Internet of Things最新文献

{"title":"Optimization strategies for neural network deployment on FPGA: An energy-efficient real-time face detection use case","authors":"Mhd Rashed Al Koutayni,&nbsp;Gerd Reis,&nbsp;Didier Stricker","doi":"10.1016/j.iot.2025.101676","DOIUrl":"10.1016/j.iot.2025.101676","url":null,"abstract":"<div><div>Field programmable gate arrays (FPGAs) are considered promising platforms for accelerating deep neural networks (DNNs) due to their parallel processing capabilities and energy efficiency. However, Deploying DNNs on FPGA platforms for computer vision tasks presents unique challenges, such as limited computational resources, constrained power budgets, and the need for real-time performance. This work presents a set of optimization methodologies to enhance the efficiency of real-time DNN inference on FPGA system-on-a-chip (SoC) platforms. These optimizations include architectural modifications, fixed-point quantization, computation reordering, and parallelization. Additionally, hardware/software partitioning is employed to optimize task allocation between the processing system (PS) and programmable logic (PL), along with system integration and interface configuration. To validate these strategies, we apply them to a baseline face detection DNN (FaceBoxes) as a use case. The proposed techniques not only improve the efficiency of FaceBoxes on FPGA but also provide a roadmap for optimizing other DNN-based applications for resource-constrained platforms. Experimental results on the AMD Xilinx ZCU102 board with VGA resolution (<span><math><mrow><mn>480</mn><mo>×</mo><mn>640</mn><mo>×</mo><mn>3</mn></mrow></math></span>) input demonstrate a significant increase in efficiency, achieving real-time performance while substantially reducing dynamic energy consumption.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101676"},"PeriodicalIF":6.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597456","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":"Joint trajectory and incentive optimization for privacy-preserving UAV crowdsensing via multi-agent federated reinforcement learning","authors":"Chaoyang Zhu ,&nbsp;Xiao Zhu ,&nbsp;Tuanfa Qin","doi":"10.1016/j.iot.2025.101689","DOIUrl":"10.1016/j.iot.2025.101689","url":null,"abstract":"<div><div>UAV-assisted mobile crowdsensing (MCS) presents a promising paradigm for enhancing data collection in smart city environments, but faces a critical systems challenge: the intricate coupling between spatial trajectory planning, economic incentive mechanisms, and information-theoretic privacy guarantees. Traditional approaches addressing these dimensions in isolation often lead to suboptimal performance. In this paper, we propose <strong>PRISM</strong>, a <em>unified framework</em> designed around a holistic optimization approach with three components. First, PRISM models the strategic interactions among Service Providers, UAVs, and ground devices through a multi-level Stackelberg game, capturing the hierarchical economic dynamics that influence participation decisions. Second, it incorporates a privacy-aware incentive mechanism that explicitly links UAV navigation decisions to privacy constraints, dynamically managing the privacy-utility trade-off based on data quality. Third, to address the resulting multi-objective optimization across distinct decision timescales, we introduce <strong>TMFR</strong>, a Two-timescale Multi-agent Federated Reinforcement Learning algorithm that enables UAVs to collaboratively learn policies for both spatial navigation and incentive allocation. Experimental evaluations demonstrate that TMFR achieves 30% faster convergence and 20% higher data quality compared to baselines that optimize only subsets of the problem. These results highlight its suitability for next-generation smart city applications.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101689"},"PeriodicalIF":6.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579210","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 intelligent and secure internet of robotic things: A review and conceptual framework","authors":"Md. Abdur Rahim ,&nbsp;Mohammad Rokonuzzaman ,&nbsp;Ahmad Abu Alqumsan ,&nbsp;Adetokunbo Arogbonlo ,&nbsp;Md. Zohirul Islam ,&nbsp;Hieu Trinh ,&nbsp;Md Shofiqul Islam","doi":"10.1016/j.iot.2025.101684","DOIUrl":"10.1016/j.iot.2025.101684","url":null,"abstract":"<div><div>Robots are increasingly being deployed across various fields and applications, including agriculture, manufacturing, transportation, surveillance, and rescue missions. The integration of technologies such as Artificial Intelligence (AI) and the Internet of Things (IoT) with robotics significantly enhances their capabilities and expands their range of applications. Rapid advancements in these technologies have driven notable progress in robotics research, particularly in the domain of AI-enabled Internet of Robotic Things (IoRT). However, our extensive literature study finds that there is a growing need for the development of big data–enabled secure IoRT systems capable of handling vast amounts of data generated by large-scale heterogeneous, homogeneous robots and multiple stakeholders. Addressing this need is essential to meet modern industrial and societal demands. Therefore, this paper presents a conceptual framework for AI-enabled, big data analytics–driven secure and reliable IoRT, based on a comprehensive review of the literature. The framework emphasizes key enabling technologies, including connectivity, cloud and edge computing, big data analytics, and cybersecurity systems, with the ultimate aim of supporting the transition to Industry 5.0. Furthermore, we explore several promising research directions that could enhance the intelligence and security of future IoRT systems. Before concluding, we provide an in-depth discussion of the benefits, limitations, and challenges associated with IoRT. We hope this work will serve as a valuable resource for researchers and practitioners in advancing next-generation intelligent robotic systems for the betterment of society.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101684"},"PeriodicalIF":6.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579139","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 feedback-driven brain organoid platform enables automated maintenance and high-resolution neural activity monitoring","authors":"Kateryna Voitiuk ,&nbsp;Spencer T. Seiler ,&nbsp;Mirella Pessoa de Melo ,&nbsp;Jinghui Geng ,&nbsp;Tjitse van der Molen ,&nbsp;Sebastian Hernandez ,&nbsp;Hunter E. Schweiger ,&nbsp;Jess L. Sevetson ,&nbsp;David F. Parks ,&nbsp;Ash Robbins ,&nbsp;Sebastian Torres-Montoya ,&nbsp;Drew Ehrlich ,&nbsp;Matthew A.T. Elliott ,&nbsp;Tal Sharf ,&nbsp;David Haussler ,&nbsp;Mohammed A. Mostajo-Radji ,&nbsp;Sofie R. Salama ,&nbsp;Mircea Teodorescu","doi":"10.1016/j.iot.2025.101671","DOIUrl":"10.1016/j.iot.2025.101671","url":null,"abstract":"<div><div>The analysis of tissue cultures requires a sophisticated integration and coordination of multiple technologies for monitoring and measuring. We have developed an automated research platform enabling independent devices to achieve collaborative objectives for feedback-driven cell culture studies. Our approach enables continuous, communicative, non-invasive interactions within an Internet of Things (IoT) architecture among various sensing and actuation devices, achieving precisely timed control of <em>in vitro</em> biological experiments. The framework integrates microfluidics, electrophysiology, and imaging devices to maintain cerebral cortex organoids while measuring their neuronal activity. The organoids are cultured in custom, 3D-printed chambers affixed to commercial microelectrode arrays. Periodic feeding is achieved using programmable microfluidic pumps. We developed a computer vision fluid volume estimator used as feedback to rectify deviations in microfluidic perfusion during media feeding/aspiration cycles. We validated the system with a set of 7-day studies of mouse cerebral cortex organoids, comparing manual and automated protocols. It was shown that the automated protocols maintained robust neural activity throughout the experiment while enabling hourly electrophysiology recordings during the experiments. The median firing rates of neural units increased for each sample, and dynamic patterns of organoid firing rates were revealed by high-frequency recordings. Surprisingly, feeding did not affect the firing rate. Furthermore, media exchange during a recording did not show acute effects on firing rate, enabling the use of this automated platform for reagent screening studies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101671"},"PeriodicalIF":6.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597463","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":"Digital Twins in Additive Manufacturing: A systematic review","authors":"Md Manjurul Ahsan ,&nbsp;Yingtao Liu ,&nbsp;Shivakumar Raman ,&nbsp;Zahed Siddique","doi":"10.1016/j.iot.2025.101692","DOIUrl":"10.1016/j.iot.2025.101692","url":null,"abstract":"<div><div>Digital Twins (DTs) are becoming popular in Additive Manufacturing (AM) due to their ability to create virtual replicas of physical components of AM machines, which helps in real-time production monitoring. Advanced techniques such as Machine Learning (ML), Augmented Reality (AR), and simulation-based models play key roles in developing intelligent and adaptable DTs in manufacturing processes. However, questions remain regarding scalability, the integration of high-quality data, and the computational power required for real-time applications in developing DTs. Understanding the current state of DTs in AM is essential to address these challenges and fully utilize their potential in advancing AM processes. Considering this opportunity, this work aims to provide a comprehensive overview of DTs in AM by addressing the following four research questions: (1) What are the key types of DTs used in AM and their specific applications? (2) What are the recent developments and implementations of DTs? (3) How are DTs employed in process improvement and hybrid manufacturing? (4) How are DTs integrated with Industry 4.0 technologies? By discussing current applications and techniques, we aim to offer a better understanding and potential future research directions for researchers and practitioners in AM and DTs.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101692"},"PeriodicalIF":6.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597457","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":"Design of an innovative solution to integrate and orchestrate IoT technologies with chatbots for smart home automation","authors":"Muhammad Ans ,&nbsp;Teodoro Montanaro ,&nbsp;Ilaria Sergi ,&nbsp;Giovanni Troisi ,&nbsp;Andrea Sponziello ,&nbsp;Miriam Pezzuto ,&nbsp;Luigi Patrono","doi":"10.1016/j.iot.2025.101693","DOIUrl":"10.1016/j.iot.2025.101693","url":null,"abstract":"<div><div>Nowadays, smart homes are rapidly gaining popularity but significant challenges still affect the sector. For instance, optimizing energy usage is essential to fully harness their potentiality. Many existing solutions rely on conventional control methods that require user interaction or need experts to configure complex automatic rules. This paper presents an innovative framework that exploits multiple chatbots to autonomously manage operations in smart homes. The framework acts at all the levels of an IoT system by autonomously: collect real-time data from sensors, interpret data, make decisions based on revealed situations, actuate strategies through actuators, and contact users in case of criticalities. Such an automation is performed through three different types of chatbots, i.e., AutomationBot, SensorBot, and ActuatorBot, each performing dedicated roles in real-time system monitoring, decision-making, and operation management. They autonomously manage and coordinate operations, only escalating issues to the user in critical scenarios, ensuring efficient system functioning with minimal user involvement 24 h a day, 7 days a week. It can be programmed by every kind of user through the provided no-code platform. The system’s effectiveness has been assessed through a series of experiments conducted in a simulated smart home environment developed through various technologies (i.e., MQTT, RabbitMQ, Raspberry Pi, Tiledesk-Chat21) focusing on heat pump management and indoor environmental condition regulation. Our results highlight that the chatbot system could independently monitor, control, and optimize operation of critical devices, maintaining operational reliability and user comfort with manual intervention. The framework represents a significant step toward realizing fully autonomous chatbot-driven smart homes.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101693"},"PeriodicalIF":6.0,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572077","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":"Pow-MUCB: A new client selection method based on Pow-d and modified UCB for federated learning in IoT","authors":"Naghmeh Khajehali ,&nbsp;Jun Yan ,&nbsp;Yang-Wai Chow ,&nbsp;Mahdi Fahmideh","doi":"10.1016/j.iot.2025.101687","DOIUrl":"10.1016/j.iot.2025.101687","url":null,"abstract":"<div><div>Federated learning (FL) is a collaborative machine learning (ML) approach that enables distributed training between multiple clients, achieving collective intelligence while preserving privacy. In FL, client selection (CS) plays an important role in choosing a portion of clients for training. The more efficient CS is, the more FL’s performance will be improved. A balanced CS is required to reduce the effects of discrepancies between clients’ local data and clients’ performance. For this problem, using historical data can be an effective solution. Due to a lack of reasonable and balanced use of historical data, existing CS methods in the literature suffer from serious drawbacks, like over/under-representation of clients, and data model skewness. This can adversely affect FL performance, particularly in terms of convergence rate and model accuracy. To help solve these challenges, this paper proposes a new CS method (Pow-MUCB) which is based on the Power of choice-(Pow-d-) and is equipped with a new, modified Upper Confidence Bound (UCB) approach to evaluate the clients’ contribution and performance. This method selects clients whose participation results in more balanced, representative selection and informative global updates, avoids over/ underrepresentation of clients, and model skewness, improving overall FL performance. To validate the method’s performance in both static and dynamic client sets, comprehensive comparisons and experimental results are provided. The results demonstrated that Pow-MUCB enhances the overall performance and significantly outperforms the existing baselines in terms of global model accuracy (up to 7%), convergence rate, resulting from a reduced communication rounds needed to reach the convergence.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101687"},"PeriodicalIF":6.0,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587609","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 energy-balanced and load-aware routing algorithm based on molecular diffusion theory for energy harvesting assisted WSN","authors":"Sheng Hao ,&nbsp;Junwei Gao ,&nbsp;Jianqun Cui ,&nbsp;Yinyi Chen ,&nbsp;Xiying Fan ,&nbsp;Zhen Li","doi":"10.1016/j.iot.2025.101691","DOIUrl":"10.1016/j.iot.2025.101691","url":null,"abstract":"<div><div>Energy Harvesting-Wireless Sensor Networks (EH-WSNs) play a crucial role in the development of Green Internet of Things (GIoT). While the energy-harvesting process alleviates the constraints of energy supply in WSNs, most current routing protocols for EH-WSNs inadequately account for the heterogeneity in energy states and traffic loads among sensor nodes, which may impair the energy efficiency and transmission performance of networks. To address the above issues, we utilize molecular diffusion theory to design an energy-balanced and load-aware routing algorithm (EBLARA-MD for short) for EH-WSNs. Initially, we construct a dual EH prediction model based on the clustering Markov chain (MC) method, to accurately forecast the amount of solar and wind power generation. Subsequently, an energy-rank model is established to assess the energy levels of nodes. Building on this, we propose a cross-layer adjustment scheme to avoid energy depletion and wastage. Namely, at the Media Access Control (MAC) layer, the backoff time is optimized dynamically to affect the channel access probability of each node; at the physical layer, the transmission power is determined adaptively by considering the wireless fading property. In addition, we construct a load-aware model to reflect the congestion degree of data buffer. Finally, we leverage molecular diffusion theory to allocate the routing probabilities for suitable paths. Simulation results demonstrate that the proposed routing algorithm achieves superior performance in terms of energy efficiency, end-to-end delay variance, and packet delivery ratio.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101691"},"PeriodicalIF":6.0,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579209","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 interpretable deep learning framework for intrusion detection in industrial Internet of Things","authors":"Jawad Ahmad ,&nbsp;Shahid Latif ,&nbsp;Imdad Ullah Khan ,&nbsp;Mohammed S. Alshehri ,&nbsp;Muhammad Shahbaz Khan ,&nbsp;Nada Alasbali ,&nbsp;Weiwei Jiang","doi":"10.1016/j.iot.2025.101681","DOIUrl":"10.1016/j.iot.2025.101681","url":null,"abstract":"<div><div>The Industrial Internet of Things (IIoT) has revolutionized smart industries by optimizing industrial operations and accelerating the decision-making process. However, its inherently distributed architecture presents complex and evolving security threats. Traditional machine learning (ML) and deep learning (DL)-based intrusion detection systems (IDSs) often lack interpretability, which undermines their trustworthiness in critical IIoT environments. To overcome these limitations, we propose XGRU-IDS, an explainable hybrid DL-based IDS that combines the strengths of the Extra Trees Classifier (ETC) for feature selection and Gated Recurrent Units (GRU) for sequential attack detection. The ETC enhances model input quality by identifying the most influential features, while the GRU processes temporal dependencies to detect sophisticated intrusion patterns. Explainability is ensured through SHapley Additive exPlanations (SHAP), which offer class-wise insights via summary plots, feature importance scores, and force plots. XGRU-IDS is evaluated on the multiclass CICIoT2023 dataset, which covers all 34 attack types. It achieves 97.56% accuracy, outperforming recent state-of-the-art DL and explainable IDS approaches. This work demonstrates that high detection accuracy can coexist with transparency, providing a robust and trustworthy IDS solution for resource-constrained IIoT networks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101681"},"PeriodicalIF":6.0,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535936","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":"Novel deep learning-based IoT network attack detection using magnet loss optimization","authors":"Chi Duc Luu ,&nbsp;Viet Hung Nguyen ,&nbsp;Van Quan Nguyen ,&nbsp;Ngoc-Son Vu","doi":"10.1016/j.iot.2025.101680","DOIUrl":"10.1016/j.iot.2025.101680","url":null,"abstract":"<div><div>The increasing prevalence of Internet of Things (IoT) devices across various industries has raised critical security concerns due to their inherent vulnerabilities and high interconnectivity. While traditional security mechanisms have shown limitations in effectively securing large IoT networks, machine learning (ML) and deep learning (DL) methods have been explored to tackle the attack detection problem in this domain. However, existing approaches still lack optimal regularization and have limited comprehensiveness in validation across different IoT-centric datasets. To address these challenges, this research proposes the extension of the Deep Magnet Autoencoder (DMAE) and introduces a novel approach, the Cascade Deep Magnet Autoencoder (CDMAE), leveraging the Magnet Loss optimization as regularization for better class distinction through local separation in latent space. This enhanced class clustering strengthens attack detection by maximizing inter-class separation while compactly grouping data points of the same class, leading to more precise identification of benign and malicious traffic. Extensive experiments conducted on three contemporary IoT datasets, CIC-BoT–IoT, CIC-ToN–IoT, and CICIoT2023, demonstrate that our proposed models are able to produce meaningful latent representations with powerful discrimination between benign and malicious IoT network data. Empirical insights for fine-tuning the model are also provided through supplementary experiments. Comprehensive results show that the proposed methods significantly boost classification across different IoT datasets with high metric scores, outperforming other approaches.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"33 ","pages":"Article 101680"},"PeriodicalIF":6.0,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510875","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}