Internet of Things最新文献_第6页

Digital twin-driven semantic offloading for LEO-MEC-enabled remote IoT networks 支持leo - mec的远程物联网网络的数字双驱动语义卸载

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

Internet of Things

Pub Date : 2025-11-21 DOI: 10.1016/j.iot.2025.101831

Ayalneh Bitew Wondmagegn, Dongwook Won, Donghyun Lee, Jaemin Kim, Juyoung Kim, Sungrae Cho

Efficient task offloading to low-Earth orbit (LEO) satellite-assisted mobile edge computing (MEC) servers is vital for addressing the computational delay and energy constraints of remote Internet of Things (IoT) devices. However, inherent challenges in LEO satellite networks–including dynamic topology, intermittent connectivity, and bandwidth scarcity undermine the performance of conventional offloading schemes. Moreover, raw data transmission inflates latency and energy consumption, hindering real-time and resource-aware decision-making. To overcome these limitations, this paper presents a digital twin (DT)-driven, semantic-aware offloading framework tailored for LEO-integrated MEC systems. The proposed framework aims to minimize end-to-end DT synchronization delay while adhering to strict energy, semantic fidelity, and computational constraints. Semantic encoders extract task-relevant information to compress payloads, and a binary offloading strategy ensures each task is either fully executed locally or offloaded entirely. The problem is formulated as a joint optimization of offloading decisions, edge server selection, semantic compression ratio, and transmission power allocation. A proximal policy optimization (PPO)-based deep reinforcement learning algorithm is developed to solve the problem, leveraging real-time DT feedback for adaptive, context-aware control under dynamic network conditions. Simulation results demonstrate that the proposed framework reduces DT synchronization delay by up to 45 % vs. local execution, by 26–35 % vs. non-semantic offloading, and by 5–10 % vs. DRL alternative at high load, with statistically significant gaps. Additionally, the system maintains energy and semantic fidelity requirements while scaling efficiently with data volume and device density. These findings offer a practical and scalable solution for enabling reliable, low-latency DT services in 6G satellite–ground integrated IoT networks.

高效地将任务卸载到低地球轨道（LEO）卫星辅助的移动边缘计算（MEC）服务器对于解决远程物联网（IoT）设备的计算延迟和能量限制至关重要。然而，低轨道卫星网络固有的挑战——包括动态拓扑、间歇性连接和带宽稀缺——削弱了传统卸载方案的性能。此外，原始数据传输增加了延迟和能耗，阻碍了实时和资源感知的决策。为了克服这些限制，本文提出了一种为leo集成MEC系统量身定制的数字孪生（DT）驱动的语义感知卸载框架。该框架旨在最小化端到端DT同步延迟，同时遵守严格的能量、语义保真度和计算约束。语义编码器提取任务相关信息来压缩有效负载，二进制卸载策略确保每个任务要么在本地完全执行，要么完全卸载。该问题被表述为卸载决策、边缘服务器选择、语义压缩比和传输功率分配的联合优化。为了解决这一问题，开发了一种基于近端策略优化（PPO）的深度强化学习算法，利用实时DT反馈在动态网络条件下进行自适应、上下文感知控制。仿真结果表明，与本地执行相比，所提出的框架可将DT同步延迟减少高达45%，与非语义卸载相比可减少26 - 35%，在高负载下与DRL替代方案相比可减少5 - 10%，具有统计学上显着的差距。此外，该系统在保持能量和语义保真度要求的同时，有效地扩展数据量和设备密度。这些发现为在6G卫星地面集成物联网网络中实现可靠、低延迟的DT服务提供了一种实用且可扩展的解决方案。

{"title":"Digital twin-driven semantic offloading for LEO-MEC-enabled remote IoT networks","authors":"Ayalneh Bitew Wondmagegn, Dongwook Won, Donghyun Lee, Jaemin Kim, Juyoung Kim, Sungrae Cho","doi":"10.1016/j.iot.2025.101831","DOIUrl":"10.1016/j.iot.2025.101831","url":null,"abstract":"<div><div>Efficient task offloading to low-Earth orbit (LEO) satellite-assisted mobile edge computing (MEC) servers is vital for addressing the computational delay and energy constraints of remote Internet of Things (IoT) devices. However, inherent challenges in LEO satellite networks–including dynamic topology, intermittent connectivity, and bandwidth scarcity undermine the performance of conventional offloading schemes. Moreover, raw data transmission inflates latency and energy consumption, hindering real-time and resource-aware decision-making. To overcome these limitations, this paper presents a digital twin (DT)-driven, semantic-aware offloading framework tailored for LEO-integrated MEC systems. The proposed framework aims to minimize end-to-end DT synchronization delay while adhering to strict energy, semantic fidelity, and computational constraints. Semantic encoders extract task-relevant information to compress payloads, and a binary offloading strategy ensures each task is either fully executed locally or offloaded entirely. The problem is formulated as a joint optimization of offloading decisions, edge server selection, semantic compression ratio, and transmission power allocation. A proximal policy optimization (PPO)-based deep reinforcement learning algorithm is developed to solve the problem, leveraging real-time DT feedback for adaptive, context-aware control under dynamic network conditions. Simulation results demonstrate that the proposed framework reduces DT synchronization delay by up to 45 % vs. local execution, by 26–35 % vs. non-semantic offloading, and by 5–10 % vs. DRL alternative at high load, with statistically significant gaps. Additionally, the system maintains energy and semantic fidelity requirements while scaling efficiently with data volume and device density. These findings offer a practical and scalable solution for enabling reliable, low-latency DT services in 6G satellite–ground integrated IoT networks.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101831"},"PeriodicalIF":7.6,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145615750","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

AtomicVAD: A tiny voice activity detection model for efficient inference in intelligent IoT systems AtomicVAD：用于智能物联网系统中高效推理的微型语音活动检测模型

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

Internet of Things

Pub Date : 2025-11-20 DOI: 10.1016/j.iot.2025.101822

Angelo J. Soto-Vergel , Prashant Sankaran , Juan C. Velez , Rene Amaya-Mier , Diana Ramirez-Rios

This paper introduces AtomicVAD, an ultra-lightweight, end-to-end voice activity detection (VAD) model designed for inference on resource-constrained microcontrollers at the extreme edge. Existing VAD models often rely on large architectures with thousands of trainable parameters, making them impractical for deployment on low-power microcontrollers commonly used in internet of things systems. Even with compression methods such as quantization or pruning, these models typically fail to achieve low-latency performance under strict power and memory limits. AtomicVAD overcomes these limitations through the introduction of the General Growing Cosine Unit, a trainable oscillatory activation function that embeds feature learning within periodic modulations. This design enables remarkable efficiency with approximately 0.3k trainable parameters, representing a 99.7 % reduction compared to commonly used baselines like MarbleNet, while maintaining competitive accuracy. Evaluated on the challenging AVA-Speech benchmark, AtomicVAD achieves an AUROC of 0.903 and an F₂-score of 0.891, outperforming larger state-of-the-art systems and demonstrating robustness to background noise and music. Optimized for extreme efficiency, AtomicVAD enables ultra-low latency inference —as low as 26 ms on a 240 MHz Cortex-M7 and 1.22 s on a 64 MHz Cortex-M4F— facilitated by INT8 quantization. Its memory footprint remains below 75 kB Flash and 65 kB SRAM. A real-world LoRaWAN field trial further validated its practicality, showing that on-device speech gating eliminates unnecessary, bandwidth-intensive audio uploads, reducing over-the-air delays from minutes to milliseconds. Key use cases include remote monitoring, smart-home control, disaster-response sensor networks, and other long-range, low-power systems requiring efficient, always-on audio processing.

本文介绍了AtomicVAD，这是一种超轻量的端到端语音活动检测（VAD）模型，旨在对资源受限的微控制器进行极端边缘推理。即使使用量化或修剪等压缩方法，在严格的功率和内存限制下，这些模型通常也无法实现低延迟性能。AtomicVAD通过引入通用增长余弦单元克服了这些限制，这是一个可训练的振荡激活函数，在周期性调制中嵌入了特征学习。这种设计能够以大约0.3k的可训练参数实现显着的效率，与常用的基准（如MarbleNet）相比，降低了99.7%，同时保持了具有竞争力的准确性。在具有挑战性的AVA-Speech基准测试中，AtomicVAD的AUROC为0.903，F2-score为0.891，优于大型最先进的系统，并表现出对背景噪声和音乐的鲁棒性。AtomicVAD为极高的效率进行了优化，通过INT8量化实现了超低延迟推理-在240 MHz的Cortex-M7上低至26 ms，在64 MHz的Cortex-M4F上低至1.22 s。它的内存占用仍然低于75 kB闪存和65 kB SRAM。真实世界的LoRaWAN现场试验进一步验证了其实用性，表明设备上的语音门控消除了不必要的、带宽密集型的音频上传，将无线延迟从几分钟减少到几毫秒。主要用例包括远程监控、智能家居控制、灾难响应传感器网络，以及其他需要高效、始终在线的音频处理的远程、低功耗系统。

{"title":"AtomicVAD: A tiny voice activity detection model for efficient inference in intelligent IoT systems","authors":"Angelo J. Soto-Vergel , Prashant Sankaran , Juan C. Velez , Rene Amaya-Mier , Diana Ramirez-Rios","doi":"10.1016/j.iot.2025.101822","DOIUrl":"10.1016/j.iot.2025.101822","url":null,"abstract":"<div><div>This paper introduces AtomicVAD, an ultra-lightweight, end-to-end voice activity detection (VAD) model designed for inference on resource-constrained microcontrollers at the extreme edge. Existing VAD models often rely on large architectures with thousands of trainable parameters, making them impractical for deployment on low-power microcontrollers commonly used in internet of things systems. Even with compression methods such as quantization or pruning, these models typically fail to achieve low-latency performance under strict power and memory limits. AtomicVAD overcomes these limitations through the introduction of the General Growing Cosine Unit, a trainable oscillatory activation function that embeds feature learning within periodic modulations. This design enables remarkable efficiency with approximately 0.3k trainable parameters, representing a 99.7 % reduction compared to commonly used baselines like MarbleNet, while maintaining competitive accuracy. Evaluated on the challenging AVA-Speech benchmark, AtomicVAD achieves an AUROC of 0.903 and an F<sub>2</sub>-score of 0.891, outperforming larger state-of-the-art systems and demonstrating robustness to background noise and music. Optimized for extreme efficiency, AtomicVAD enables ultra-low latency inference —as low as 26 ms on a 240 MHz Cortex-M7 and 1.22 s on a 64 MHz Cortex-M4F— facilitated by INT8 quantization. Its memory footprint remains below 75 kB Flash and 65 kB SRAM. A real-world LoRaWAN field trial further validated its practicality, showing that on-device speech gating eliminates unnecessary, bandwidth-intensive audio uploads, reducing over-the-air delays from minutes to milliseconds. Key use cases include remote monitoring, smart-home control, disaster-response sensor networks, and other long-range, low-power systems requiring efficient, always-on audio processing.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101822"},"PeriodicalIF":7.6,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145681810","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

Improving power consumption in IoT devices through neural network-based decision making 通过基于神经网络的决策改善物联网设备的功耗

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

Internet of Things

Pub Date : 2025-11-19 DOI: 10.1016/j.iot.2025.101827

Vladimir G. Da Silva , Nelson S. Rosa , Fernando Aires , Wellison R.M. Santos

Advances in the Internet of Things (IoT) have led to several challenges across domains, creating opportunities for new solutions. The large volume of data and high processing demands of IoT applications, typically handled by cloud providers, make this approach costly regarding storage, computation, and latency. This fact has led to the emergence of the fog computing paradigm that enables the integrated use of edge and cloud resources. In this new scenario, one of the main challenges is managing containerised IoT applications that may migrate from fog nodes (IoT Devices) to the cloud and vice versa. This management is needed to preserve system performance and user experience while considering cloud resource costs. The container migration becomes especially critical for battery-powered devices, whose energy autonomy is a significant concern. Existing solutions do not consider power consumption and the cost of fog-cloud settings in the migration process. This paper proposes IRAS-IoT (Intelligent Replacement as a Service for IoT), a solution for autonomously migrating containers between fog nodes and the cloud. Based on MAPE-K, IRAS-IoT adopts a Multilayer Perceptron (MLP) neural network model to decide on migrating containers and optimising workload distribution according to devices’ power consumption. Regarding cost optimisation, in scenarios where fog nodes become overloaded, the solution may also allocate containers to a cloud provider, selecting the most cost-effective option. Experimental results show that IRAS-IoT reduces energy consumption by up to 18% and extends battery life by 34%, and lowers cloud operational costs compared to the baseline scenario.

物联网（IoT）的进步带来了跨领域的挑战，为新的解决方案创造了机会。物联网应用程序的大量数据和高处理需求通常由云提供商处理，这使得这种方法在存储、计算和延迟方面成本高昂。这一事实导致了雾计算范式的出现，它支持边缘和云资源的集成使用。在这种新情况下，主要挑战之一是管理容器化物联网应用程序，这些应用程序可能从雾节点（物联网设备）迁移到云，反之亦然。在考虑云资源成本的同时，需要这种管理来保持系统性能和用户体验。对于电池供电的设备来说，容器的迁移变得尤为重要，因为电池供电设备的能源自主性是一个重大问题。现有的解决方案没有考虑迁移过程中的功耗和雾云设置的成本。本文提出了IRAS-IoT (Intelligent Replacement as a Service for IoT)，这是一种在雾节点和云之间自主迁移容器的解决方案。IRAS-IoT基于MAPE-K，采用多层感知器（Multilayer Perceptron， MLP）神经网络模型，根据设备功耗决定迁移容器，优化工作负载分配。关于成本优化，在雾节点过载的情况下，解决方案还可以将容器分配给云提供商，选择最具成本效益的选项。实验结果表明，与基准方案相比，IRAS-IoT可将能耗降低18%，将电池寿命延长34%，并降低云运营成本。

{"title":"Improving power consumption in IoT devices through neural network-based decision making","authors":"Vladimir G. Da Silva , Nelson S. Rosa , Fernando Aires , Wellison R.M. Santos","doi":"10.1016/j.iot.2025.101827","DOIUrl":"10.1016/j.iot.2025.101827","url":null,"abstract":"<div><div>Advances in the Internet of Things (IoT) have led to several challenges across domains, creating opportunities for new solutions. The large volume of data and high processing demands of IoT applications, typically handled by cloud providers, make this approach costly regarding storage, computation, and latency. This fact has led to the emergence of the fog computing paradigm that enables the integrated use of edge and cloud resources. In this new scenario, one of the main challenges is managing containerised IoT applications that may migrate from fog nodes (IoT Devices) to the cloud and vice versa. This management is needed to preserve system performance and user experience while considering cloud resource costs. The container migration becomes especially critical for battery-powered devices, whose energy autonomy is a significant concern. Existing solutions do not consider power consumption and the cost of fog-cloud settings in the migration process. This paper proposes <span>IRAS-IoT</span> (Intelligent Replacement as a Service for IoT), a solution for autonomously migrating containers between fog nodes and the cloud. Based on MAPE-K, <span>IRAS-IoT</span> adopts a Multilayer Perceptron (MLP) neural network model to decide on migrating containers and optimising workload distribution according to devices’ power consumption. Regarding cost optimisation, in scenarios where fog nodes become overloaded, the solution may also allocate containers to a cloud provider, selecting the most cost-effective option. Experimental results show that IRAS-IoT reduces energy consumption by up to 18% and extends battery life by 34%, and lowers cloud operational costs compared to the baseline scenario.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101827"},"PeriodicalIF":7.6,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145570535","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

Energy-efficient cryptographic optimization for narrowband IoT security: Integrating blockchain and EP-CuMAC with ECM-SHA256 窄带物联网安全节能加密优化：区块链和EP-CuMAC与ECM-SHA256集成

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

Internet of Things

Pub Date : 2025-11-18 DOI: 10.1016/j.iot.2025.101828

Hafizullah Kakar , Vamshi S. Mohan , Swapnoneel Roy , Ayan Dutta , O. Patrick Kreidl , Ladislau Bölöni , Sriram Sankaran

Narrowband Internet of Things (NB-IoT) continues to expand but faces challenges of cryptographic overhead and energy consumption. Security frameworks such as blockchain and Energy-Performance Cumulative Message Authentication Codes (EP-CuMAC) rely heavily on SHA-256, which is not optimized for energy-limited devices. This work unifies two complementary approaches-a hybrid blockchain-based NB-IoT framework and an EP-CuMAC-based framework-by engineering their cryptographic core with an Energy Complexity Model-optimized SHA-256 (ECM-SHA256). ECM applies parallel memory-bank mapping and block-level access optimization to reduce redundant power usage while preserving algorithmic integrity. Experimental evaluation on identical Intel DDR3 systems using pyRAPL shows energy savings of 2–13 % across blockchain (Unique ID Generation, Device Join, Transactions) and EP-CuMAC modules (Feedback, Prediction, Verification, Retransmission). The optimization leverages the Energy Complexity Model’s parallel memory-bank mapping of SHA-256, implemented on identical Intel DDR3 systems using pyRAPL for repeatable measurements. The results position ECM-SHA256 as a generalizable cryptographic optimization strategy for secure and sustainable NB-IoT deployments.

窄带物联网（NB-IoT）在不断扩展的同时，也面临着加密开销和能耗的挑战。区块链和能源性能累积消息认证码（EP-CuMAC）等安全框架严重依赖SHA-256，而SHA-256并未针对能源限制设备进行优化。这项工作结合了两种互补的方法-基于混合区块链的NB-IoT框架和基于ep - cumac的框架-通过使用优化的能量复杂性模型SHA-256 （ECM-SHA256）来设计其加密核心。ECM采用并行内存库映射和块级访问优化来减少冗余功耗，同时保持算法的完整性。在使用pyRAPL的相同英特尔DDR3系统上的实验评估显示，在区块链（唯一ID生成，设备连接，事务）和EP-CuMAC模块（反馈，预测，验证，重发）中节能2 - 13%。优化利用了能量复杂性模型的SHA-256并行内存库映射，在相同的英特尔DDR3系统上实现，使用pyRAPL进行可重复测量。研究结果将ECM-SHA256定位为安全、可持续的NB-IoT部署的通用加密优化策略。

{"title":"Energy-efficient cryptographic optimization for narrowband IoT security: Integrating blockchain and EP-CuMAC with ECM-SHA256","authors":"Hafizullah Kakar , Vamshi S. Mohan , Swapnoneel Roy , Ayan Dutta , O. Patrick Kreidl , Ladislau Bölöni , Sriram Sankaran","doi":"10.1016/j.iot.2025.101828","DOIUrl":"10.1016/j.iot.2025.101828","url":null,"abstract":"<div><div>Narrowband Internet of Things (NB-IoT) continues to expand but faces challenges of cryptographic overhead and energy consumption. Security frameworks such as blockchain and Energy-Performance Cumulative Message Authentication Codes (EP-CuMAC) rely heavily on SHA-256, which is not optimized for energy-limited devices. This work unifies two complementary approaches-a hybrid blockchain-based NB-IoT framework and an EP-CuMAC-based framework-by engineering their cryptographic core with an Energy Complexity Model-optimized SHA-256 (ECM-SHA256). ECM applies parallel memory-bank mapping and block-level access optimization to reduce redundant power usage while preserving algorithmic integrity. Experimental evaluation on identical Intel DDR3 systems using pyRAPL shows energy savings of 2–13 % across blockchain (Unique ID Generation, Device Join, Transactions) and EP-CuMAC modules (Feedback, Prediction, Verification, Retransmission). The optimization leverages the Energy Complexity Model’s parallel memory-bank mapping of SHA-256, implemented on identical Intel DDR3 systems using pyRAPL for repeatable measurements. The results position ECM-SHA256 as a generalizable cryptographic optimization strategy for secure and sustainable NB-IoT deployments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101828"},"PeriodicalIF":7.6,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145570536","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

Proactive context aware task offloading in digital twin driven federated IoT systems with large language models 具有大型语言模型的数字孪生驱动的联邦物联网系统中的主动上下文感知任务卸载

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

Internet of Things

Pub Date : 2025-11-17 DOI: 10.1016/j.iot.2025.101826

Klea Elmazi , Donald Elmazi , Jonatan Lerga

This study considers the combination of Digital Twins (DT), Federated Learning (FL), and computation offloading to establish a context-aware framework for effective resource management in IoT networks. Although DT models can predict battery levels, CPU usage, and network delays to aid reinforcement learning (RL) agents, earlier RL-based controllers require significant training and are slow to adapt to changes. To overcome this issue, we propose a Large Language Model (LLM)-assisted offloading method that transforms real-time DT predictions and selected historical Explainable DT with Federated Multi-Agent RL (MARL) examples into structured natural-language prompts. Through in-context learning, LLM deduces offloading tactics without retraining, while FL aligns global convergence metrics to optimize the balance between inference accuracy and energy efficiency. Simulation studies conducted for baseline and unstable wireless network scenarios reveal that the LLM controller persistently maintains near-optimal latency and reduces energy use. In a baseline scenario with

N = 36

devices, the LLM achieves an average latency of 252 ms, which is only 5 % higher than edge offloading, while cutting energy consumption by around 20 %. Under unstable wireless conditions, it achieves an average latency of 276 ms with energy use of 0.122 J, as opposed to 0.154 J for edge offloading. These findings validate that LLM-based decision making facilitates scalable, adaptive, and energy-efficient task scheduling, presenting a viable alternative to RL controllers in DT-enabled federated IoT systems.

本研究考虑了数字孪生（DT）、联邦学习（FL）和计算卸载的结合，为物联网网络中有效的资源管理建立了一个上下文感知框架。虽然DT模型可以预测电池电量、CPU使用率和网络延迟，以帮助强化学习（RL）代理，但早期基于强化学习的控制器需要大量的训练，并且适应变化的速度很慢。为了克服这个问题，我们提出了一种大型语言模型（LLM）辅助卸载方法，该方法将实时DT预测和具有联邦多代理RL （MARL）示例的选定历史可解释DT转换为结构化的自然语言提示。通过上下文学习，LLM推导卸载策略而无需再训练，而FL对齐全局收敛指标以优化推理精度和能源效率之间的平衡。对基线和不稳定无线网络场景进行的仿真研究表明，LLM控制器持续保持接近最佳的延迟，并减少了能源消耗。在N=36个设备的基线场景中，LLM实现了252毫秒的平均延迟，仅比边缘卸载高5%，同时降低了大约20%的能耗。在不稳定的无线条件下，它的平均延迟为276毫秒，能耗为0.122 J，而边缘卸载的能耗为0.154 J。这些发现验证了基于llm的决策有助于可扩展、自适应和节能的任务调度，在支持dt的联邦物联网系统中提供了RL控制器的可行替代方案。

{"title":"Proactive context aware task offloading in digital twin driven federated IoT systems with large language models","authors":"Klea Elmazi , Donald Elmazi , Jonatan Lerga","doi":"10.1016/j.iot.2025.101826","DOIUrl":"10.1016/j.iot.2025.101826","url":null,"abstract":"<div><div>This study considers the combination of Digital Twins (DT), Federated Learning (FL), and computation offloading to establish a context-aware framework for effective resource management in IoT networks. Although DT models can predict battery levels, CPU usage, and network delays to aid reinforcement learning (RL) agents, earlier RL-based controllers require significant training and are slow to adapt to changes. To overcome this issue, we propose a Large Language Model (LLM)-assisted offloading method that transforms real-time DT predictions and selected historical Explainable DT with Federated Multi-Agent RL (MARL) examples into structured natural-language prompts. Through in-context learning, LLM deduces offloading tactics without retraining, while FL aligns global convergence metrics to optimize the balance between inference accuracy and energy efficiency. Simulation studies conducted for baseline and unstable wireless network scenarios reveal that the LLM controller persistently maintains near-optimal latency and reduces energy use. In a baseline scenario with <span><math><mrow><mi>N</mi><mo>=</mo><mn>36</mn></mrow></math></span> devices, the LLM achieves an average latency of 252 ms, which is only 5 % higher than edge offloading, while cutting energy consumption by around 20 %. Under unstable wireless conditions, it achieves an average latency of 276 ms with energy use of 0.122 J, as opposed to 0.154 J for edge offloading. These findings validate that LLM-based decision making facilitates scalable, adaptive, and energy-efficient task scheduling, presenting a viable alternative to RL controllers in DT-enabled federated IoT systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101826"},"PeriodicalIF":7.6,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145570538","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

Enhancing beamforming performance in 6G-V2X base stations using meta-deep reinforcement Q-learning 利用元深度强化q学习增强6G-V2X基站的波束成形性能

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

Internet of Things

Pub Date : 2025-11-14 DOI: 10.1016/j.iot.2025.101825

Ali Belgacem , Abbas Bradai

Beamforming plays a crucial role in base stations, particularly with the integration of Vehicle-to-Everything (V2X), Artificial Intelligence (AI), and massive Multiple Input Multiple Output (MIMO) technologies in 6G networks. It significantly enhances network performance by accurately tracking vehicles. However, achieving effective beamforming in dynamic environments with moving vehicles while maintaining high performance at base stations remains challenging. This paper presents a novel approach using meta-deep reinforcement Q-learning (Meta-DRQL) to develop a beamforming model that narrows beamwidth and improves system performance. The model dynamically adjusts key parameters for optimal beamforming. Simulation results demonstrate notable improvements in beamwidth efficiency and energy consumption, highlighting the model’s potential for V2X communications and 6G MIMO systems. These advancements contribute to the creation of more reliable, high-capacity networks for connected vehicles and smart infrastructure.

波束成形在基站中起着至关重要的作用，特别是在6G网络中集成了车联网（V2X）、人工智能（AI）和大规模多输入多输出（MIMO）技术。它通过精确跟踪车辆显著提高了网络性能。然而，在移动车辆的动态环境中实现有效的波束形成，同时保持基站的高性能仍然具有挑战性。本文提出了一种利用元深度强化q -学习（Meta-DRQL）开发波束形成模型的新方法，该模型可以缩小波束宽度并提高系统性能。该模型动态调整波束形成的关键参数。仿真结果表明，该模型在波束宽度效率和能耗方面有显著改善，突出了该模型在V2X通信和6G MIMO系统中的潜力。这些进步有助于为互联汽车和智能基础设施创建更可靠、更大容量的网络。

引用次数: 0

Blockchain-enabled traceability for rice blending fraud: A practical framework to strengthen supply chain integrity in smart agricultural IoT 支持区块链的大米混合欺诈可追溯性：智能农业物联网中加强供应链完整性的实用框架

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

Internet of Things

Pub Date : 2025-11-14 DOI: 10.1016/j.iot.2025.101824

Tao Peng, Langfeng Wang

The rising demand for high-quality rice, driven by improving living standards, has led consumers to increasingly pay premium prices. However, the scarcity of high-quality rice resources has created opportunities for adulteration, often motivated by profit-seeking behavior. Blockchain technology, characterized by its tamper-proof nature, transparency, and traceability, presents a robust solution to this challenge. This paper proposes a blockchain-based framework to address the issue of mixed selling of rice of varying qualities, thereby enhancing supply chain efficiency and credibility. The proposed solution is designed to be generalizable, applicable to products with similar forms yet significantly different qualities. Empirical results show that the data throughput of the proposed model scales linearly with increasing test size, highlighting its scalability and stable performance in large-scale implementation. This study underscores the potential of blockchain technology to mitigate adulteration risks while supporting scalable and reliable supply chain management.

在生活水平提高的推动下，对优质大米的需求不断增长，导致消费者越来越多地支付高价。然而，优质大米资源的稀缺为掺假创造了机会，而掺假往往是出于逐利行为的动机。区块链技术的特点是防篡改、透明和可追溯性，为这一挑战提供了一个强大的解决方案。本文提出了一个基于区块链的框架来解决不同质量大米的混合销售问题，从而提高供应链的效率和可信度。所提出的解决方案被设计为具有通用性，适用于具有相似形式但显著不同质量的产品。实验结果表明，该模型的数据吞吐量随测试规模的增加呈线性增长，突出了其在大规模实施中的可扩展性和稳定性。这项研究强调了区块链技术在支持可扩展和可靠的供应链管理的同时减轻掺假风险的潜力。

引用次数: 0

IoT-enabled CCTV monitoring and deep learning for automated water body segmentation in agricultural reservoirs 基于物联网的闭路电视监控和深度学习，用于农业水库的自动水体分割

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

Internet of Things

Pub Date : 2025-11-12 DOI: 10.1016/j.iot.2025.101823

Soon Ho Kwon , Youcan Feng , Seungyub Lee

This study presents an IoT-enabled deep learning framework for automated water body segmentation in agricultural reservoirs using CCTV imagery. The framework integrates IoT-based long-term monitoring imagery with public benchmark water datasets to improve segmentation robustness under diverse visual conditions encountered in real-world agricultural settings. Three training strategies were defined—(I) benchmark-only, (II) CCTV-only, and (III) integrated—to systematically evaluate generalization across heterogeneous data sources. We also evaluate three U-Net–based architectures: Model 1 (baseline with binary cross-entropy loss), Model 2 (the same architecture trained with a differentiable Jaccard loss), and Model 3 (a parameter-reduced architecture with weighted cross-entropy, designed for edge inference on IoT hardware). Each configuration was trained and validated over ten independent runs to ensure statistical reliability. Model 2 consistently achieved the highest and most stable performance across all training strategies, demonstrating that loss-function optimization, rather than architectural expansion alone, is the primary driver of performance improvement. The integrated training strategy (Strategy III), which combines benchmark and CCTV imagery, yielded the strongest generalization, improving mean IoU by roughly 15–20% and reducing variability compared to single-source training. Performance differences between test sites were attributable mainly to environmental variability—fog, reflections, shadows, surface ripples, and vegetation occlusions—rather than model instability. Validated on two independent reservoirs that were fully held out from training, the framework generalized to new sites without requiring additional site-specific annotation. Model 3′s parameter-efficient design (approximately 60% fewer trainable parameters) supports near-edge inference on embedded IoT devices, enabling continuous, unattended, IoT-based monitoring of agricultural reservoirs for smart irrigation management.

本研究提出了一种基于物联网的深度学习框架，用于利用闭路电视图像对农业水库的水体进行自动分割。该框架将基于物联网的长期监测图像与公共基准水数据集集成在一起，以提高在现实农业环境中遇到的不同视觉条件下的分割鲁棒性。定义了三种训练策略- (I)仅基准，（II）仅cctv和（III）集成-以系统地评估跨异构数据源的泛化。我们还评估了三种基于u - net的架构：模型1（具有二进制交叉熵损失的基线），模型2（使用可微分的Jaccard损失训练的相同架构）和模型3（具有加权交叉熵的参数减少架构，专为物联网硬件的边缘推理而设计）。每个配置都经过十次独立运行的训练和验证，以确保统计可靠性。模型2在所有训练策略中始终获得最高和最稳定的性能，表明损失函数优化，而不仅仅是架构扩展，是性能改进的主要驱动因素。综合训练策略（策略III）结合了基准和CCTV图像，产生了最强的泛化，与单源训练相比，平均IoU提高了大约15-20%，并减少了可变性。测试地点之间的性能差异主要归因于环境的可变性——雾、反射、阴影、表面波纹和植被遮挡——而不是模型的不稳定性。在两个独立的水库上进行了验证，这些水库从训练中完全坚持下来，该框架推广到新的站点，而不需要额外的站点特定注释。Model 3的参数高效设计（可训练参数减少约60%）支持嵌入式物联网设备的近边缘推理，实现对农业水库的连续、无人值守、基于物联网的智能灌溉管理监测。

{"title":"IoT-enabled CCTV monitoring and deep learning for automated water body segmentation in agricultural reservoirs","authors":"Soon Ho Kwon , Youcan Feng , Seungyub Lee","doi":"10.1016/j.iot.2025.101823","DOIUrl":"10.1016/j.iot.2025.101823","url":null,"abstract":"<div><div>This study presents an IoT-enabled deep learning framework for automated water body segmentation in agricultural reservoirs using CCTV imagery. The framework integrates IoT-based long-term monitoring imagery with public benchmark water datasets to improve segmentation robustness under diverse visual conditions encountered in real-world agricultural settings. Three training strategies were defined—(I) benchmark-only, (II) CCTV-only, and (III) integrated—to systematically evaluate generalization across heterogeneous data sources. We also evaluate three U-Net–based architectures: Model 1 (baseline with binary cross-entropy loss), Model 2 (the same architecture trained with a differentiable Jaccard loss), and Model 3 (a parameter-reduced architecture with weighted cross-entropy, designed for edge inference on IoT hardware). Each configuration was trained and validated over ten independent runs to ensure statistical reliability. Model 2 consistently achieved the highest and most stable performance across all training strategies, demonstrating that loss-function optimization, rather than architectural expansion alone, is the primary driver of performance improvement. The integrated training strategy (Strategy III), which combines benchmark and CCTV imagery, yielded the strongest generalization, improving mean IoU by roughly 15–20% and reducing variability compared to single-source training. Performance differences between test sites were attributable mainly to environmental variability—fog, reflections, shadows, surface ripples, and vegetation occlusions—rather than model instability. Validated on two independent reservoirs that were fully held out from training, the framework generalized to new sites without requiring additional site-specific annotation. Model 3′s parameter-efficient design (approximately 60% fewer trainable parameters) supports near-edge inference on embedded IoT devices, enabling continuous, unattended, IoT-based monitoring of agricultural reservoirs for smart irrigation management.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101823"},"PeriodicalIF":7.6,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145615717","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

LoRaGeo-PSW: a prompt-aligned large language model for few-shot fingerprint geolocation in urban LoRaWAN networks LoRaGeo-PSW：用于城市LoRaWAN网络中少拍指纹定位的提示对齐大语言模型

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

Internet of Things

Pub Date : 2025-11-10 DOI: 10.1016/j.iot.2025.101821

Wenbin Shi , Zhongxu Zhan , Jingsheng Lei , Xingli Gan

Accurate and efficient geolocation remains a critical need for low-power IoT networks, particularly in large urban environments where GNSS-based positioning is often infeasible. Fingerprint-based localization using LoRaWAN signals offers a scalable alternative, but conventional methods depend on rigid matching algorithms and static radio maps, leading to poor performance in complex cityscapes. This work proposes LoRaGeo-PSW, a novel geolocation framework based on large language models (LLMs) that aligns structured wireless signal features with prompt-driven reasoning. Built upon a GPT-2 foundation, the model encodes LoRaWAN fingerprints—including RSSI and SNR from multiple gateways—as token sequences, and interprets them in context using a structured workflow-aware architecture. By integrating signal processing workflows via lightweight adapter modules and employing low-rank adaptation (LoRA), LoRaGeo-PSW offers both interpretability and parameter efficiency. Crucially, the model enables few-shot localization by conditioning on a handful of example fingerprints, thereby adapting to new environments without retraining. Evaluated on a public LoRaWAN dataset from urban Antwerp with over 130,000 transmissions, the model achieves a median localization error of approximately 150 m, substantially surpassing classical fingerprinting and deep learning baselines. This work introduces a new paradigm for wireless localization, demonstrating that LLMs can effectively bridge structured signal reasoning and geospatial inference through prompt-driven alignment.

准确和高效的地理定位仍然是低功耗物联网网络的关键需求，特别是在大型城市环境中，基于gnss的定位通常是不可行的。使用LoRaWAN信号的基于指纹的定位提供了一种可扩展的替代方案，但传统方法依赖于严格的匹配算法和静态无线电地图，导致在复杂的城市环境中性能不佳。这项工作提出了LoRaGeo-PSW，这是一种基于大型语言模型（llm）的新型地理定位框架，它将结构化无线信号特征与提示驱动推理相结合。该模型建立在GPT-2的基础上，将LoRaWAN指纹（包括来自多个网关的RSSI和SNR）编码为令牌序列，并使用结构化工作流感知架构在上下文中对其进行解释。通过轻量级适配器模块集成信号处理工作流，并采用低阶自适应（LoRA）， LoRaGeo-PSW提供了可解释性和参数效率。至关重要的是，该模型通过对少数指纹样本进行条件反射，实现了几次定位，从而无需重新训练即可适应新环境。在来自安特卫普城市超过13万次传输的公共LoRaWAN数据集上进行评估后，该模型的中位定位误差约为150米，大大超过了传统的指纹识别和深度学习基线。这项工作为无线定位引入了一种新的范例，表明llm可以通过提示驱动的校准有效地桥接结构化信号推理和地理空间推理。

{"title":"LoRaGeo-PSW: a prompt-aligned large language model for few-shot fingerprint geolocation in urban LoRaWAN networks","authors":"Wenbin Shi , Zhongxu Zhan , Jingsheng Lei , Xingli Gan","doi":"10.1016/j.iot.2025.101821","DOIUrl":"10.1016/j.iot.2025.101821","url":null,"abstract":"<div><div>Accurate and efficient geolocation remains a critical need for low-power IoT networks, particularly in large urban environments where GNSS-based positioning is often infeasible. Fingerprint-based localization using LoRaWAN signals offers a scalable alternative, but conventional methods depend on rigid matching algorithms and static radio maps, leading to poor performance in complex cityscapes. This work proposes LoRaGeo-PSW, a novel geolocation framework based on large language models (LLMs) that aligns structured wireless signal features with prompt-driven reasoning. Built upon a GPT-2 foundation, the model encodes LoRaWAN fingerprints—including RSSI and SNR from multiple gateways—as token sequences, and interprets them in context using a structured workflow-aware architecture. By integrating signal processing workflows via lightweight adapter modules and employing low-rank adaptation (LoRA), LoRaGeo-PSW offers both interpretability and parameter efficiency. Crucially, the model enables few-shot localization by conditioning on a handful of example fingerprints, thereby adapting to new environments without retraining. Evaluated on a public LoRaWAN dataset from urban Antwerp with over 130,000 transmissions, the model achieves a median localization error of approximately 150 m, substantially surpassing classical fingerprinting and deep learning baselines. This work introduces a new paradigm for wireless localization, demonstrating that LLMs can effectively bridge structured signal reasoning and geospatial inference through prompt-driven alignment.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101821"},"PeriodicalIF":7.6,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145521123","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

HealthCare 5.0: An industry 5.0 perspective for next-generation medical systems with synergistic integration of IoT, AI, and 6G 医疗保健5.0：具有物联网、人工智能和6G协同集成的下一代医疗系统的行业5.0视角

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

Internet of Things

Pub Date : 2025-11-07 DOI: 10.1016/j.iot.2025.101815

Abolfazl Younesi , Elyas Oustad , Mohsen Ansari , Thomas Fahringer , Rajkumar Buyya

The rising demand for personalized, reliable, and sustainable health services requires a significant shift beyond current technology barriers. This paper introduces HealthCare 5.0, a transformative vision for next-generation medical systems. It brings the Internet of Things (IoT), Artificial Intelligence (AI), and 6G communications together under the human-centered, sustainable, and resilient principles of Industry 5.0. HealthCare 5.0 showcases the convergence of IoT for continuous health monitoring, AI for intelligent reasoning, and 6G for dependable, low-latency connectivity. These elements work together to provide real-time, personalized, and proactive care. The analysis looks into how this collaboration supports advancements like remote diagnostics, digital twins, federated learning, explainable AI (XAI), and medical large language models (MedLLMs). It also addresses challenges in interoperability, energy efficiency, data privacy, and ethical AI. The framework stresses the importance of digital twins, ambient sensing, and wearable devices in facilitating predictive and patient-centered care. Despite progress, there are still gaps in standardization, clinician adoption, and the ethical use of these technologies. To overcome these issues, we propose a complete approach that combines IoT, AI, and 6G based on Industry 5.0 principles. This closed-loop model of “sense, transmit, reason, act” is backed by key performance indicators, real-world case studies, and a roadmap for compliance and regulatory support. By merging innovation with human values and systemic resilience, HealthCare 5.0 offers a forward-thinking plan for smart, safe, and fair healthcare systems.

对个性化、可靠和可持续的卫生服务的需求日益增长，这要求我们作出重大转变，突破目前的技术壁垒。本文介绍了下一代医疗系统的变革性愿景——HealthCare 5.0。它将物联网（IoT）、人工智能（AI）和6G通信在工业5.0的以人为本、可持续和弹性原则下结合在一起。医疗保健5.0展示了用于持续健康监测的物联网、用于智能推理的人工智能和用于可靠、低延迟连接的6G的融合。这些因素共同作用，提供实时、个性化和主动的护理。该分析着眼于这种合作如何支持远程诊断、数字双胞胎、联邦学习、可解释人工智能（XAI）和医学大型语言模型（medllm）等进步。它还解决了互操作性、能源效率、数据隐私和道德人工智能方面的挑战。该框架强调了数字孪生体、环境传感和可穿戴设备在促进预测性和以患者为中心的护理方面的重要性。尽管取得了进展，但在这些技术的标准化、临床医生采用和伦理使用方面仍存在差距。为了克服这些问题，我们提出了一种基于工业5.0原则结合物联网，人工智能和6G的完整方法。这种“感知、传递、推理、行动”的闭环模型得到了关键绩效指标、真实案例研究以及合规和监管支持路线图的支持。通过将创新与人类价值观和系统弹性相结合，HealthCare 5.0为智能、安全和公平的医疗保健系统提供了前瞻性的计划。

{"title":"HealthCare 5.0: An industry 5.0 perspective for next-generation medical systems with synergistic integration of IoT, AI, and 6G","authors":"Abolfazl Younesi , Elyas Oustad , Mohsen Ansari , Thomas Fahringer , Rajkumar Buyya","doi":"10.1016/j.iot.2025.101815","DOIUrl":"10.1016/j.iot.2025.101815","url":null,"abstract":"<div><div>The rising demand for personalized, reliable, and sustainable health services requires a significant shift beyond current technology barriers. This paper introduces HealthCare 5.0, a transformative vision for next-generation medical systems. It brings the Internet of Things (IoT), Artificial Intelligence (AI), and 6G communications together under the human-centered, sustainable, and resilient principles of Industry 5.0. HealthCare 5.0 showcases the convergence of IoT for continuous health monitoring, AI for intelligent reasoning, and 6G for dependable, low-latency connectivity. These elements work together to provide real-time, personalized, and proactive care. The analysis looks into how this collaboration supports advancements like remote diagnostics, digital twins, federated learning, explainable AI (XAI), and medical large language models (MedLLMs). It also addresses challenges in interoperability, energy efficiency, data privacy, and ethical AI. The framework stresses the importance of digital twins, ambient sensing, and wearable devices in facilitating predictive and patient-centered care. Despite progress, there are still gaps in standardization, clinician adoption, and the ethical use of these technologies. To overcome these issues, we propose a complete approach that combines IoT, AI, and 6G based on Industry 5.0 principles. This closed-loop model of “sense, transmit, reason, act” is backed by key performance indicators, real-world case studies, and a roadmap for compliance and regulatory support. By merging innovation with human values and systemic resilience, HealthCare 5.0 offers a forward-thinking plan for smart, safe, and fair healthcare systems.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"35 ","pages":"Article 101815"},"PeriodicalIF":7.6,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145500386","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