EAI Endorsed Trans. Ind. Networks Intell. Syst.最新文献

ERKT-Net: Implementing Efficient and Robust Knowledge Distillation for Remote Sensing Image Classification ERKT-Net：为遥感图像分类实现高效稳健的知识蒸馏

EAI Endorsed Trans. Ind. Networks Intell. Syst. Pub Date : 2024-07-03 DOI: 10.4108/eetinis.v11i3.4748

Huaxiang Song, Yafang Li, Xiaowen Li, Yuxuan Zhang, Yangyan Zhu, Yong Zhou

{"title":"ERKT-Net: Implementing Efficient and Robust Knowledge Distillation for Remote Sensing Image Classification","authors":"Huaxiang Song, Yafang Li, Xiaowen Li, Yuxuan Zhang, Yangyan Zhu, Yong Zhou","doi":"10.4108/eetinis.v11i3.4748","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.4748","url":null,"abstract":"The classification of Remote Sensing Images (RSIs) poses a significant challenge due to the presence of clustered ground objects and noisy backgrounds. While many approaches rely on scaling models to enhance accuracy, the deployment of RSI classifiers often requires substantial computational and storage resources, thus necessitating the use of lightweight algorithms. In this paper, we present an efficient and robust knowledge transfer network named ERKT-Net, which is designed to provide a lightweight yet accurate Convolutional Neural Network (CNN) classifier. This method utilizes innovative yet simple concepts to better accommodate the inherent nature of RSIs, thereby significantly improving the efficiency and robustness of traditional Knowledge Distillation (KD) techniques developed on ImageNet-1K. We evaluated ERKT-Net on three benchmark RSI datasets and found that it demonstrated superior accuracy and a very compact volume compared to 40 other advanced methods published between 2020 and 2023. On the most challenging NWPU45 dataset, ERKT-Net outperformed other KD-based methods with a maximum Overall Accuracy (OA) value of 22.4%. Using the same criterion, it also surpassed the first-ranked multi-model method with a minimum OA value of 0.7 but presented at least an 82% reduction in parameters. Furthermore, ablation experiments indicated that our training approach has significantly improved the efficiency and robustness of classic DA techniques. Notably, it can reduce the time expenditure in the distillation phase by at least 80%, with a slight sacrifice in accuracy. This study confirmed that a logit-based KD technique can be more efficient and effective in developing lightweight yet accurate classifiers, especially when the method is tailored to the inherent characteristics of RSIs.","PeriodicalId":502655,"journal":{"name":"EAI Endorsed Trans. Ind. Networks Intell. Syst.","volume":"53 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141683022","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

Resource-Efficient Deep Learning: Fast Hand Gestures on Microcontrollers 资源节约型深度学习：微控制器上的快速手势

EAI Endorsed Trans. Ind. Networks Intell. Syst. Pub Date : 2024-07-03 DOI: 10.4108/eetinis.v11i3.5616

Tuan Kiet Tran Mach, Khai Nguyen Van, Minhhuy Le

{"title":"Resource-Efficient Deep Learning: Fast Hand Gestures on Microcontrollers","authors":"Tuan Kiet Tran Mach, Khai Nguyen Van, Minhhuy Le","doi":"10.4108/eetinis.v11i3.5616","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.5616","url":null,"abstract":"Hand gesture recognition using a camera provides an intuitive and promising means of human-computer interaction and allows operators to execute commands and control machines with simple gestures. Research in hand gesture recognition-based control systems has garnered significant attention, yet the deploying of microcontrollers into this domain remains relatively insignificant. In this study, we propose a novel approach utilizing micro-hand gesture recognition built on micro-bottleneck Residual and micro-bottleneck Conv blocks. Our proposed model, comprises only 42K parameters, is optimized for size to facilitate seamless operation on resource-constrained hardware. Benchmarking conducted on STM32 microcontrollers showcases remarkable efficiency, with the model achieving an average prediction time of just 269ms, marking a 7× faster over the state-of-art model. Notably, despite its compact size and enhanced speed, our model maintains competitive performance result, achieving an accuracy of 99.6% on the ASL dataset and 92% on OUHANDS dataset. These findings underscore the potential for deploying advanced control methods on compact, cost-effective devices, presenting promising avenues for future research and industrial applications.","PeriodicalId":502655,"journal":{"name":"EAI Endorsed Trans. Ind. Networks Intell. Syst.","volume":" 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141680973","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

Machine Learning in Cybersecurity: Advanced Detection and Classification Techniques for Network Traffic Environments 网络安全中的机器学习：网络流量环境的高级检测和分类技术

EAI Endorsed Trans. Ind. Networks Intell. Syst. Pub Date : 2024-07-01 DOI: 10.4108/eetinis.v11i3.5237

Samer El Hajj Hassan, Nghia Duong-Trung

{"title":"Machine Learning in Cybersecurity: Advanced Detection and Classification Techniques for Network Traffic Environments","authors":"Samer El Hajj Hassan, Nghia Duong-Trung","doi":"10.4108/eetinis.v11i3.5237","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.5237","url":null,"abstract":"In the digital age, the integrity of business operations and the smoothness of their execution heavily depend on cybersecurity and network efficiency. The need for robust solutions to prevent cyber threats and enhance network functionality has never been more critical. This research aims to utilize machine learning (ML) techniques for the meticulous analysis of network traffic, with the dual goals of detecting anomalies and categorizing network activities to bolster security and performance. Employing a detailed methodology, this study begins with data preparation and progresses through to the deployment of advanced ML models, including logistic regression, decision trees, and ensemble learning techniques. This approach ensures the accuracy of the analysis and facilitates a nuanced understanding of network dynamics. Our findings indicate a notable enhancement in identifying network inefficiencies and in the more accurate classification of network traffic. The application of ML models significantly reduces network delays and bottlenecks by providing a strong defence strategy against cyber threats and network shortcomings, thereby improving user satisfaction, and boosting the organizational reputation as a secure and effective service layer. Conclusively, the research highlights the pivotal role of machine learning in network traffic analysis, offering innovative insights and fresh perspectives on anomaly detection and the identification of malicious activities. It lays a foundation for future explorations and acts as an evaluation benchmark in the fields of cybersecurity and network management.","PeriodicalId":502655,"journal":{"name":"EAI Endorsed Trans. Ind. Networks Intell. Syst.","volume":"268 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141692224","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

Jointly power allocation and phase shift optimization for RIS empowered downlink cellular networks 为增强 RIS 的下行链路蜂窝网络联合进行功率分配和相移优化

EAI Endorsed Trans. Ind. Networks Intell. Syst. Pub Date : 2023-12-11 DOI: 10.4108/eetinis.v10i4.4359

P. Q. Truong, Tan Do-Duy, Van-Ca Phan, Antonino Masaracchia

{"title":"Jointly power allocation and phase shift optimization for RIS empowered downlink cellular networks","authors":"P. Q. Truong, Tan Do-Duy, Van-Ca Phan, Antonino Masaracchia","doi":"10.4108/eetinis.v10i4.4359","DOIUrl":"https://doi.org/10.4108/eetinis.v10i4.4359","url":null,"abstract":"Reconfigurable Intelligent Surfaces (RIS) have been highlighted by the research community as a key enabling technology for the enhancement of next-generation wireless network performance, including energy efficiency, spectral efficiency, and network throughput. This paper investigates how RIS-assisted communication can effectively maximize the downlink throughput of a cellular network. Specifically, the paper considers a communication scenario where a single base station serves multiple ground users with the aid of an RIS placed on a building facade. For such a communication scenario, we considered an optimization problem aimed at maximizing the overall downlink throughput by jointly optimizing power allocation at the base station and phase shift of RIS reflecting elements, subject to power consumption and quality-of-service constraints. To address its non-convex nature, the original optimization problem has been divided into two subproblems. The first one, for power control with fixed phase shift values, is a convex problem that can be easily solved. Subsequently, a phase shift searching procedure to solve the non-convex problem of RIS phase shift optimization has been adopted. The results from numerical simulations show that the proposed method outperforms other conventional methods proposed in the literature. In addition, computational complexity analysis has been conducted to prove the low complexity of the proposed method.","PeriodicalId":502655,"journal":{"name":"EAI Endorsed Trans. Ind. Networks Intell. Syst.","volume":"42 5-6","pages":"4"},"PeriodicalIF":0.0,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184181","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