检索结果-内蒙古大学图书馆

9th International Conference on Integrated Circuits and Microsystems, ICICM 2024

作者： Chen, Zhikang Zhang, Yuejun Ren, Mingze Xia, Donghao Wang, Pengjun Zhang, Huihong Wen, Liang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China College of Electrical and Electronic Engineering Wenzhou University Wenzhou China China Coast Guard Academy Department of Electronic Technology Ningbo China

ISBN: (纸本)9798331509453

With the rise of the Internet of Things, smart healthcare with remote monitoring and diagnosis enables patients to reduce the number and duration of hospitalizations, thereby reducing the pressure on doctors. However, the transmission data of disease detection chips is susceptible to cache attacks, leading to user health data leakage. Hardware level encryption design has become a research hotspot. Firstly, by adding a Mask channel at the upper level of each convolution layer, the preprocessed data is transmitted simultaneously with the obfuscated data, and the channel exchange during transmission is utilized to protect user privacy;Secondly, there is a redundancy mechanism between the input matrix and weight matrix of the storage module, and invalid values are added to the redundant parts to prevent cache attacks from stealing user information;Finally, add multi temporal obfuscation to the first input data to achieve the different lengths between the first and subsequent data. The protection circuit designed in this article achieves user privacy protection on the basis of only increasing hardware overhead by 2.5%, power consumption overhead by 3.61%, and not affecting disease monitoring accuracy. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Does the Height Matter? A Case for Wi-Fi based Wireless Positioning System

Does the Height Matter? A Case for Wi-Fi based Wireless Posi...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Ismail, Abdul Halim Sunang, Godrey Amos Azmi, Muhamad Safwan Muhamad Ayob, Mohd Nasir Hashim, Mohd Sani Mohamad Basri, Hassrizal Hassan Widyasmoro, Widyasmoro Ismail, Mohd Muzafar Mechatronic Faculty of Electrical Engineering & Technology Perlis Arau Malaysia Mechanical Faculty of Mechanical Engineering & Technology Perlis Arau Malaysia Faculty of Electrical Engineering Yogyakarta Bantul Indonesia Faculty of Technology and Engineering Electronic and Computer Hang Tuah Jaya Durian Tunggal Melaka Malaysia

ISBN: (纸本)9798350382914

Wireless Positioning System (WPS) is an emerging field rises with the aim to minimize the development and algorithm cost as well as applicable in many applications. The methods are rather straightforward compared to the use of conventional on-board sensing elements that often require fusion of several sensors as well as complex algorithms. Wireless Fidelity (Wi-Fi) is the choice of elements in WPS due to wide availability as well as use of existing infrastructure. One interesting factor to consider in obtaining higher positioning accuracy is to assess the Wi-Fi height level. Many previous studies proposed optimization of the Wi-Fi antenna heights, but our direction is towards experimental works to observe if the antenna heights does matter or is it a totally insignificant parameter. Three different analyses were conducted on the data, which are statistical, two-layer average and quotient calculations. The results are validated for our experiments heights from 0.5 to 2.0 meter. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of 5G IoT for Retirement Village in Metaverse 5

Design and Implementation of 5G IoT for Retirement Village i...

引用

5th Research, Invention, and Innovation Congress: Innovative Electricals and electronics, RI2C 2024

作者： Vanichchanunt, Pisit Saengthongkam, Sirapop Waichampa, Natthapong Wuttiananchai, Navy Janthong, Bancha Swatdipisal, Khatathap Sittakul, Vitawat Wuttisittikulkij, Lunchakorn Paripurana, Sukritta King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand King Mongkut's University of Technology North Bangkok College of Industrial Technology Department of Electronic Engineering Technology Bangkok Thailand Chulalongkorn University Faculty of Engineering Department of Electrical Engineering Bangkok Thailand

ISBN: (纸本)9798331505998

This paper proposes the use of metaverse in the design, implementation, and pretest of 5G IoT systems for smart cities, in which this paper, a retirement village is selected as a preliminary example for the demonstration. Metaverse not only enables the system design and integration under multidisciplinary considerations including electrical system, solar energy system, 5G IoT system, communication, and automation, to be carried out economically but the system functionalities can also be carefully tested under various scenarios due to less limitation in the virtual world. The developed 5G IoT system for the retirement village monitors electrical power usage, solar power generation and consumption, air pollution, and environmental status. Moreover, the developed system also allows users to directly control lights and CCTV cameras using dashboards. To support various demands of such IoT services, the 5G network slice templates are designed and prepared according to the service requirements. In the system test, the monitoring data is shown on the dashboards to confirm the system connections and functionalities. Besides, wireless CCTV cameras via the developed 5G IoT systems are tested and compared between the virtual video in metaverse and the actual video from the real world. The results of both cases reveal no significant difference in terms of video quality degradation and latency. This shows the benefits and potentials of using metaverse in the design, implementation, and testing especially the system integration. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study of Diverse Models and Datasets for Transfer Learning based Image Classification on Sparse Data 10

An Exploratory Study of Diverse Models and Datasets for Tran...

引用

10th International Multidisciplinary engineering Research Conference on Moratuwa engineering Research, MERCon 2024

作者： Pathmarasa, Jathurshan Wijenayake, Udaya Wijesinghe, Ruchire Eranga Silva, Bhagya Nathali University of Sri Jayewardenepura Faculty of Engineering Department of Computer Engineering Nugegoda Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798331529048

Transfer learning is a powerful technique for image classification, especially when dealing with limited data. However, selection of the best transfer learning approach and model remains challenging, since the strategy is highly influenced by the scenario. This work conducted a thorough analysis of four transfer learning approaches for binary classification, and multiclass classification using four pretrained models i.e. MobileNetV2, MobileNetV3Large, EfficientNetB0, and EfficientNetB5. The test accuracy was measured with respect to the sample size considering the effects of data augmentation and fine tuning. The key finding of the study revealed that data augmentation has improved the test accuracy by up to 11.8%. Moreover, the lightweight models marked a breakthrough by outperforming large scale models' accuracy for sparse data settings when fine tuning (FT) and data augmentation (DA) are applied appropriately. Hence, this work provides a comprehensive overview on selecting different transfer learning approaches for sparse data classification by exploring diverse models and datasets, while discussing the consequences and challenges for future real-world applications. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

CARA: A Hybrid Framework Integrating Swarm AI Agents and Knowledge Graphs for Advanced LLM Reasoning 6

CARA: A Hybrid Framework Integrating Swarm AI Agents and Kno...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Pussadeniya, Nirodya Wijesinghe, Ruchira Wijenayake, Udaya Silva, Bhagya University of Sri Jayewardenepura Faculty of Engineering Department of Computer Engineering Nugegoda Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798331517878

Language models excel in linguistic processing but often face challenges with complex reasoning tasks that require real-world interaction and multi-step logic. This paper presents the Cognitive Adaptive Reasoning Architecture (CARA), a framework that enhances reasoning by integrating a modular swarm architecture with knowledge graphs (KGs) and specialized agents. These agents, equipped with diverse tools, dynamically adapt to various tasks, actively engaging with real-world data. CARA's continuous memory update cycle ensures each reasoning step is based on up-to-date, contextual KG knowledge, enhancing decision-making. Incorporating human insights further aligns outcomes with nuanced cognition. Experimental results demonstrate CARA's superior performance over larger models, advancing language models' reasoning capabilities for more context-aware, informed decision-making in dynamic environments. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

High-Efficiency Asymmetrically Designed Three-Phase Virtual 48-Pulse Power Supply for Electrolytic Hydrogen

引用

IEEE Transactions on Power electronics 2025年第8期40卷 10335-10342页

作者： Tian, Hanlei Cui, Haoran Han, Wei Sathik M, Jagabar Liang, Guozhuang Chen, Maolin Mekhilef, Saad Electrical Engineering School of Hebei University of Science and Technology Shijiazhuang050091 China Sustainable Energy and Environment Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong SRM Institute of Science and Technology Faculty of Engineering and Technology Kattankulathur603203 India Sichuan University College of Electrical Engineering Chengdu610065 China Swinburne University of Technology School of Science Computing and Engineering Technologies MelbourneVIC3122 Australia

To address the low-voltage, high-current requirements in hydrogen production applications, a virtual 48-pulse three-phase rectifier is proposed, and achieves the equivalent performance of four parallel 12-pulse rectifiers (12-PR). The proposed approach builds upon the conventional 12-PR design and incorporates novel asymmetric current injection units (ACIU). The ACIU is installed on the dc side of the ac-dc converter, generating a specific current at the dc link to modulate and enhance the operating modes of the 12-PR. Consequently, the 12-pulse is extended to 48, resulting in an almost sinusoidal input current with a total harmonic distortion of 3.2% and an output current with a ripple rate of 2.3%, thus significantly improving power quality. Furthermore, the asymmetric design of the current injection units eliminates the need for a phase-shifting transformer. The efficacy of the proposed rectifier for electrolytic hydrogen production is validated using a 2.2-kW experimental prototype. © 1986-2012 IEEE.

关键词： Voltage Hydrogen Rectifiers Production Windings Circuits Inductors Transformers Harmonic analysis Electrochemical processes

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Evaluation Performance of Convolutional Neural Networks-Based Vehicle Classification Systems

Enhancing the Evaluation Performance of Convolutional Neural...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Kiyindou, Michel Precieux Sunday, Samuel Enobong Hong, Zhou Huaiyin Institute of Technology Faculty of Electronic Information Engineering Huai'an City China Huaiyin Institute of Technology Foreign Expeert Workshop Huai'an Faculty of Computer Engineering Huai'an City China

ISBN: (纸本)9798350306293

The rapid advancement of artificial intelligence, particularly deep learning, has spurred its integration into diverse domains. Among these, the application of deep learning in vehicle classification stands out as a vital focus within intelligent transportation systems, road traffic planning, safety warning, and driverless driving. In this research, a comprehensive approach of CNN's evolution such as LeNet, AlexNet, and other CNN-based vehicle classification techniques are enhanced for a better performance, while also investigating R-CNN, YOLO, and related methods for vehicle detection. Evaluative datasets for these methods are highlighted. Moreover, the enhancement of the computing power of the Graphics Processing Unit (GPU) and the sharp increase in the amount of data, deep learning based on convolutional neural networks has become a research hotspot. To evaluate the accuracy and efficiency of our vehicle detection methods, RCNN and YOLO series datasets were used to evaluate these methods and an the development of CNN as the main line was introduced and use to analyze the vehicle classification methods based on LeNet, AlexNet and other CNNs. This research is pivotal for vehicle tracking, traffic management, and autonomous driving progress. In this landscape, convolutional neural networks (CNNs), self-encoder neural networks, and deep belief networks take prominence, with CNNs evolving as the most dynamic. Notably, CNN's development has led to refined vehicle classification through models like LeNet, AlexNet, VGG, and GoogLeNet. The paper concludes by outlining prospective research directions in this domain. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Healthcare Monitoring System 1

IoT-Based Healthcare Monitoring System

引用

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Hadi, Marwa Abdulrahman Al-Gaphari, Ghaleb Hamoud Al-Baltah, Ibrahim Ahmed Julian, Francisco Bacallao Al-Hadi, Ahmed Abdulrahman Department of Computer Science Faculty of Computer Science and IT Sana’a University Sana’a Yemen Department of Information Technology Faculty of Computer Science and IT Sana’a University Sana’a Yemen Faculty of Science and Engineering Al-Hikma University Sana’a Yemen Cardiac-Center Military Hospital Yemen Department of Science and Technologies Faculty of Engineering and Technology Mohamed Boudiaf University M'sila Algeria Department of Industrial Electronic and Automatic Engineering Faculty of Higher Polytechnic Technology Burgos University Burgos Spain

ISBN: (纸本)9798331533557

In an era when healthcare was becoming increasingly crucial, many developing nations, including Yemen, struggled to provide basic medical services. Nearly half of Yemen's population lacked access to adequate healthcare, with the situation being even more dire in rural and remote areas. While sectors such as industry, agriculture, and environmental science rapidly embraced technological advancements, healthcare systems in these regions lagged, with limited research addressing affordable and accessible solutions. This gap was further highlighted by the global healthcare crisis and the urgent need for innovative, cost-effective approaches. In response, this study outlined the creation and deployment of a cost-effective health monitoring system utilizing Internet of Things (IoT) technology to address these challenges. The system was designed to monitor vital signs, specifically heart rate (HR), using an Arduino Uno and ECG sensor, at a meager total cost of $27.25. It provided real-time monitoring for situations requiring immediate intervention. Power consumption tests demonstrated that the system operated efficiently, consuming between 1.061 and 1.35 watts, making it practical and affordable. Additionally, the potential integration of deep learning techniques promises to enhance the system's accuracy and efficiency. Although this study focused on IoT-based health monitoring, its potential extended beyond this, offering broader implications for future healthcare technology solutions. © 2024 IEEE.

关键词： electronic health record

来源：评论

学校读者我要写书评

暂无评论

SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

引用

IEEE Transactions on Neural Networks and Learning Systems 2023年第8期34卷 5122-5132页

作者： Huang, Shih-Chia Hoang, Quoc-Viet Le, Trung-Hieu National Taipei University of Technology Department of Electronic Engineering Taipei10608 Taiwan National Taipei University of Technology International Graduate Program in Electrical Engineering and Computer Science Taipei10608 Taiwan Hung Yen University of Technology and Education Faculty of Information Technology Hungyen 17000 Viet Nam

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Development of a Smart IOT Enabled Arduino Glove Supporting Sign Language Communication 26

Development of a Smart IOT Enabled Arduino Glove Supporting ...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Zaman, Muhammad Shahriar Victor Biswas, Richard Faculty of Science and Technology Department of Computer Science and Engineering Dhaka1229 Bangladesh Faculty of Engineering Department of Electrical and Electronic Engineering 408/1 Kuratoli Dhaka1229 Bangladesh

ISBN: (纸本)9798350359015

Deafness is an unfortunate issue of our society impairing many people. Around 3 million people in Bangladesh suffer from partial or complete deafness. One key challenge for these individuals is communicating with regular people. Various sign languages are available but very few people are knowledgeable about it. Keeping this issue in consideration this project has been developed. The smart Arduino glove allows the user to express their ideas by translating their fingerspelling as well as the gestures into comprehensible messages. The system also allows identification of common sentences by identifying simple gestures. The suggested system if applied in daily life can bring a positive change in the lives of deaf-mute individuals. © 2023 IEEE.

关键词： Accelerometer Alphabets Deaf Digits Fingerspelling Flex sensor Gesture Recognition I2C MPU-6050 Mute PAJ7620 Sign language

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：