Internet of Things最新文献_第3页

Energy-efficient throughput optimization in UAV-based microservice networks for rural connectivity scenarios 农村互联场景下基于无人机的微业务网络节能吞吐量优化

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-24 DOI: 10.1016/j.iot.2026.101880

José Gómez-delaHiz , Aymen Fakhreddine , Jaime Galán-Jiménez

The research community is currently exploring the use of Unmanned Aerial Vehicle (UAV) networks to address coverage challenges in rural and economically disadvantaged regions. By equipping UAVs with small cells, coverage can be improved in areas where network operators are not prone to invest due to low Return on Investment. If there is a requirement from users in rural scenarios to achieve higher throughput (for instance, users seeking IoT services with stringent Quality-of-Service requirements), deploying multiple UAVs in the same area could be an effective strategy. However, this approach would also result in increased energy consumption. This paper addresses the challenge of maximizing the throughput offered in rural areas for users accessing microservice-based IoT applications, while also minimizing the energy consumption of UAV swarms. To achieve this, an optimal solution is proposed through a Mixed Integer Linear Programming (MILP) model, which is evaluated within realistic environments. Since this placement problem is complex due to its NP hard nature, in order to obtain solutions for large scenarios in tractable times, we also present a genetic algorithm (GA) that obtains results close to those reported by the MILP with a remarkable reduction in the computation time. Specifically, the optimality gap of the proposed GA-based solution is on average 2.32%, with a reduction of 89.92% in the computation time.

研究界目前正在探索使用无人机（UAV）网络来解决农村和经济落后地区的覆盖挑战。通过为无人机配备小型基站，可以在网络运营商由于投资回报率低而不倾向于投资的地区改善覆盖范围。如果农村用户要求实现更高的吞吐量（例如，用户寻求具有严格服务质量要求的物联网服务），在同一区域部署多架无人机可能是一种有效的策略。然而，这种方法也会导致能源消耗的增加。本文解决了在农村地区为用户访问基于微服务的物联网应用提供最大吞吐量的挑战，同时也最大限度地减少了无人机群的能耗。为了实现这一目标，通过混合整数线性规划（MILP）模型提出了最优解，并在实际环境中进行了评估。由于该放置问题由于其NP困难性质而变得复杂，为了在可处理的时间内获得大型场景的解决方案，我们还提出了一种遗传算法（GA），该算法获得的结果与MILP报告的结果接近，并且显著减少了计算时间。具体而言，基于遗传算法的方案的最优性差距平均为2.32%，计算时间减少了89.92%。

{"title":"Energy-efficient throughput optimization in UAV-based microservice networks for rural connectivity scenarios","authors":"José Gómez-delaHiz , Aymen Fakhreddine , Jaime Galán-Jiménez","doi":"10.1016/j.iot.2026.101880","DOIUrl":"10.1016/j.iot.2026.101880","url":null,"abstract":"<div><div>The research community is currently exploring the use of Unmanned Aerial Vehicle (UAV) networks to address coverage challenges in rural and economically disadvantaged regions. By equipping UAVs with small cells, coverage can be improved in areas where network operators are not prone to invest due to low Return on Investment. If there is a requirement from users in rural scenarios to achieve higher throughput (for instance, users seeking IoT services with stringent Quality-of-Service requirements), deploying multiple UAVs in the same area could be an effective strategy. However, this approach would also result in increased energy consumption. This paper addresses the challenge of maximizing the throughput offered in rural areas for users accessing microservice-based IoT applications, while also minimizing the energy consumption of UAV swarms. To achieve this, an optimal solution is proposed through a Mixed Integer Linear Programming (MILP) model, which is evaluated within realistic environments. Since this placement problem is complex due to its NP hard nature, in order to obtain solutions for large scenarios in tractable times, we also present a genetic algorithm (GA) that obtains results close to those reported by the MILP with a remarkable reduction in the computation time. Specifically, the optimality gap of the proposed GA-based solution is on average 2.32%, with a reduction of 89.92% in the computation time.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101880"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077989","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}

引用次数: 0

A spatio-temporal deep learning-based decision support system for energy awareness in IoT-based smart buildings 基于物联网的智能建筑能源意识时空深度学习决策支持系统

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-29 DOI: 10.1016/j.iot.2025.101856

Berna Cengiz, Resul Das

The increasing demand for energy and rising expectations for user comfort necessitate the more accurate and efficient management of climate control systems in smart buildings. A crucial step in this process is reliably predicting indoor temperature. In this study, multivariate time series data, including environmental parameters such as temperature, Relative Humidity (RH), light, and Heating, Ventilating and Air Conditioning (HVAC) consumption, were used to evaluate the performance of various deep learning models. Hybrid approaches integrating Recurrent Neural Networks (RNN) architectures, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, with Graph Convolutional Networks (GCN)(GCN-RNN, GCN-LSTM, GCN-GRU) were systematically compared. Furthermore, the Transformer architecture and the Extreme Gradient Boosting (XGBoost) algorithm were included in the comparison as a baseline reference. The results show that the GCN-GRU model achieved superior accuracy compared to other models in the analyzed regions and throughout the test period, reaching an R² score of 0.9976 with low error rates and providing consistent accuracy. Beyond model performance, a user-friendly interface has been developed that enables the selection of alternative models, interactive visualization of prediction results, examination of the impact of the current control strategy on energy efficiency, and dynamic integration of new algorithms, thanks to a modular software architecture. These findings emphasize the importance of jointly processing temporal and spatial patterns and provide a practical foundation for decision support systems aimed at enhancing energy awareness and operational sustainability in IoT-enabled smart buildings.

日益增长的能源需求和对用户舒适度的期望使得智能建筑中气候控制系统的管理更加准确和有效。这一过程的关键一步是可靠地预测室内温度。在这项研究中，多变量时间序列数据，包括环境参数，如温度，相对湿度（RH），光，采暖，通风和空调（HVAC）消耗，用于评估各种深度学习模型的性能。将包括长短期记忆（LSTM）和门控循环单元（GRU）模型在内的循环神经网络（RNN）架构与图卷积网络（GCN）（GCN-RNN、GCN-LSTM、GCN-GRU）相结合的混合方法进行了系统比较。此外，变压器架构和极限梯度增强（XGBoost）算法被纳入比较作为基准参考。结果表明，GCN-GRU模型在分析区域和整个测试期间的精度优于其他模型，R2得分为0.9976，错误率低，准确度一致。除了模型性能，还开发了一个用户友好的界面，可以选择替代模型，预测结果的交互式可视化，检查当前控制策略对能源效率的影响，以及新算法的动态集成，这要归功于模块化的软件架构。这些发现强调了联合处理时空模式的重要性，并为决策支持系统提供了实践基础，旨在提高物联网智能建筑的能源意识和运营可持续性。

{"title":"A spatio-temporal deep learning-based decision support system for energy awareness in IoT-based smart buildings","authors":"Berna Cengiz, Resul Das","doi":"10.1016/j.iot.2025.101856","DOIUrl":"10.1016/j.iot.2025.101856","url":null,"abstract":"<div><div>The increasing demand for energy and rising expectations for user comfort necessitate the more accurate and efficient management of climate control systems in smart buildings. A crucial step in this process is reliably predicting indoor temperature. In this study, multivariate time series data, including environmental parameters such as temperature, Relative Humidity (RH), light, and Heating, Ventilating and Air Conditioning (HVAC) consumption, were used to evaluate the performance of various deep learning models. Hybrid approaches integrating Recurrent Neural Networks (RNN) architectures, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, with Graph Convolutional Networks (GCN)(GCN-RNN, GCN-LSTM, GCN-GRU) were systematically compared. Furthermore, the Transformer architecture and the Extreme Gradient Boosting (XGBoost) algorithm were included in the comparison as a baseline reference. The results show that the GCN-GRU model achieved superior accuracy compared to other models in the analyzed regions and throughout the test period, reaching an <em>R</em><sup>2</sup> score of 0.9976 with low error rates and providing consistent accuracy. Beyond model performance, a user-friendly interface has been developed that enables the selection of alternative models, interactive visualization of prediction results, examination of the impact of the current control strategy on energy efficiency, and dynamic integration of new algorithms, thanks to a modular software architecture. These findings emphasize the importance of jointly processing temporal and spatial patterns and provide a practical foundation for decision support systems aimed at enhancing energy awareness and operational sustainability in IoT-enabled smart buildings.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101856"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926744","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}

引用次数: 0

Internet of Things Technologies for Occupational Health and Safety: A Review 面向职业健康与安全的物联网技术综述

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-02-03 DOI: 10.1016/j.iot.2026.101886

Sotiris Zikas , Theodor Panagiotakopoulos , Yiannis Kiouvrekis

The Internet of Things (IoT) has significantly enhanced Occupational Health and Safety (OHS) by enabling real-time monitoring of workplace environments and employee well-being through smart sensors and connected devices. IoT systems help identify hazards, improve response times, and ensure compliance with safety regulations. Despite these advancements, the literature highlights a gap in investigating the technologies and algorithms specifically tailored for OHS applications. This paper presents a comprehensive review of IoT OHS technologies, structured around a four-tier IoT OHS system architecture, which serves as a framework for analyzing existing studies in the field. Our findings indicate that sensors from the perception tier are the most widely utilized component across IoT OHS implementations, underscoring their critical role in hazard detection and safety monitoring. In contrast, IoT cloud technologies remain underutilized, suggesting potential barriers to widespread adoption. From a machine learning (ML) perspective, supervised learning and classification models emerge as the dominant approaches, with classification models being employed in studies that incorporate all four sensor categories. In contrast, unsupervised learning models are infrequently applied in IoT OHS systems, indicating a preference for structured, labeled data analysis. Notably, accident prevention applications, particularly those addressing collisions and falls from height, leverage the full spectrum of ML approaches and sensor technologies, making them the most comprehensive category within the domain. By categorizing sensors, controllers, gateways, communication technologies, and cloud platforms, alongside analyzing ML methodologies, this paper provides valuable insights into the current landscape of IoT OHS systems and highlights key trends, challenges, and opportunities for future research.

物联网（IoT）通过智能传感器和连接设备实现对工作场所环境和员工健康状况的实时监控，极大地增强了职业健康与安全（OHS）。物联网系统有助于识别危险，缩短响应时间，并确保遵守安全法规。尽管取得了这些进步，但文献强调了在调查专门为OHS应用量身定制的技术和算法方面的差距。本文围绕四层物联网OHS系统架构对物联网OHS技术进行了全面回顾，并作为分析该领域现有研究的框架。我们的研究结果表明，感知层的传感器是物联网OHS实施中应用最广泛的组件，强调了它们在危害检测和安全监测中的关键作用。相比之下，物联网云技术仍未得到充分利用，这表明广泛采用存在潜在障碍。从机器学习（ML）的角度来看，监督学习和分类模型是主要的方法，分类模型被用于包含所有四种传感器类别的研究。相比之下，无监督学习模型很少应用于物联网OHS系统，这表明人们更倾向于结构化、标签化的数据分析。值得注意的是，事故预防应用，特别是那些解决碰撞和高空坠落的应用，充分利用了机器学习方法和传感器技术的全部范围，使其成为该领域最全面的类别。通过对传感器、控制器、网关、通信技术和云平台进行分类，并分析机器学习方法，本文提供了对物联网OHS系统当前格局的宝贵见解，并强调了未来研究的关键趋势、挑战和机遇。

{"title":"Internet of Things Technologies for Occupational Health and Safety: A Review","authors":"Sotiris Zikas , Theodor Panagiotakopoulos , Yiannis Kiouvrekis","doi":"10.1016/j.iot.2026.101886","DOIUrl":"10.1016/j.iot.2026.101886","url":null,"abstract":"<div><div>The Internet of Things (IoT) has significantly enhanced Occupational Health and Safety (OHS) by enabling real-time monitoring of workplace environments and employee well-being through smart sensors and connected devices. IoT systems help identify hazards, improve response times, and ensure compliance with safety regulations. Despite these advancements, the literature highlights a gap in investigating the technologies and algorithms specifically tailored for OHS applications. This paper presents a comprehensive review of IoT OHS technologies, structured around a four-tier IoT OHS system architecture, which serves as a framework for analyzing existing studies in the field. Our findings indicate that sensors from the perception tier are the most widely utilized component across IoT OHS implementations, underscoring their critical role in hazard detection and safety monitoring. In contrast, IoT cloud technologies remain underutilized, suggesting potential barriers to widespread adoption. From a machine learning (ML) perspective, supervised learning and classification models emerge as the dominant approaches, with classification models being employed in studies that incorporate all four sensor categories. In contrast, unsupervised learning models are infrequently applied in IoT OHS systems, indicating a preference for structured, labeled data analysis. Notably, accident prevention applications, particularly those addressing collisions and falls from height, leverage the full spectrum of ML approaches and sensor technologies, making them the most comprehensive category within the domain. By categorizing sensors, controllers, gateways, communication technologies, and cloud platforms, alongside analyzing ML methodologies, this paper provides valuable insights into the current landscape of IoT OHS systems and highlights key trends, challenges, and opportunities for future research.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101886"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173167","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}

引用次数: 0

An e-health environment conceived with the support of a self-adaptive IoT architecture 在自适应物联网架构的支持下构思的电子医疗环境

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-03 DOI: 10.1016/j.iot.2025.101844

Mateus G. do Nascimento, José Maria N. David, Mario A.R. Dantas, Regina Braga, Victor Ströele

IoT has gradually exposed society to intelligent environments. Software developed for these environments requires efficient data processing, low response time, and proper functioning of sensors, devices, and systems. To meet these software requirements, we can leverage edge, fog, and cloud computing. However, the use of these computational resources presents challenges for software engineering, such as determining which architectures to employ for developing software in intelligent environments. Considering these challenges, this work addresses the research question: How can a self-adaptive architecture support automated computational resource allocation in e-health environments? To answer this research question, we propose a self-adaptive IoT architecture that uses artificial intelligence to manage computational resource usage in intelligent environments, enabling the management of physical spaces and ensuring the correct functioning of applications. A case study was conducted in an e-health environment to support our arguments. The Design Science Research methodology was used to develop the research, and its execution cycles in a real e-health corporate environment, through a case study, enabled the incremental construction of the architecture. The results demonstrate that the proposed architecture enhances the efficiency of allocating computational resources - encompassing edge, fog, and cloud computing - while ensuring the functioning of applications and supporting the management of the physical environment using artificial intelligence. As contributions, the study shows: (i) the self-adaptive architecture construction phases; (ii) how architecture adapts to the demands of the IoT intelligent environment; (iii) how artificial intelligence can support the allocation of computational resources.

物联网逐渐将社会暴露在智能环境中。为这些环境开发的软件需要高效的数据处理、较低的响应时间以及传感器、设备和系统的适当功能。为了满足这些软件需求，我们可以利用边缘计算、雾计算和云计算。然而，这些计算资源的使用对软件工程提出了挑战，例如确定在智能环境中开发软件采用哪种体系结构。考虑到这些挑战，本工作解决了研究问题：自适应架构如何在电子卫生环境中支持自动计算资源分配？为了回答这个研究问题，我们提出了一种自适应物联网架构，该架构使用人工智能来管理智能环境中的计算资源使用，实现物理空间的管理并确保应用程序的正确运行。为了支持我们的论点，我们在电子医疗环境中进行了一个案例研究。设计科学研究方法用于开展研究，其在真实的电子医疗企业环境中的执行周期，通过案例研究，使体系结构的增量构建成为可能。结果表明，所提出的架构提高了分配计算资源的效率——包括边缘计算、雾计算和云计算——同时确保应用程序的功能并支持使用人工智能管理物理环境。作为贡献，研究表明：(i)自适应建筑的构建阶段；（ii）架构如何适应物联网智能环境的需求；（iii）人工智能如何支持计算资源的分配。

{"title":"An e-health environment conceived with the support of a self-adaptive IoT architecture","authors":"Mateus G. do Nascimento, José Maria N. David, Mario A.R. Dantas, Regina Braga, Victor Ströele","doi":"10.1016/j.iot.2025.101844","DOIUrl":"10.1016/j.iot.2025.101844","url":null,"abstract":"<div><div>IoT has gradually exposed society to intelligent environments. Software developed for these environments requires efficient data processing, low response time, and proper functioning of sensors, devices, and systems. To meet these software requirements, we can leverage edge, fog, and cloud computing. However, the use of these computational resources presents challenges for software engineering, such as determining which architectures to employ for developing software in intelligent environments. Considering these challenges, this work addresses the research question: How can a self-adaptive architecture support automated computational resource allocation in e-health environments? To answer this research question, we propose a self-adaptive IoT architecture that uses artificial intelligence to manage computational resource usage in intelligent environments, enabling the management of physical spaces and ensuring the correct functioning of applications. A case study was conducted in an e-health environment to support our arguments. The Design Science Research methodology was used to develop the research, and its execution cycles in a real e-health corporate environment, through a case study, enabled the incremental construction of the architecture. The results demonstrate that the proposed architecture enhances the efficiency of allocating computational resources - encompassing edge, fog, and cloud computing - while ensuring the functioning of applications and supporting the management of the physical environment using artificial intelligence. As contributions, the study shows: (i) the self-adaptive architecture construction phases; (ii) how architecture adapts to the demands of the IoT intelligent environment; (iii) how artificial intelligence can support the allocation of computational resources.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101844"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791859","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}

引用次数: 0

Machine learning on the edge for sustainable IoT networks: A systematic literature review 可持续物联网网络边缘的机器学习：系统文献综述

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-12 DOI: 10.1016/j.iot.2025.101846

Luisa Schuhmacher , Jimmy Fernandez Landivar , Ihsane Gryech , Hazem Sallouha , Michele Rossi , Sofie Pollin

The Internet of Things (IoT) has become integral to modern technology, enhancing daily life and industrial processes through seamless connectivity. However, the rapid expansion of IoT systems presents significant sustainability challenges, such as high energy consumption and inefficient resource management. Addressing these issues is critical for the long-term viability of IoT networks. Machine learning (ML), with its proven success across various domains, offers promising solutions for optimizing IoT operations. ML algorithms can learn directly from raw data, uncovering hidden patterns and optimizing processes in dynamic environments. Executing ML at the edge of IoT networks can further enhance sustainability by reducing bandwidth usage, enabling real-time decision-making, and improving data privacy. Additionally, testing ML models on actual hardware is essential to ensure satisfactory performance under real-world conditions, as it captures the complexities and constraints of real-world IoT deployments. Combining ML at the edge and actual hardware testing, therefore, increases the reliability of ML models to effectively improve the sustainability of IoT systems. The present systematic literature review explores how ML can be utilized to enhance the sustainability of IoT networks, examining current methodologies, benefits, challenges, and future opportunities. Through our analysis, we aim to provide insights that will drive future innovations in making IoT networks more sustainable.

物联网（IoT）已成为现代技术不可或缺的一部分，通过无缝连接改善了日常生活和工业流程。然而，物联网系统的快速扩展带来了重大的可持续性挑战，例如高能耗和低效的资源管理。解决这些问题对于物联网网络的长期可行性至关重要。机器学习（ML）在各个领域都取得了成功，为优化物联网运营提供了有前途的解决方案。机器学习算法可以直接从原始数据中学习，发现隐藏的模式，并在动态环境中优化过程。在物联网网络边缘执行机器学习可以通过减少带宽使用、实现实时决策和改善数据隐私来进一步增强可持续性。此外，在实际硬件上测试ML模型对于确保在现实条件下的令人满意的性能至关重要，因为它捕捉了现实世界物联网部署的复杂性和局限性。因此，将边缘机器学习与实际硬件测试相结合，可以提高机器学习模型的可靠性，从而有效提高物联网系统的可持续性。本系统的文献综述探讨了如何利用机器学习来增强物联网网络的可持续性，研究了当前的方法、好处、挑战和未来的机会。通过我们的分析，我们的目标是提供见解，推动未来的创新，使物联网网络更具可持续性。

{"title":"Machine learning on the edge for sustainable IoT networks: A systematic literature review","authors":"Luisa Schuhmacher , Jimmy Fernandez Landivar , Ihsane Gryech , Hazem Sallouha , Michele Rossi , Sofie Pollin","doi":"10.1016/j.iot.2025.101846","DOIUrl":"10.1016/j.iot.2025.101846","url":null,"abstract":"<div><div>The Internet of Things (IoT) has become integral to modern technology, enhancing daily life and industrial processes through seamless connectivity. However, the rapid expansion of IoT systems presents significant sustainability challenges, such as high energy consumption and inefficient resource management. Addressing these issues is critical for the long-term viability of IoT networks. Machine learning (ML), with its proven success across various domains, offers promising solutions for optimizing IoT operations. ML algorithms can learn directly from raw data, uncovering hidden patterns and optimizing processes in dynamic environments. Executing ML at the edge of IoT networks can further enhance sustainability by reducing bandwidth usage, enabling real-time decision-making, and improving data privacy. Additionally, testing ML models on actual hardware is essential to ensure satisfactory performance under real-world conditions, as it captures the complexities and constraints of real-world IoT deployments. Combining ML at the edge and actual hardware testing, therefore, increases the reliability of ML models to effectively improve the sustainability of IoT systems. The present systematic literature review explores how ML can be utilized to enhance the sustainability of IoT networks, examining current methodologies, benefits, challenges, and future opportunities. Through our analysis, we aim to provide insights that will drive future innovations in making IoT networks more sustainable.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101846"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791861","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}

引用次数: 0

A game-theoretic approach to sustainable smart manufacturing using IoT under policy incentives: a case study of Iran and South Korea 政策激励下利用物联网实现可持续智能制造的博弈论方法：以伊朗和韩国为例

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-26 DOI: 10.1016/j.iot.2025.101860

Mahnaz Naghsh-Nilchi , Morteza Rasti-Barzoki , Mohammad-Bagher Jamali , Jörn Altmann , Bernhard Egger

This study presents a mathematical model to analyze the competition between smart and traditional home appliance manufacturers in Iran and South Korea using a game theory approach. The smart manufacturer utilizes IoT-enabled products and a Sensing-as-a-Service (SaaS) ecosystem to collect and analyze real-time operational data, enabling predictive maintenance, energy optimization, and intelligent product design. This data-driven approach extends the product life cycle, reduces operating costs, and reduces material waste and carbon emissions. In contrast, the traditional manufacturer relies on conventional R&D and after-sales feedback, which limits responsiveness and efficiency. The proposed model is the first to highlight the strategic value of data analytics in the SaaS ecosystem in shaping competitive advantage, sustainability, and market performance by considering customer behavior and government incentives. The results show that providing targeted incentives for data sharing significantly increases demand, profitability, and environmental benefits, especially in mature digital markets. Furthermore, the study shows that supporting context-specific policies enhances the effectiveness of smart manufacturing strategies. Overall, this research provides actionable insights for policymakers, manufacturers, and IoT stakeholders seeking to foster sustainable, competitive, and digital industrial systems in emerging and advanced economies.

本研究提出一个数学模型，运用博弈论的方法分析伊朗和韩国的智能家电制造商和传统家电制造商之间的竞争。智能制造商利用物联网产品和感知即服务（SaaS）生态系统收集和分析实时运营数据，实现预测性维护、能源优化和智能产品设计。这种数据驱动的方法延长了产品生命周期，降低了运营成本，减少了材料浪费和碳排放。相比之下，传统制造商依赖于传统的研发和售后反馈，这限制了响应能力和效率。该模型首次强调了数据分析在SaaS生态系统中的战略价值，即通过考虑客户行为和政府激励，塑造竞争优势、可持续性和市场表现。研究结果表明，为数据共享提供有针对性的激励措施可以显著提高需求、盈利能力和环境效益，尤其是在成熟的数字市场。此外，研究表明，支持特定情境的政策可以提高智能制造战略的有效性。总体而言，本研究为决策者、制造商和物联网利益相关者提供了可操作的见解，以寻求在新兴和发达经济体中培育可持续、有竞争力的数字工业系统。

{"title":"A game-theoretic approach to sustainable smart manufacturing using IoT under policy incentives: a case study of Iran and South Korea","authors":"Mahnaz Naghsh-Nilchi , Morteza Rasti-Barzoki , Mohammad-Bagher Jamali , Jörn Altmann , Bernhard Egger","doi":"10.1016/j.iot.2025.101860","DOIUrl":"10.1016/j.iot.2025.101860","url":null,"abstract":"<div><div>This study presents a mathematical model to analyze the competition between smart and traditional home appliance manufacturers in Iran and South Korea using a game theory approach. The smart manufacturer utilizes IoT-enabled products and a Sensing-as-a-Service (SaaS) ecosystem to collect and analyze real-time operational data, enabling predictive maintenance, energy optimization, and intelligent product design. This data-driven approach extends the product life cycle, reduces operating costs, and reduces material waste and carbon emissions. In contrast, the traditional manufacturer relies on conventional R&D and after-sales feedback, which limits responsiveness and efficiency. The proposed model is the first to highlight the strategic value of data analytics in the SaaS ecosystem in shaping competitive advantage, sustainability, and market performance by considering customer behavior and government incentives. The results show that providing targeted incentives for data sharing significantly increases demand, profitability, and environmental benefits, especially in mature digital markets. Furthermore, the study shows that supporting context-specific policies enhances the effectiveness of smart manufacturing strategies. Overall, this research provides actionable insights for policymakers, manufacturers, and IoT stakeholders seeking to foster sustainable, competitive, and digital industrial systems in emerging and advanced economies.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101860"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885163","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}

引用次数: 0

AI for IoMT security: a comprehensive survey of intrusion detection and system architectures 人工智能物联网安全：入侵检测和系统架构的全面调查

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-06 DOI: 10.1016/j.iot.2025.101869

Mohammed Yacoubi , Omar Moussaoui , Cyril Drocourt

Recent advances in the Internet of Medical Things (IoMT) have significantly improved data processing and patient care within Smart Healthcare systems. However, these developments have also expanded the surface of potential cyber threats targeting sensitive medical infrastructures. To address these challenges, a variety of security approaches both traditional and Artificial Intelligence (AI)-based have been proposed to strengthen the resilience of IoMT environments. In particular, Machine Learning (ML) and Deep Learning (DL) techniques have demonstrated strong capabilities in detecting and mitigating abnormal behaviors and malicious activities. This paper provides a comprehensive survey of recent AI-driven methods applied to IoMT security, with a particular focus on intrusion detection systems (IDS), the availability and characteristics of public datasets, and architectural considerations for deploying security solutions across Cloud, Fog, and Edge computing layers. The paper also discusses legal and ethical concerns related to data protection in healthcare contexts. Finally, the study outlines open challenges and future research directions for developing robust, adaptive, and trustworthy security frameworks in the IoMT ecosystem.

医疗物联网（IoMT）的最新进展显著改善了智能医疗保健系统中的数据处理和患者护理。然而，这些发展也扩大了针对敏感医疗基础设施的潜在网络威胁的范围。为了应对这些挑战，人们提出了各种传统和基于人工智能（AI）的安全方法，以加强物联网环境的弹性。特别是机器学习（ML）和深度学习（DL）技术在检测和减轻异常行为和恶意活动方面表现出了强大的能力。本文对最近应用于IoMT安全的人工智能驱动方法进行了全面调查，特别关注入侵检测系统（IDS）、公共数据集的可用性和特征，以及跨云、雾和边缘计算层部署安全解决方案的架构考虑。本文还讨论了与医疗保健环境中的数据保护相关的法律和伦理问题。最后，该研究概述了在IoMT生态系统中开发健壮、自适应和可信赖的安全框架的开放挑战和未来研究方向。

{"title":"AI for IoMT security: a comprehensive survey of intrusion detection and system architectures","authors":"Mohammed Yacoubi , Omar Moussaoui , Cyril Drocourt","doi":"10.1016/j.iot.2025.101869","DOIUrl":"10.1016/j.iot.2025.101869","url":null,"abstract":"<div><div>Recent advances in the Internet of Medical Things (IoMT) have significantly improved data processing and patient care within Smart Healthcare systems. However, these developments have also expanded the surface of potential cyber threats targeting sensitive medical infrastructures. To address these challenges, a variety of security approaches both traditional and Artificial Intelligence (AI)-based have been proposed to strengthen the resilience of IoMT environments. In particular, Machine Learning (ML) and Deep Learning (DL) techniques have demonstrated strong capabilities in detecting and mitigating abnormal behaviors and malicious activities. This paper provides a comprehensive survey of recent AI-driven methods applied to IoMT security, with a particular focus on intrusion detection systems (IDS), the availability and characteristics of public datasets, and architectural considerations for deploying security solutions across Cloud, Fog, and Edge computing layers. The paper also discusses legal and ethical concerns related to data protection in healthcare contexts. Finally, the study outlines open challenges and future research directions for developing robust, adaptive, and trustworthy security frameworks in the IoMT ecosystem.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101869"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978119","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}

引用次数: 0

WiAR : Wi-Fi-based human activity recognition using time-frequency analysis and lightweight deep learning for smart environments WiAR：基于wi - fi的人类活动识别，用于智能环境的时频分析和轻量级深度学习

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-28 DOI: 10.1016/j.iot.2026.101881

Vamsi Krishna Puduru , Rakesh Reddy Yakkati , Sreenivasa Reddy Yeduri , Sagar Koorapati , Linga Reddy Cenkeramaddi

Recognizing human activities in smart environments has significant usage in home automation, security, healthcare monitoring, etc. This paper proposes WiAR, which is a Wi-Fi-based human activity recognition method using Continuous Wavelet Transform (CWT) and lightweight Convolutional Neural Networks (CNNs). The proposed approach is evaluated on the IEEE 802.11ax Channel State Information (CSI) dataset. First, WiAR utilizes the CWT to generate the spectrogram images from the CSI extracted from Wi-Fi signals for different activities: walking, running, staying in place, and empty space. Then, these spectrogram images are processed with a CNN to classify these activities efficiently. Experimental results show that the proposed WiAR achieves an accuracy of approximately 91.1% when compared to various pre-trained models such as DenseNet, EfficientNet, MobileNet, ResNet, and VGGNet. Finally, the proposed CNN model is deployed on various edge computing devices, including Raspberry Pi 5, to validate its real-time implementation in terms of inference time.

识别智能环境中的人类活动在家庭自动化、安全、医疗监控等方面具有重要用途。WiAR是一种基于wi - fi的基于连续小波变换（CWT）和轻量级卷积神经网络（cnn）的人体活动识别方法。该方法在IEEE 802.11ax信道状态信息（CSI）数据集上进行了评估。首先，WiAR利用CWT从Wi-Fi信号中提取的CSI中生成不同活动的频谱图图像：步行、跑步、原地不动和空旷。然后，对这些光谱图图像进行CNN处理，有效地对这些活动进行分类。实验结果表明，与DenseNet、EfficientNet、MobileNet、ResNet和VGGNet等多种预训练模型相比，本文提出的WiAR模型的准确率约为91.1%。最后，将提出的CNN模型部署在各种边缘计算设备上，包括Raspberry Pi 5，以验证其在推理时间方面的实时性。

{"title":"WiAR : Wi-Fi-based human activity recognition using time-frequency analysis and lightweight deep learning for smart environments","authors":"Vamsi Krishna Puduru , Rakesh Reddy Yakkati , Sreenivasa Reddy Yeduri , Sagar Koorapati , Linga Reddy Cenkeramaddi","doi":"10.1016/j.iot.2026.101881","DOIUrl":"10.1016/j.iot.2026.101881","url":null,"abstract":"<div><div>Recognizing human activities in smart environments has significant usage in home automation, security, healthcare monitoring, etc. This paper proposes WiAR, which is a Wi-Fi-based human activity recognition method using Continuous Wavelet Transform (CWT) and lightweight Convolutional Neural Networks (CNNs). The proposed approach is evaluated on the IEEE 802.11ax Channel State Information (CSI) dataset. First, WiAR utilizes the CWT to generate the spectrogram images from the CSI extracted from Wi-Fi signals for different activities: walking, running, staying in place, and empty space. Then, these spectrogram images are processed with a CNN to classify these activities efficiently. Experimental results show that the proposed WiAR achieves an accuracy of approximately 91.1% when compared to various pre-trained models such as DenseNet, EfficientNet, MobileNet, ResNet, and VGGNet. Finally, the proposed CNN model is deployed on various edge computing devices, including Raspberry Pi 5, to validate its real-time implementation in terms of inference time.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101881"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077993","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}

引用次数: 0

μTEE: Certification-ready RISC-V platform for secure IIoT lifecycle management μTEE：用于安全工业物联网生命周期管理的认证就绪RISC-V平台

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-02-02 DOI: 10.1016/j.iot.2026.101885

Alessandro Cilardo , Jesús García-Rodríguez , Jose Manuel Merlos Espín , Roberto Nardone

The digital transformation of industrial environments increasingly relies on resource-constrained Industrial Internet of Things (IIoT) devices, which must operate securely despite limited computational capabilities and hostile deployment conditions. Ensuring their trustworthiness is essential for complying with emerging regulations such as the EU Cyber-Resilience Act and for achieving certification under standards such as IEC 62443. This paper presents μTEE, a lightweight Trusted Execution Environment for RISC-V microcontroller-class platforms, explicitly designed to support certification-ready lifecycle security in ultra-lightweight IIoT nodes. μTEE combines hardware-enforced isolation, a secure root of trust, and enclave-based modularity for trusted system services, with an efficient symmetric-cryptography framework tailored to constrained devices. Beyond the architectural contribution, we perform a detailed IEC 62443 Security Level 3 compliance analysis, providing one of the first systematic demonstrations of how a constrained IIoT platform can be evaluated against this standard. The full compliance checklist is released as supplementary material, offering a practical methodology for applying IEC 62443 in novel IIoT contexts. We further illustrate μTEE’s integration into lifecycle management flows and demonstrate its deployment in a PLC-based smart metering scenario. A prototypical FPGA implementation on an AMD-Xilinx Artix-7 platform shows modest area and performance costs, with limited overhead on application throughput. Comparative evaluation highlights μTEE’s advantages over software-only TEEs, Arm TrustZone-M, and baseline RISC-V PMP approaches. The results confirm that μTEE delivers a certifiable, open-hardware trust anchor for IIoT, and that it serves as a replicable case study of IEC 62443 compliance evaluation, advancing the secure deployment of Industry 4.0 infrastructures.

工业环境的数字化转型越来越依赖于资源受限的工业物联网（IIoT）设备，这些设备必须在有限的计算能力和恶劣的部署条件下安全运行。确保他们的可信度对于遵守欧盟网络弹性法案等新兴法规以及实现IEC 62443等标准的认证至关重要。μTEE是一种用于RISC-V微控制器级平台的轻量级可信执行环境，旨在支持超轻量IIoT节点的认证就绪生命周期安全。μTEE结合了硬件强制隔离、安全的信任根和基于enclave的受信任系统服务模块化，以及针对受限设备量身定制的高效对称加密框架。除了架构贡献之外，我们还执行了详细的IEC 62443安全级别3合规性分析，提供了如何根据该标准评估受限IIoT平台的首批系统演示之一。完整的符合性检查表作为补充材料发布，为在新的工业物联网环境中应用IEC 62443提供了实用的方法。我们进一步说明μTEE集成到生命周期管理流程中，并演示其在基于plc的智能计量场景中的部署。在AMD-Xilinx Artix-7平台上的FPGA原型实现显示出适度的面积和性能成本，以及有限的应用吞吐量开销。对比评估突出了μTEE相对于纯软件tee、Arm TrustZone-M和基准RISC-V PMP方法的优势。结果证实，μTEE为工业物联网提供了可认证的开放硬件信任锚，并且它可以作为IEC 62443合规性评估的可复制案例研究，推进工业4.0基础设施的安全部署。

{"title":"μTEE: Certification-ready RISC-V platform for secure IIoT lifecycle management","authors":"Alessandro Cilardo , Jesús García-Rodríguez , Jose Manuel Merlos Espín , Roberto Nardone","doi":"10.1016/j.iot.2026.101885","DOIUrl":"10.1016/j.iot.2026.101885","url":null,"abstract":"<div><div>The digital transformation of industrial environments increasingly relies on resource-constrained Industrial Internet of Things (IIoT) devices, which must operate securely despite limited computational capabilities and hostile deployment conditions. Ensuring their trustworthiness is essential for complying with emerging regulations such as the EU Cyber-Resilience Act and for achieving certification under standards such as IEC 62443. This paper presents <em>μ</em>TEE, a lightweight Trusted Execution Environment for RISC-V microcontroller-class platforms, explicitly designed to support certification-ready lifecycle security in ultra-lightweight IIoT nodes. <em>μ</em>TEE combines hardware-enforced isolation, a secure root of trust, and enclave-based modularity for trusted system services, with an efficient symmetric-cryptography framework tailored to constrained devices. Beyond the architectural contribution, we perform a detailed IEC 62443 Security Level 3 compliance analysis, providing one of the first systematic demonstrations of how a constrained IIoT platform can be evaluated against this standard. The full compliance checklist is released as supplementary material, offering a practical methodology for applying IEC 62443 in novel IIoT contexts. We further illustrate <em>μ</em>TEE’s integration into lifecycle management flows and demonstrate its deployment in a PLC-based smart metering scenario. A prototypical FPGA implementation on an AMD-Xilinx Artix-7 platform shows modest area and performance costs, with limited overhead on application throughput. Comparative evaluation highlights <em>μ</em>TEE’s advantages over software-only TEEs, Arm TrustZone-M, and baseline RISC-V PMP approaches. The results confirm that <em>μ</em>TEE delivers a certifiable, open-hardware trust anchor for IIoT, and that it serves as a replicable case study of IEC 62443 compliance evaluation, advancing the secure deployment of Industry 4.0 infrastructures.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101885"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173269","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}

引用次数: 0

TinyHAR-UQ: Battery-aware, uncertainty-controlled tinyML for wearable activity recognition on IoT edge devices TinyHAR-UQ：电池感知、不确定性控制的tinyML，用于物联网边缘设备上的可穿戴活动识别

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1016/j.iot.2026.101889

Ismail Lamaakal , Chaymae Yahyati , Yassine Maleh , Khalid El Makkaoui , Ibrahim Ouahbi

Tiny, battery-powered wearables increasingly run human activity recognition (HAR) models, yet they rarely know when to trust predictions or when to stop computing to save energy. We address this gap with TinyHAR-UQ, a microcontroller-ready HAR pipeline that turns int8 networks into risk-aware, energy-aware predictors. Our contributions are threefold. First, we realize on-device conformal prediction sets for HAR by combining an int8 temporal backbone, early exits, Dirichlet (evidential) heads, and a streaming integer-only conformal layer that enforces user-chosen miscoverage levels. Second, we design a budget-aware controller that, at test time, decides whether to exit early, continue, or abstain based on prediction-set size and resource constraints. Third, we propose micro-temperature personalization, a zero-cost calibration scheme (two scalars per exit folded into quantized scales/biases) that recovers calibration lost to quantization. Deployed on Cortex-M4F and ESP32-S3 devices and evaluated on four HAR benchmarks, TinyHAR-UQ achieves nominal 90-95% coverage with near-singleton sets while cutting median latency and energy by up to 50% and 20-30% versus a matched single-exit baseline, enabling reliable, efficient HAR on off-the-shelf IoT edge platforms.

微型、电池供电的可穿戴设备越来越多地运行人类活动识别（HAR）模型，但它们很少知道何时该相信预测，或者何时该停止计算以节省能源。我们通过TinyHAR-UQ解决了这一差距，这是一种微控制器就绪的HAR管道，可将网络转变为具有风险意识和能量意识的预测器。我们的贡献是三重的。首先，我们通过结合int8时间骨干、早期出口、Dirichlet（证据）头和强制用户选择误覆盖级别的流整型保形层，实现了HAR的设备上保形预测集。其次，我们设计了一个预算感知控制器，在测试时，根据预测集的大小和资源约束来决定是否提前退出、继续还是放弃。第三，我们提出了微温度个性化，这是一种零成本校准方案（每个出口两个标量折叠成量化尺度/偏差），可以恢复量化损失的校准。TinyHAR-UQ部署在Cortex-M4F和ESP32-S3设备上，并在四个HAR基准上进行了评估，在接近单一集的情况下实现了90-95%的标称覆盖率，同时与匹配的单出口基线相比，中位延迟和能量分别减少了50%和20-30%，从而在现有的物联网边缘平台上实现了可靠、高效的HAR。

{"title":"TinyHAR-UQ: Battery-aware, uncertainty-controlled tinyML for wearable activity recognition on IoT edge devices","authors":"Ismail Lamaakal , Chaymae Yahyati , Yassine Maleh , Khalid El Makkaoui , Ibrahim Ouahbi","doi":"10.1016/j.iot.2026.101889","DOIUrl":"10.1016/j.iot.2026.101889","url":null,"abstract":"<div><div>Tiny, battery-powered wearables increasingly run human activity recognition (HAR) models, yet they rarely know when to trust predictions or when to stop computing to save energy. We address this gap with <em>TinyHAR-UQ</em>, a microcontroller-ready HAR pipeline that turns int8 networks into risk-aware, energy-aware predictors. Our contributions are threefold. First, we realize on-device conformal prediction sets for HAR by combining an int8 temporal backbone, early exits, Dirichlet (evidential) heads, and a streaming integer-only conformal layer that enforces user-chosen miscoverage levels. Second, we design a budget-aware controller that, at test time, decides whether to exit early, continue, or abstain based on prediction-set size and resource constraints. Third, we propose micro-temperature personalization, a zero-cost calibration scheme (two scalars per exit folded into quantized scales/biases) that recovers calibration lost to quantization. Deployed on Cortex-M4F and ESP32-S3 devices and evaluated on four HAR benchmarks, <em>TinyHAR-UQ</em> achieves nominal 90-95% coverage with near-singleton sets while cutting median latency and energy by up to 50% and 20-30% versus a matched single-exit baseline, enabling reliable, efficient HAR on off-the-shelf IoT edge platforms.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101889"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173271","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}

引用次数: 0