Internet Technology Letters最新文献_第8页

TinyML-Based Adaptive Pulse Shaping for Edge Intelligence in IoT/IIoT 基于tinyml的IoT/IIoT边缘智能自适应脉冲整形

IF 0.9

Internet Technology Letters Pub Date : 2025-07-15 DOI: 10.1002/itl2.70060

Afan Ali

引用次数: 0

EdgeKG-EN: A Dynamic English Knowledge Graph Framework With Edge Computing-Driven Optimization 基于边缘计算驱动优化的动态英语知识图谱框架

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70083

Minling Wu

引用次数: 0

A Stacking Ensemble Learning-Based Intrusion Detection System for Internet of Vehicles 基于层叠集成学习的车联网入侵检测系统

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70046

Huibin Xu, Long Fang

引用次数: 0

Design of Intelligent Building Environment Control System Based on Internet of Things and 6G Network 基于物联网和6G网络的智能建筑环境控制系统设计

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70040

Fenghua Xia, Luyue Han, Wei Qiao, Shan Su, Bowen Song

{"title":"Design of Intelligent Building Environment Control System Based on Internet of Things and 6G Network","authors":"Fenghua Xia, Luyue Han, Wei Qiao, Shan Su, Bowen Song","doi":"10.1002/itl2.70040","DOIUrl":"https://doi.org/10.1002/itl2.70040","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper proposes an intelligent building environment control system based on the Internet of Things and 6G network, aiming to solve the shortcomings of traditional intelligent building control systems in terms of high response delay and low energy efficiency. The Internet of Things technology is used to realize the interconnection and interoperability of devices and sensors, and the ultrahigh speed and low latency characteristics of the 6G network are used to ensure real-time data transmission and efficient collaboration. The system adopts a data processing architecture that combines edge computing and cloud computing to perform real-time processing and intelligent analysis of environmental data. In terms of security and privacy protection, AES-256 and RSA encryption technologies are used to ensure data security. The particle swarm optimization algorithm effectively reduces energy consumption and achieves a 6.67% energy saving efficiency improvement in the total energy consumption of the building. The evaluation results show that the total response time of the system on the temperature and humidity sensor is 80 ms, and the energy consumption performance is better than that of the traditional system. Even in high-density equipment and complex environments, the system can still achieve low-latency real-time response and intelligent adjustment, providing technical support for the future development of intelligent building environment control systems.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 5","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144615188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging 5G and AI Technologies to Enhance Real-Time English Language Learning 利用5G和人工智能技术增强实时英语学习

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70075

Xueqin Wang

{"title":"Leveraging 5G and AI Technologies to Enhance Real-Time English Language Learning","authors":"Xueqin Wang","doi":"10.1002/itl2.70075","DOIUrl":"https://doi.org/10.1002/itl2.70075","url":null,"abstract":"<div>\u0000 \u0000 <p>The integration of 5G and Artificial Intelligence (AI) technologies offers a powerful opportunity to revolutionize real-time English language learning by enabling faster, more responsive, and personalized educational experiences. These limitations hinder learner engagement and reduce the overall effectiveness of language acquisition, particularly in real-time communication scenarios. To overcome these challenges, this paper proposes a novel framework called the Smart Real-Time Language Enhancement System (SRLES). This framework integrates 5G-enabled connectivity with AI-driven tools such as speech recognition, natural language processing (NLP), and real-time error detection. The SRLES framework employs deep learning models, particularly recurrent and transformer-based architectures, for speech recognition and adaptive feedback. These are sometimes integrated with rule-based components for contextual fine-tuning, forming a hybrid approach. Experimental implementation of SRLES showed a significant improvement in learner outcomes, including a 30% increase in real-time communication accuracy and a 40% boost in learner retention rates. Additionally, users reported greater satisfaction and confidence in speaking skills. These results highlight the effectiveness of combining 5G and AI in creating an adaptive, efficient, and engaging English language learning environment. The 93.43% learner retention rate and 96.25% communication accuracy were measured over a 12-week period using a dataset of 120 participants across diverse age groups and educational backgrounds. Metrics were derived from usage logs, interaction success rates, and follow-up assessments.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 5","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144615184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TinyML-Driven On-Device Sports Command Recognition in Mobile and Dynamic Environments 移动和动态环境中tinyml驱动的设备上运动命令识别

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70090

Jiali Zang

{"title":"TinyML-Driven On-Device Sports Command Recognition in Mobile and Dynamic Environments","authors":"Jiali Zang","doi":"10.1002/itl2.70090","DOIUrl":"https://doi.org/10.1002/itl2.70090","url":null,"abstract":"<div>\u0000 \u0000 <p>In this article, we propose a novel TinyML-based framework for real-time sports command recognition under mobile conditions. Unlike conventional Human Activity Recognition (HAR) systems that rely on cloud-based processing or heavy on-device models, our method leverages lightweight deep neural networks, personalized transfer learning, and signal augmentation techniques to perform low-latency and energy-efficient inference directly on microcontroller-class devices. The system is designed to recognize a set of critical sports instructions (e.g., “Start Running,” “Jump,” and “Sprint”) in mobile or outdoor environments using only wearable inertial sensors. Extensive experiments demonstrate our method outperforms several state-of-the-art baselines in accuracy (95.8%), model size (14.5 KB), and energy efficiency (0.82 mJ per inference). Compared to prior wearable HAR systems, our method uniquely integrates motion-aware segmentation and user-personalized few-shot adaptation, resulting in a 5.3% accuracy gain and 4× model compression over baseline TinyML frameworks. The proposed method provides an effective balance between model accuracy, generalization, and hardware efficiency, even in scenarios with significant motion noise and environmental variability.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 5","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cloud-Native 5G Core Network Virtualization, Scalability, and Intelligent Traffic Management Applications 云原生5G核心网虚拟化、可扩展性和智能流量管理应用

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70076

Shangdong Li

{"title":"Cloud-Native 5G Core Network Virtualization, Scalability, and Intelligent Traffic Management Applications","authors":"Shangdong Li","doi":"10.1002/itl2.70076","DOIUrl":"https://doi.org/10.1002/itl2.70076","url":null,"abstract":"<div>\u0000 \u0000 <p>To meet the increasing demands of the modern networks, the dynamic resource allocation (DRA), improved Scalability and intelligent traffic management were made possible by the virtualization of the Cloud-native 5G Core Network (5GC). 5GC successfully manages the various network services using cloud-native principles, which could increase 5GC's potential in terms of automation, flexibility, and efficiency. Current 5GC applications primarily face three challenges: poor traffic management tactics, limited scalability in heavy traffic loads, and inefficient resource utilization (RU). Conventional virtualization techniques do not achieve dynamic response to changing network needs. Those traditional approaches may lead to higher latency and performance constraints. We suggest the Cloud-Native Adaptive 5G Core (CA5GC) Framework, which combines AI-driven traffic management, microservice-based architectures, and containerized network operations to address these problems. To maximize resource usage, guarantee scalability, and improve intelligent traffic handling, the framework makes use of dynamic network slicing, Kubernetes-based orchestration, and machine learning-powered predictive traffic analysis. The proposed CA5GC framework facilitates real-time adaptation of 5GC resources, ensuring optimal network performance even during peak loads. By integrating intelligent traffic classification and automated orchestration, CA5GC enhances network efficiency and reduces operational costs for service providers. Significant improvements in resource efficiency, reduced network congestion, and enhanced service quality are attained by the potential of CA5GC. The results are encouraging, with 96.35% resource utilization and 95.27% service quality achieved. These metrics reflect the framework's effectiveness in optimizing performance in cloud-native 5G environments.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 5","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144615030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Edge-Oriented Lightweight Facial Recognition for Real-Time Security Threat Detection in Sports Venues 面向边缘的轻量级面部识别技术用于体育场馆的实时安全威胁检测

IF 0.9

Internet Technology Letters Pub Date : 2025-07-14 DOI: 10.1002/itl2.70088

Chao Liu, Yi Qin

{"title":"Edge-Oriented Lightweight Facial Recognition for Real-Time Security Threat Detection in Sports Venues","authors":"Chao Liu, Yi Qin","doi":"10.1002/itl2.70088","DOIUrl":"https://doi.org/10.1002/itl2.70088","url":null,"abstract":"<div>\u0000 \u0000 <p>To address the challenges of complex background handling, detail enhancement, and lightweight requirements when using facial recognition as a security screening tool in sporting events, a lightweight network is proposed for rapid face recognition. In this network, the integration of the GhostNet block with the Squeeze-and-Excitation block is used to reduce feature redundancy and computational costs while enhancing foreground target discrimination and suppressing background interference. The network is further configured to incorporate Cross Stage Partial Networks, a development which has the effect of reducing computational costs by means of the division of gradient flows, whilst retaining multi-scale feature representation capabilities. The model that was trained with this network was then tested for face recognition using public datasets. Experimental results demonstrate that the model attains an [email protected] of 91.8% in face recognition, with a frame rate of 9.5 FPS and a latency of 38.1 ms on edge devices, surpassing comparable models. The proposed model demonstrates outstanding effectiveness in real-world event scenarios, providing valuable technical insights for improving face recognition in sports event management.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 5","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144615187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IoTGUARD: A Graph Learning Based-Approach for Early IoT Attack Traffic Detection IoTGUARD：基于图学习的早期物联网攻击流量检测方法

IF 0.9

Internet Technology Letters Pub Date : 2025-07-07 DOI: 10.1002/itl2.70055

Zinuo Yin, Wenbo Wang, Tao Hu, Hailong Ma

引用次数: 0

Enhancing 5G Networks Performance Using MIMO and MU-MIMO Technologies for High-Capacity Communication 利用MIMO和MU-MIMO技术增强5G网络性能，实现大容量通信

IF 0.9

Internet Technology Letters Pub Date : 2025-07-07 DOI: 10.1002/itl2.70069

P. Ashok, D. Sumathi, Krishnaraj Natarajan, S. Balakrishnan

{"title":"Enhancing 5G Networks Performance Using MIMO and MU-MIMO Technologies for High-Capacity Communication","authors":"P. Ashok, D. Sumathi, Krishnaraj Natarajan, S. Balakrishnan","doi":"10.1002/itl2.70069","DOIUrl":"https://doi.org/10.1002/itl2.70069","url":null,"abstract":"<div>\u0000 \u0000 <p>In order to accommodate the exponential growth of data-intensive apps and linked devices in the current era, the next generation of wireless networks must offer extraordinarily high speeds, great connection, and low latency. Two of the most significant advanced technologies fifth-generation (5G) networks use to fulfill these goals are multiple-input multiple-objectives (MIMO) and multiuser MIMO (MU-MIMO). The main emphasis of this work is on high-capacity communication and how MIMO and MU-MIMO technologies might enhance the performance of the 5G network. MU-MIMO expanded allows several users to access the same time-frequency resources free from interference, thereby optimizing spectrum consumption and boosting network capacity. These solutions meet the congested and dynamic conditions typical of modern urban and industrial settings by allowing flawless mobile broadband and ultrareliable low-latency communications (URLLC). The present article investigates the foundations of MIMO and MU-MIMO, how they are included into 5G new radio (NR) standards, and what part beamforming, spatial multiplexing, and channel estimation play in them. Among the subjects addressed are hardware complexity, pilot contamination, and channel state information (CSI) acquisition. Real-time inference and task scheduling in E5G-SPF are powered by machine learning for predictive analytics and reinforcement learning for dynamic resource allocation. These techniques enable adaptive decision-making and efficient task management. 5G networks use MIMO and MU-MIMO to manage the great rise in user demand and data traffic. Without these technologies, which this paper contends are necessary to open the path for future developments in the 6G network, the expected performance targets of 5G cannot be reached.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 4","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0