检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mandal, Kavita Pandey, Manish Singh, Dhirendra Pratap Kumar, Lalit Maulana Azad National Institute of Technology Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350370249

Electromagnetic optimization problems entail the fine tuning of electromagnetic systems across various domains. In many applications such as antenna design, microwave circuits, and metamaterial configuration, a large number of parameters must be finely tuned to achieve the desired device functionality. Given the complexity of real systems, analytical solutions are often unavailable, making the computational cost of a single analysis prohibitive. Therefore, an effective and flexible design strategy is crucial. This paper investigates the application of electromagnetic (EM) simulators in ML and DL for antenna configuration within electromagnetic optimization challenges. Various optimization strategies are reviewed in this work based on literature from comprehensive searches in IEEE Transactions and IEEE Access. From 24 identified studies, 8 key studies were selected to illustrate recent research trends, challenges, and opportunities in optimizing antenna design. Additionally, the paper introduces a novel deep learning approach for addressing electromagnetic problems in antenna design. © 2024 IEEE.

关键词： Metamaterial antennas

来源：评论

学校读者我要写书评

暂无评论

Virtual dressing room using Deep learning 2

Virtual dressing room using Deep learning

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Kurtakoti, Sangareddy B. Kavana, V. Manasa, T.Y. Mayuk Gowda, A. Shashank, C.B. Department of Computer Science and Engineering Adichunchanagiri Institute of Technology Karnataka Chikkamagaluru India

ISBN: (纸本)9798350383867

Clients Fashion in the twenty-first century has become intertwined with daily life, varying based on factors like physical stature, gender, and social context. Despite the rise of online shopping, the traditional in-store experience remains dominant, but challenges like limited fitting roomsand privacy concerns persist. To address this, our aim is to develop a highly realistic virtual dressing system, leveraging deep learning techniques, particularly Generative Adversarial Networks (GAN). This system predicts the semantic layout of areference image, determines whether to generate or preserve image content accordingly, resulting in lifelike try-on experiences. Through virtual reality, customers can explore a wide array of clothing items without physically wearing them, saving time and effort. Moreover, retailers stand to benefit by streamlining inventory management and conserving space. ©2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Prototype Matching with Domain Alignment for Open-world Specific Emitter Identification

Prototype Matching with Domain Alignment for Open-world Spec...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xiao, Wang Ye, Yalan Pan, Tongjie Li, Chenyang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

Open-world specific emitter identification (SEI) is a practical but challenging task, because it requires accurate identification of both known and unknown emitters in open environments with channel variations. However, traditional closed-set SEI methods suffer from severe performance degradation in open-world environments since 1) closed-set SEI models would misclassify unknown specific emitters (SEs) as known ones, and 2) channel variations would lead to distribution shifts in the radio frequency (RF) fingerprint of known SEs. It is challenging to address both issues, as they coexist and interact with each other. In this paper, we propose a novel prototype matching with domain alignment framework for open-world SEI, which designed to simultaneously address the challenges of unknown SE identification and channel variation. The proposed framework first pretrains a feature extractor and then trains the pretrained feature extractor and an extended open-set classifier via the self-training paradigm. Towards the former, a partial domain alignment strategy is introduced to mitigate the impact of channel variations. Towards the latter, a prototype matching-based pseudo-labeling strategy is proposed to generate reliable pseudo-labels, facilitating subsequent fine-grained identification of unknown SEs. An open-set classification loss is introduced later to help the classifier avoid classifying unknown SEs as known ones. Experiments conducted on a public WiFi dataset demonstrate the superiority and robustness of the proposed method, illustrating its potential application prospects in open-world environments. © 2025 IEEE.

关键词： open-set recognition prototype learning self-training specific emitter identification unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Velocity Powered Sprint: Gesture Controlled Car Racing Game 2

Velocity Powered Sprint: Gesture Controlled Car Racing Game

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Mamatha Bai, B.G. Singh, Priyanshu Pramod Tuttagunta, Sowmya Goutam, Vachaspati Nitte Meenakshi Institute of Technology Computer Science and Engineering Karnataka Benguluru India

ISBN: (纸本)9798350372892

An innovative real-time car racing game controlled by hand gestures is introduced, employing OpenCV and advanced AI techniques. The primary goal is to offer players an immersive gaming experience by allowing them to steer a virtual car along a racing track using intuitive hand movements. The system utilizes OpenCV's computer vision algorithms, analyzing live video feeds from a webcam to instantly detect and interpret hand gestures. These gestures, including commands like 'move forward,' 'move backward,' 'turn left,' and 'turn right,' act as input signals for directing the car within the game. To enhance gesture recognition accuracy, AI methods are integrated, training a model with machine learning algorithms such as Convolutional Neural Networks (CNNs) to precisely categorize various hand gestures. The identified gestures are then translated into control signals for the virtual car, resulting in a seamless and captivating gaming experience. Featuring visually stunning graphics, challenging racecourses, and competitive adversaries, this project exemplifies the synergy of computer vision, AI, and gaming technologies, offering a user-friendly and immersive hand gesture-controlled car racing game. It not only provides entertainment but also opens up avenues for potential applications in gaming, virtual reality, and human-computer interaction. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection Using Deep Learning

Diabetic Retinopathy Detection Using Deep Learning

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Keerthi, B. Powmika, K Kalai Narendra, Pranudev Karthik, N. National Institute of Technology Puducherry Department of Computer Science and Engineering Karaikal India

ISBN: (纸本)9798331540685

- In this research, we present DRNet, a deep learning model for automated detection and grading of diabetic retinopathy (DR) using fundus images. DR is a leading cause of vision loss in diabetic individuals, emphasizing the importance of early detection. Our model combines the ResNet architecture for feature extraction with the U-Net architecture for lesion segmentation. Trained on a large dataset of 666,383 fundus images from 121,342 diabetic patients, DRNet incorporates realtime image quality assessment, lesion detection, and grading of DR severity. Evaluation on both local and external datasets, totaling 409,455 images, demonstrates the effectiveness of DRNet, achieving an area under the receiver operating characteristic curves (AUC) of 0.90-0.936 for lesion detection and 0.96-0.98 for DR severity grading. Our results suggest that DRNet has the potential to enhance DR screening programs by improving accuracy and efficiency in diagnosis, thereby benefiting patient outcomes and healthcare systems. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Leukemia Classification using Multi-Neural Networks 1

A Novel Approach for Leukemia Classification using Multi-Neu...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Kumar, J Senthil Ramalakshmi, B. KIT-Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350372748

Leukemia is a type of cancer that originates in the bone marrow and affects the blood-forming cells. These abnormal cells, typically white blood cells, multiply uncontrollably, hindering the production of normal blood cells. Because of its various genetic and molecular properties, leukemia, a complex and heterogeneous group of blood malignancies, provides major hurdles in correct subtype categorization. Traditional categorization approaches often fail to reflect the complexities of leukemia subgroups. In this paper, this research offer the Multi-Neural Network (MNN), a ground-breaking strategy for addressing these difficulties by exploiting hierarchical information and merging specialized neural networks. The dataset was collected from Kaggle repository. After collecting dataset this research use Non adaptive threshold for Image denoising. After denoising, this research use Adam optimization algorithm for optimization process. After optimization this research use HOG algorithm for feature selection. The proposed MNN architecture is made up of a unique collection of neural networks, each adapted to a certain hierarchical level of leukemia subtypes. An Improved Convolutional Neural Network (CNN), a DenseNet, and an improved VGG19 are among the specialized networks. These networks are painstakingly developed to extract distinguishing information from leukemia cell pictures, enhancing classification accuracy. This research uses the cross-entropy loss function in combination with the Adam optimization approach to improve the performance of our MNN even more. This combination improves the training process, allowing our MNN to discover complex patterns and correlations from the leukemia dataset. © 2024 IEEE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Smart Metro Railway Ticketing System

Smart Metro Railway Ticketing System

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Nandini, N.S. Bhoomika, N. Lavanya, K.V. Monika, H.L. Suchithra, H.M. Bgs Institute of Technology Computer Science and Engineering Karnataka BG Nagara India

ISBN: (纸本)9798350359688

In one's life, transportation is vital. The primary objective of this paper is to dispose of dailyand massive troubles related to sporting a price ticket while touring and to promote a more tranquil journey enjoy. For this purpose, however no longer exclusively within the context of metro railways, we are suggesting a biometric-based totally to the ticketing system. When registering, purchasing tickets, and authenticating the fingerprint at the day of journey, we recollect everyone's fingerprint to create a completely unique identification. This lets in her or him to travel to their desired area on a sure day and on the desired teach. An Arduino interface can be created using the fingerprint sensor, and this. © 2024 IEEE.

关键词： Subways

来源：评论

学校读者我要写书评

暂无评论

BERT based Citation Recommender and Impactful Nodes Identifier in RDF Knowledge Graphs 4

BERT based Citation Recommender and Impactful Nodes Identifi...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Vaidhyaraman, Raghavan Sharon Jessika, S. Sahaaya Arul Mary, S.A. School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

ISBN: (纸本)9798331515720

Knowledge graphs have emerged as powerful tools for representing and organizing information in a structured and interconnected manner. In this research, we aim to build a knowledge graph and a recommendation system for research papers. This research is divided into three parts: Charting the Research Progress (constructing the RDF knowledge graph and visualizing), The Search for Knowledge (making a research paper recommender system), and revealing the Trailblazers (finding the most impactful paper in the dataset). By leveraging state-of-The-Art tools and models, the knowledge graph was not only accurate but also visually intuitive, offering insights into the complex web of academic interrelations. The recommender system, built on this knowledge base, demonstrated high efficacy in suggesting relevant and significant research papers, with its recommendations being both contextually and academically pertinent. The impact analysis reveals the most influential papers, providing a clear view of research works that have shaped and directed academic discourse in their respective fields. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Developing Lexicons for Enhanced Sentiment Analysis in Software engineering:An Innovative Multilingual Approach for Social Media Reviews

引用

computers, Materials & Continua 2024年第5期79卷 2771-2793页

作者： Zohaib Ahmad Khan Yuanqing Xia Ahmed Khan Muhammad Sadiq Mahmood Alam Fuad AAwwad Emad A.A.Ismail School of Automation Beijing Institute of TechnologyBeijing100081China Department of Computer Science and Technology University of Science and Technology BannuKPKBannu28100Pakistan School of Computer Science and Engineering Central South UniversityChangsha410083China Department of Quantitative Analysis College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh11587Saudi Arabia

Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.

关键词： Emotional assessment regional dialects SentiWordNet naive bayesian technique lexicons software engineering user feedback

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Cataract Infected Eyes and Normal Eyes using Convolutional Neural Network 4

Deep Learning-based Classification of Cataract Infected Eyes...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Ashitha Sandrin, A. Denisha, M. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385793

Cataract, a common eye disease characterized by clouding of the natural lens of the eye, is a serious threat to visual health. If left untreated, they can lead to blurred vision and even blindness, underscoring the importance of timely intervention. To address the urgent need for accurate cataract diagnosis, this study provides an improved approach using convolutional neural networks (CNN) to distinguish cataract eyes from eyes with normal vision. Because cataracts are the most common cause of visual impairment worldwide, recognition and accurate classification are critical for prompt intervention and mitigation of potential harms. Taking advantage of recent advances in deep learning, especially CNNs, this method introduces a new feature extraction technique that uses hyperparameter optimization. The systematic exploration of the hyperparameter space determines the optimal configuration that maximizes the efficiency of the classification algorithm to distinguish cataract from normal eyes. Experimental validation on a comprehensive fundus image dataset demonstrates the effectiveness of this approach, achieving robust performance and high classification accuracy. A deep learning approach with optimization techniques will improve the efficiency and accuracy of cataract diagnosis, offering promising solutions to alleviate the global burden of vision loss and blindness. © 2024 IEEE.

关键词： Convolutional neural networks

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：