a practical, low-cost framework suitable for urban and remote areas alike, with measurable environmental and economic benefits.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101546"},"PeriodicalIF":6.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759777","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":"EVACUSCAPE: Internet of Things-enabled emergency evacuation based on matching theory","authors":"Joshua R. Atencio ,&nbsp;Md Sadman Siraj ,&nbsp;Eirini Eleni Tsiropoulou","doi":"10.1016/j.iot.2025.101581","DOIUrl":"10.1016/j.iot.2025.101581","url":null,"abstract":"<div><div>The effective evacuation during disaster scenarios, either physical or man-made, is critical in order to ensure the safety and survival of the victims, minimize the casualties, and facilitate the rapid and organized movement of people to safety. In this paper, the EVACUSCAPE model is introduced to optimize the matching between victims and evacuation routes during an evacuation process. Initially, the characteristics of both the victims and the evacuation routes are analyzed to establish a foundational matching mechanism among them. The Approximate EVACUSCAPE algorithm is developed to perform an initial matching between the victims and the evacuation routes by disregarding externalities that influence the victims’ decisions, such as the actions of other evacuees. Then, the Accurate EVACUSCAPE algorithm refines the matching process by incorporating the principles of coalition games to account for these externalities and ultimately derive an optimal and stable evacuation strategy. A comprehensive evaluation using real-world datasets demonstrates the effectiveness and robustness of the EVACUSCAPE model, which significantly outperforms conventional evacuation strategies where the victims select routes based solely on proximity or time-optimization in a selfish manner.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101581"},"PeriodicalIF":6.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735006","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 Explainable Artificial Intelligence empowered energy efficient indoor localization framework for smart buildings","authors":"Zeynep Turgut","doi":"10.1016/j.iot.2025.101586","DOIUrl":"10.1016/j.iot.2025.101586","url":null,"abstract":"<div><div>The indoor localization problem remains a prominent and extensively debated area of research, lacking a universally accepted solution, especially within the context of smart buildings. A major concern revolves around the energy consumption associated with indoor localization systems. This study presents a proposed framework for an energy-efficient indoor localization system designed for smart buildings. The approach focuses on a fingerprinting indoor localization technique that involves constructing a signal map. To address challenges arising from distinct signal effects and the environment-specific structure of signal maps, the study introduces a framework incorporating an adaptive filter selection scheme. This scheme includes Kalman, particle, and Savitzky–Golay filters in the pre-processing stage to enhance the signal map. Rather than resorting to additional hardware for improved localization accuracy, the study advocates for optimizing the signal map to minimize energy consumption. Additionally, the research emphasizes the selection of effective features for machine learning techniques to enhance performance and boost localization accuracy. The findings are subjected to analysis using Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) Explainable Artificial Intelligence (XAI) models. The investigation delves into the impact of each signal and filter on positioning estimation, providing a comprehensive understanding of the system’s functionality.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101586"},"PeriodicalIF":6.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143746774","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":"Attention-augmented multi-agent collaboration for Smart Industrial Internet of Things task offloading","authors":"Yihang Wang ,&nbsp;Shengchao Su ,&nbsp;Yiwang Wang","doi":"10.1016/j.iot.2025.101572","DOIUrl":"10.1016/j.iot.2025.101572","url":null,"abstract":"<div><div>The integration of Multi-access Edge Computing (MEC) technology within the Smart Industrial Internet of Things (SIIoT) ecosystem can significantly enhance both computational and storage capabilities. This advancement facilitates improved data processing and a more efficient utilization of resources in industrial applications. However, the high density of devices typical of SIIoT environments often presents several challenges, including a low success rate for task offloading, increased latency, higher energy consumption, and the risk of overloading edge servers. This paper addresses these challenges by treating Smart Devices (SDs) as agents and proposing a collaborative multi-agent task offloading strategy. A computational offloading model has been developed to minimize delayed energy consumption, which is then formulated as a Multi-Agent Partially Observable Markov Decision Process (MAPOMDP) featuring a hybrid action space composed of discrete and continuous elements. An attention mechanism is introduced to tackle the complex competition for edge server resources among SDs during the offloading process, enabling the observation of the actions and states of other devices within the system. A Prioritized Experience Replay (PER) mechanism is employed to optimize the training process. A Multi-Agent Attention Deep Reinforcement Learning (MA2DRL) algorithm is proposed to improve computational task offloading. Experimental results demonstrate that the proposed algorithm outperforms other comparative algorithms regarding task offloading latency, average energy consumption, offloading success rate, and server load variance.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101572"},"PeriodicalIF":6.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735008","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 effective IoT interface considering an eye-tracking method for autonomous vehicle","authors":"Junghoon Park","doi":"10.1016/j.iot.2025.101583","DOIUrl":"10.1016/j.iot.2025.101583","url":null,"abstract":"<div><div>The number of Internet-connected devices is steadily increasing, exceeding 25 billion globally and projected to surpass 50 billion about 6.5 times the world population. At the core of IoT is data collection via sensors, forming big data for AI-driven analysis, optimization, and visualization. A convenient control environment is essential for devices like autonomous vehicles, requiring new interfaces such as touchless eye movement. This research proposes a real-time eye-tracking method using a single web camera, easily installed in cars and integrated with IoT. The system detects gaze by recognizing iris shape, enabling software-only tracking without extra hardware. Experiments show a mean absolute error (MAE) of 3.49°, ensuring accuracy even with head movement. Unlike existing infrared (IR) LED or head-mounted methods, this approach offers a cost-effective, real-time solution. Using lightweight image processing instead of deep learning, the system achieves real-time tracking with low latency, making it ideal for low-power IoT and autonomous vehicles. It is expected to become a next-generation input interface for these applications.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101583"},"PeriodicalIF":6.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143746773","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":"DeMiRaR-6T: A new defense method for detecting and mitigating rank attacks in RPL-based 6TiSCH networks","authors":"Hakan Aydin,&nbsp;Burak Aydin,&nbsp;Sedat Gormus","doi":"10.1016/j.iot.2025.101582","DOIUrl":"10.1016/j.iot.2025.101582","url":null,"abstract":"<div><div>The Industrial Internet of Things (IIoT) has revolutionized the industrial sector with advanced automation and connectivity. IIoT applications widely implement the IPv6 over the Time Slotted Channel Hopping (TSCH) mode of IEEE 802.15.4e (6TiSCH) protocol in conjunction with the Routing Protocol for Low-Power and Lossy Networks (RPL) to ensure reliable communication. However, the RPL protocol is vulnerable to security attacks that target network topology, traffic, and node resources. These attacks pose significant risks to the integrity and reliability of IIoT systems, particularly rank attacks, in which malicious nodes manipulate rank values to disrupt communication. In order to enhance the security of IIoT technology, this study introduces DeMiRaR-6T, a method that effectively detects and mitigates rank attacks in 6TiSCH networks. DeMiRaR-6T relies on two key components. First, it incorporates a monitoring mechanism that continuously tracks node behavior, analyzing network activities to identify abnormal patterns indicative of rank attacks. Second, it utilizes a centralized authority (Join Registrar/Coordinator, Rank Control Unit) to maintain and disseminate an updated list of attacker nodes. This trusted entity collects information about malicious nodes and notifies other network participants, enabling them to adapt their communication strategies and take preventive actions. Through this comprehensive approach, DeMiRaR-6T enhances the security of RPL-based 6TiSCH networks. Experimental results demonstrate that under attack conditions, DeMiRaR-6T achieves up to a 12% increase in packet delivery rate and a 20% improvement in throughput compared to state-of-the-art methods. Additionally, notable enhancements are observed in control packet overhead, end-to-end delay, and energy consumption.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101582"},"PeriodicalIF":6.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725741","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":"MmWave beam path blockage prevention through codebook value prediction under domain shift","authors":"Bram van Berlo,&nbsp;Tanir Ozcelebi,&nbsp;Nirvana Meratnia","doi":"10.1016/j.iot.2025.101584","DOIUrl":"10.1016/j.iot.2025.101584","url":null,"abstract":"<div><div>Use of millimeter and terahertz spectra for communication is very sensitive to obstacles blocking signal beam paths. Beam angle codebook values can be adapted to control beam operation angles for blockage prevention, but this requires prediction of beam paths that are blocked. The performance of the prediction pipeline may be affected by domain factors such as physical characteristics of an operation environment and a specific blocker. This can be illustrated by artificially introducing domain factor shifts between training and test data subsets where a specific domain factor is left out of the training subset. Our experiments reveal significant performance drops in the blockage prediction performance on left-out test subset folds that contain all the samples of a specific domain factor. Thus, the prediction pipeline must employ effective domain shift mitigation techniques to attain consistent prediction performance in different domains. Pipeline performance should be supported by logical input data to prediction causation. We quantify causation by means of Shapley importance values with input regions attributable to signal aspects such as linear array antennas. Shapley importance results show high neural network prediction confidence value affection for amplitude variance and a limited set of subsequent fast-time blocks. Random inductively biased convolutions affection differs in a limited number of spatially separated antennas causing affection. Equally high prediction confidence value affection is assumed for iterative component search due to internal extraction mechanics and time complexity increases when zero-masking input data regions. We link equally high assumed prediction confidence value affection for iterative component search to highly logical IF signal to prediction causation. The affection of amplitude variance and a limited set of subsequent fast-time blocks shows weaker causation, still considered logical if the neural network can separate observations in representation distributions for varying distance and angle combination sets. The random inductively biased convolutions show illogical causation. They rely on direct IF signal features. Affection by a limited number of antennas indicates reliance on features with inadequate separation ability along angles at appropriate resolution.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101584"},"PeriodicalIF":6.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of light variations on drone’s visual positioning","authors":"Che-Cheng Chang,&nbsp;Po-Ting Wu,&nbsp;Bo-Yu Liu,&nbsp;Bo-Ren Chen","doi":"10.1016/j.iot.2025.101578","DOIUrl":"10.1016/j.iot.2025.101578","url":null,"abstract":"<div><div>Positioning systems and algorithms play a crucial role in drone applications. Although Global Positioning Systems (GPS) are the most widely used method for drone localization, they are not always reliable and accurate in some scenarios. A recent study explores the visual-based positioning method, using Convolutional Neural Networks (CNNs) to match geometric features for drone positioning. The authors use an orthophotomap obtained from an actual drone to evaluate their algorithm. This can reduce the gap between research and practical operation. However, the approach overlooks the impact of lighting variations on positioning performance, i.e., brightness and color temperature. To address this limitation, we propose a novel CNN architecture to handle lighting variations. Our method improves reliability, accuracy, and computational complexity under varying lighting conditions by incorporating several critical components into the network. Remarkably, our architecture has only 51.35% trainable parameters and 83.97% floating point operations (FLOPs) of the existing one. Still, we can exceed it by 3.73% while not considering light variations and average 2.36% while considering light variations. The experimental results, also derived from an orthophotomap obtained via an actual drone, demonstrate that our approach effectively mitigates the challenges induced by lighting changes, ensuring reliable and accurate drone localization.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101578"},"PeriodicalIF":6.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696990","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":"Proposal for a security and privacy enhancement system for private smart environments","authors":"Sonia Solera-Cotanilla ,&nbsp;Manuel Álvarez-Campana ,&nbsp;Carmen Sánchez-Zas ,&nbsp;Mario Vega-Barbas","doi":"10.1016/j.iot.2025.101585","DOIUrl":"10.1016/j.iot.2025.101585","url":null,"abstract":"<div><div>Far from being considered a consolidated and regulated paradigm, the Internet of Things has multiple unaddressed challenges that open the way to unresolved security and privacy issues. The reality is that just as technology has evolved, so have attacks on devices, which are becoming increasingly sophisticated and complicated to prevent and detect. This problem is of particular concern in private environments where sensitive data are handled and which, on many occasions, require an early response to conditions of uncertainty. In this sense, this paper contributes to improving the security and privacy of connected devices in private environments. To this end, we propose a system for managing the security and privacy of connected devices that is adaptable to the environment’s requirements. This system, integrated in the router, consists of a set of components that address the problem through the tasks of monitoring and data acquisition, information storage, data analysis, event processing, and data visualisation. Finally, a set of mechanisms is proposed to further automate the secure integration and continuous monitoring of devices in order to make processes more secure and efficient. Thus, these mechanisms, which can be integrated into the proposed system, provide the environment with real-time management capabilities of the devices and notification of alerts detected in the home network, with the sole purpose of keeping the environment secure against possible threats and attacks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"31 ","pages":"Article 101585"},"PeriodicalIF":6.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}