检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Batool Mohammed Radhi Mohammed Abdulridha Hussain Zaid Ameen Abduljabbar Vincent Omollo Nyangaresi Department of Computer Science College of Education for Pure Sciences University of Basrah Basrah Iraq Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and Technology Bondo Kenya

The proliferation of the internet of things (IoT) has led to the emergence of a wide range of intelligent devices, creating a broad domain with significant security concerns. These concerns impose a high level of security; unfortunately, IoT devices usually have limited resources in terms of little memory, low computing power, and a short battery life. Therefore, IoT application developers must use lightweight cryptographic tools to achieve a trade-off between performance and security. The storage and high computation capacity of cloud computing is often exploited to manage the vast amount of data produced by such gadgets. Some methods still suffer from attacks, and others cannot achieve low complexity. We propose a secure and low-complexity system for smart buildings in transferring data between the local server, the cloud, and users authorized by the owner. The LED encryption algorithm, which is lightweight and requires limited resources and less energy, was used to create a mobile application system characterized by confidentiality, authentication, and privacy. For further security, the owner's biometrics were used and derived as the key to decrypt data from the cloud. We have leveraged Dragonfly authentication technology to transfer data from the local server to the users. The owner can add authorized persons in the cloud database and local server to enjoy using the application. Moreover, we successfully balance security complexity and performance in our work. As a result, we achieve good results with a computation cost of 0.281 s and a communication cost of 1472 $bit$ .

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Transformer Topology for Distribution Networks

A New Hybrid Transformer Topology for Distribution Networks

引用

Annual Conference of Industrial Electronics Society

作者： Rupert Power Udaya Madawala Craig Baguley Bingkun Song Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand Department of Engineering Computing and Mathematical Sciences Auckland University of Technology Auckland New Zealand

The widespread integration of Distributed Generation (DG) and new loads such as Electric Vehicles (EVs) into power distribution networks presents substantial technical challenges for network operators, such as voltage fluctuations and phase unbalance. These can be addressed by many power electronic devices with advanced control strategies, including the Hybrid Transformer (HT). This paper presents a new three-phase HT concept which can perform multiple functions, including voltage regulation and voltage balancing, to address power quality problems in distribution networks. Theory and control strategy are presented, along with simulated results incorporating an unbalance-tolerant control scheme and 3D Space Vector Modulation, to demonstrate the validity of the proposed HT topology. Its advantages include being retrofittable to existing distribution transformers, not requiring bulky low-frequency converter magnetics, having a low semiconductor component count, and allowing reduced DC-link capacitances. This makes it cost-effective, compact and light weight in comparison to the existing topologies that provide similar functionality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Networks and Deep Learning: Innovations and Applications in Soft Computing

Neural Networks and Deep Learning: Innovations and Applicati...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Jahagirdar Imran Abdulkadar Chinnem Rama Mohan P. Vijaya Bharati Shamik Palit Gunda Srinivasa Rao Pankaj Mudholkar Computer Application Savitribai Phule Pune University Department of Computer Science and Engineering Narayana Engineering College Nellore Andhra Pradesh India Department of CSE Vignans Institute of Engineering for Women Visakhapatnam Andhra Pradesh India Department of Computing Science and Software Engineering University of Stirling RAK Campus UAE School of Management and Commerce Mallareddy University Kompally Faculty of Computer Applications Marwadi University Rajkot Gujarat India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

The Paper explores different aspects of deep learning techniques and neural networks in the fields of healthcare, time-series forecasting, agriculture, and other relevant sectors through soft computing. The objective of the report is to examine the significant potential and applications of neural networks. While machine learning techniques called neural networks (NN) are utilized for audio, picture, and the processing of natural languages, it has huge implications in robotics where several machine learning algorithms are significantly required. Improvements in deep machine learning are also investigated in the article specifically in the fields of drug construction, genetics, recognizing faces, farming, biological medicine, biological informatics, medical treatment, natural language, multimedia analysis of data, and mobility prediction. However black box challenges and privacy concerns with data are often ignored in this research. The paper also outlines deep learning-driven data mining techniques for precisely predicting, displaying, evaluating, and classifying data. The report has also emphasized on addressing the potential privacy concerns and challenges associated to information representation. By reviewing recent literature sources about neural network techniques, the study proposes innovation strategies and potential improvement areas for the development of advanced technologies like deep learning and neural networks while addressing the key privacy concerns in data processing.

关键词： Deep learning Technological innovation Data privacy Privacy Natural languages Process control Real-time systems Informatics Biological neural networks Robots

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blockchain Technology Education with Innovative Active Learning 2

Enhancing Blockchain Technology Education with Innovative Ac...

引用

2nd IEEE International Conference on Advanced Learning Technologies on Education and Research, ICALTER 2022

作者： Shi, Yong Shahriar, Hossain Lo, Dan Chi, Hongmei College of Computing and Software Engineering Kennesaw State University Marietta United States Florida A&m University Department of Computer and Information Sciences TallahasseeFL United States

ISBN: (数字)9781665456968

ISBN: (纸本)9781665456968

As an emerging technology that has already impacted various sectors including finance, energy, education, and more, blockchain provides a decentralized ledger system that ensures the integrity of the recorded transactions. With its wide application comes the huge demand for blockchain researchers and engineers, however, most schools have not offered courses related to blockchain research and development. To fill the gap between the increasing needs for blockchain professionals and shortage of blockchain curriculum, we propose a portable labware that covers the complete cycle of blockchain development. In this labware we apply active learning strategies to engage students in learning the blockchain knowledge more efficiently and effectively. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

AdaptVR: An Adaptive Learning VR System for Dental Students Training

AdaptVR: An Adaptive Learning VR System for Dental Students ...

引用

International Conference on computer and Applications (ICCA)

作者： Meriam Sherif Nahla Barakat Abeer Hamdy Department of Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt Department of Artificial Intelligence Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

The paper proposes “AdaptVR” a virtual reality (VR) system designed to enhance dental training through realistic real tile simulations and adaptive learning environment, to overcome traditional training challenges in dental education. The system aims to provide personalized learning experiences, facilitating skill development and comprehensive assessments for students. The proposed system was tested by 17 dentistry students and 5 experts. AdaptVR framework is done for operative dentistry which is removing decay especially Class I and Class II of classification of caries. Results from the experiment revealed that 77.3% of participants exceed their expectations, 59.1% saw a positive effect on their dental skills, 90.9% reported higher levels of engagement, and 65% indicated that vibration and force feedback provided students with a genuine sensation. AdpatVR's experimental findings show an average accuracy of 50.85% for Class I, 51.7% for Class II, and 82.09% for the Class II box technique. The error percentage averages 49% for Class I, 48% for Class II, and 18% for Class II box technique.

关键词： Training Vibrations Drilling Solid modeling Adaptive learning Adaptation models Force feedback Virtual reality Teeth Dentistry

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-ONU Customers Access Network using Spectrum Slicing and Duplication Techniques 5

Performance Evaluation of Multi-ONU Customers Access Network...

引用

5th International Conference on Emerging Electrical Energy, Electronics and Computing Technologies, ICE4CT 2024

作者： Rahman, Juwairiyyah Abdul Mugunthan, Sivaguru A.L. Hassan, Hasliza Abu Muslim, Norliana Ab-Rahman, Mohammad Syuhaimi Department of Electrical Engineering Faculty of Engineering and Life Sciences Universiti Selangor Selangor Bestari Jaya45600 Malaysia Department of Computer and Communication Technology Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar31900 Malaysia Department of Electrical Electronics and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Malaysia Electrical and Computer Engineering Program Faculty of Engineering Sohar University PC:311 Sohar Oman

This study aims to increase the number of access users by limiting the sample size to 30 users while ensuring that every Optical Network Unit (ONU) receives data from the Optical Line Terminal (OLT). The proposed solution allows for the determination of power requirements at each ONU based on bus-star topologies, facilitating an increase in user capacity. The power received by each ONU is a critical parameter that system designers must consider when planning the implementation of Fiber to the Home (FTTH), as it impacts the output data in terms of Bit Error Rate (BER) and Signal Quality Factor (QF) for each user. Various parameters were evaluated to ensure that the enhanced network improves scalability while adhering to standard specifications. These parameters included the Q-factor, BER, eye diagram, user count, and received power. The study employed slicing and duplication techniques, utilizing Arrayed Waveguide Grating (AWG) for signal duplication and Wavelength Division Multiplexing for signal slicing. The simulations were conducted using a transmitter operating at a frequency of 1491 nm with a power output of 0 dBm, utilizing the latest version of OptiSystem 20 software. The results highlighted the system's capability to support a total of 73,728 users, meeting stringent performance criteria. Specifically, the system achieved a Q-factor greater than 6, indicating high signal quality, and a bit error rate (BER) lower than 1 × 10-9, ensuring reliable data transmission. For the sampled 30 users, the average Q factor was 8.1527, and the average BER was 5.3648 × 10^-11, with an output power level of -54.278 dBm. Despite an increase in users, the quality of the data supplied to clients remained unchanged. These outcomes underscore the robustness and efficiency of the design in delivering high-capacity, error-resilient optical communication. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

FINE-TUNING TRANSFER LEARNING MODEL IN WOVEN FABRIC PATTERN CLASSIFICATION

引用

International Journal of Innovative Computing, Information and Control 2022年第6期18卷 1885-1894页

作者： Noprisson, Handrie Ermatita, Ermatita Abdiansah, Abdiansah Ayumi, Vina Purba, Mariana Setiawan, Hadiguna Program of Doctoral Program in Engineering Universitas Sriwijaya Jalan Raya Prabumulih-Inderalaya Palembang30128 Indonesia Faculty of Computer Science Universitas Sriwijaya Jalan Raya Prabumulih-Inderalaya Palembang30128 Indonesia Department of Research and Development Stikhafi Academy Jalan Timur Indah Raya Bengkulu38225 Indonesia

It is important to figure out the patterns of woven fabrics before producing woven fabric with a machine. Recognition of woven fabric pattern usually with the help of the human eye can understand the fabric pattern. However, this manual checking takes a lot of time, money, and work, which will raise the cost of making woven fabrics. This study uses the VGG16, VGG19, MobileNet, and Inception-V3 methods to classify woven fabric patterns. It also wants to see how fine-tuning method can help algorithms be more accurate at classifying images. The research was divided into four phases, including image acquisition, image preprocessing, image classification and evaluation. A total of 978 pictures of motifs included in the research dataset. There are 351 images for the cotton class, 76 images for linen, 195 images for silk, and 356 images for wool. As the result, the highest testing accuracy was in the Inception-V3 experiment (with fine-tuning) of 72.51%, and the lowest was in the VGG19 experiment (with fine-tuning) of 52.92%. © 2022 ICIC International.

关键词： Weaving

来源：评论

学校读者我要写书评

暂无评论

Progressive Representation Learning for Real-Time UAV Tracking

arXiv

引用

arXiv 2024年

作者： Fu, Changhong Lei, Xiang Zuo, Haobo Yao, Liangliang Zheng, Guangze Pan, Jia The School of Mechanical Engineering Tongji University Shanghai201804 China The School of Software Engineering Tongji University Shanghai201804 China The Department of Computer Science The University of Hong Kong Hong Kong

Visual object tracking has significantly promoted autonomous applications for unmanned aerial vehicles (UAVs). However, learning robust object representations for UAV tracking is especially challenging in complex dynamic environments, when confronted with aspect ratio change and occlusion. These challenges severely alter the original information of the object. To handle the above issues, this work proposes a novel progressive representation learning framework for UAV tracking, i.e., PRL-Track. Specifically, PRL-Track is divided into coarse representation learning and fine representation learning. For coarse representation learning, two innovative regulators, which rely on appearance and semantic information, are designed to mitigate appearance interference and capture semantic information. Furthermore, for fine representation learning, a new hierarchical modeling generator is developed to intertwine coarse object representations. Exhaustive experiments demonstrate that the proposed PRL-Track delivers exceptional performance on three authoritative UAV tracking benchmarks. Real-world tests indicate that the proposed PRL-Track realizes superior tracking performance with 42.6 frames per second on the typical UAV platform equipped with an edge smart camera. The code, model, and demo videos are available at https://***/vision4robotics/PRL-Track. Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Scheme for Image-Text Comments Based on Multimodal Deep Learning and Spatiotemporal Attention

Sentiment Analysis Scheme for Image-Text Comments Based on M...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Fanchang TangYa Ling Amit Yadav Abhishek Pratap Sah Asif Khan Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

A sentiment analysis scheme for image and text comments based on multimodal deep learning and spatiotemporal attention is proposed to address the issues of incomplete spatiotemporal considerations, incomplete implementation details, and cutting-edge theoretical algorithms in graphic and textual sentiment analysis schemes. The proposed model has clear layering including data preprocessing layer, modal encoding layer, modal fusion layer, sentiment classification layer, loss function and optimizer, evaluation and feedback. The implementation details of each layer are introduced. The entire scheme model incorporates Multimodal Fusion Neural Network (MFNN) deep learning and spatiotemporal attention mechanism, which makes the scheme perform well in terms of security, robustness and performance, making up for the shortcomings of existing research schemes.

关键词： Deep learning Sentiment analysis Neural networks Data preprocessing Encoding Robustness Spatiotemporal phenomena Security Informatics Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Online Sexism Detection and Classification by Injecting User Gender Information

Online Sexism Detection and Classification by Injecting User...

引用

Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), IEEE International Conference on

作者： Amit Das Mostafa Rahgouy Zheng Zhang Tathagata Bhattacharya Gerry Dozier Cheryl D. Seals Department of Computer Science & Software Engineering Auburn University Auburn AL USA Department of Computer Science Auburn University at Montgomery Montgomery AL USA

This paper investigates the potential effects that user gender information has on online sexism detection, in terms of both binary and multi class detection. Social media has recently developed into a center for sexist posts that target especially women. Since most sexist comments are made especially against people of a particular gender, whether the gender information of the users could be effective or not for sexism detection, is still an important question. Here we try to address this issue using Natural Language Processing (NLP) and machine learning models. Experiments showed that combining user gender information with textual features improved classification performance both in terms of binary classification and multi class classification. The effectiveness of the proposed strategy is demonstrated by the experimental results reported in this research.

关键词：

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：