检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramanan, S.V. Rajasekar, M. Shanmugapriya, G. Sujitha, R. Akshya, J. Choudhry, Mani Deepak P Pg Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Vsb college of Engineering Department of Computer Science and Engineering Technical Campus Coimbatore India Dr.N G.P Institute of Technology Department of Computer Science and Business Systems Coimbatore India Christ The King Engineering College Department of Information Technology Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

The ability to match features and keep track of objects in changing dynamic environments is still an important problem, particularly due to varying noise levels, diverse datasets, and high dimensional feature spaces. Euclidean Distance and Cosine Similarity based matching are existing methods that commonly do not generalize well, particularly in the case of cross domain scenarios, where noise and motion dynamics are powerful factors to limit the accuracy of tracking. However, Deep Metric Learning approaches can extract robust features at the cost of computational efficiency and are unsuitable for real-time applications. This research proposes a Siamese Network framework to solve these problems by using robust feature matching and multi-object tracking. Based on that, the proposed framework uses a dual-branch network architecture in which feature embeddings extracted from paired inputs are mapped through the same shared latent space. Furthermore, the adaptive learning rate leads to efficient convergence during the training. Experimental results show that the Siamese Network not only achieves better accuracy than the existing methods and the more such as Deep Metric Learning but also performs significantly more efficient computation. With an accuracy of 90.2 % at a precision of 88.5%, the framework's inference time is much faster than that of Deep Metric Learning at 2.0ms. Furthermore, the proposed method performs well on the generalization over datasets with a 15% improvement of cross-domain matching accuracy on Euclidean Distance. By striking this balance between accuracy, efficiency and adaptability, it shows its suitability for dynamic and noisy environments for real-time tracking. The proposed method fills existing gaps and achieves a new state of the art for feature matching and tracking performance. © 2025 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity using Machine Learning Strategies for Phishing Defense 9

Enhancing Cybersecurity using Machine Learning Strategies fo...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Jamunadevi, C. Pandikumar, S. Naveen, N. Prasath, S. Dhivyashree, S. Pg Kongu Engineering College Department of Computer Technology Perundurai Erode India Acharya Institute of technology Department of Mca Bangalore India Excel Engineering College Department of It Komarapalayam India college Department of Computer Science Thindal India Kongu Engineering College Perundurai Erode India

ISBN: (纸本)9798350377972

Cybersecurity experts continue to be concerned about phishing attacks because it causes a real risk to people, businesses, and economies all around the world. Phishing attacks cause a critical threat to global cybersecurity, necessitating effective classification methods for phishing URL operations. So, this work aims to categorize phishing URL operations into distinct types: deceptive, spear, whaling, and pharming. Leveraging machine learning techniques including logistic regression, support vector machine, Naive Bayes, decision tree, K-NN, and Perceptron, evaluate their efficacy in accurately identifying and classifying phishing attacks. The findings underscore the importance of these models in providing cybersecurity professionals with actionable insights into the diverse tactics employed by malicious actors. Among the evaluated models, logistic regression emerges as the preferred choice, demonstrating superior performance in accurately categorizing phishing URLs. This work contributes to enhancing cybersecurity defenses by offering a comprehensive framework for understanding and mitigating the impact of phishing attacks on digital ecosystems. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation with IoT Sensor Systems for Energy Conservation using Zigbee and Wifi 5

Smart Home Automation with IoT Sensor Systems for Energy Con...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Jagannathan, Srinivasan Deepa, V. Sakthi Karthi Durai, B. Rajan, M. Sundar Celin, J. Jeya A. Dhamodaran, Sasikala Madanapalle Institute of Technology & Science Department of Computer Applications Madanapalle India Tiruppur Kumaran College for Women Pg and Research Department of Computer Science Tamil Nadu Tiruppur India Kalasalingam Academy of Research and Education Computer Science and Engineering India Arbaminch Institute of Technology Arbaminch University Faculty of Electrical and Computer Engineering Ethiopia Kalasalingam Academy of Research and Education Department of Information Technology Viruthunagar Krishnankoil626126 India Rajasthan Jaipur India

ISBN: (纸本)9798350379945

This study presents a comprehensive study on smart home automation systems utilizing Internet of Things (IoT) sensor technology to achieve efficient energy conservation. The proposed system integrates ZigBee and WiFi communication protocols for effective and reliable connectivity across various smart devices within a home. Through the deployment of interconnected sensors and intelligent controllers, the system allows real-time monitoring and management of household energy usage, optimizing energy consumption and reducing waste. The combination of ZigBee for low-power, long-range sensor networks and WiFi for high-speed data transmission enables seamless interaction between smart appliances, lighting, heating, and cooling systems. Proposesd approach offers a scalable, cost-effective solution for enhancing home automation with an emphasis on energy conservation and sustainability. Also discussed the implementation, challenges, and future potential of IoT-based smart home systems for improved energy efficiency. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Fashion Recommendation System for E-Commerce using Deep Learning Algorithms 15

Fashion Recommendation System for E-Commerce using Deep Lear...

引用

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

作者： Arunkumar, M.S. Gopinath, R. Chandru, M. Suguna, R. Deepa, S. Omprasath, V. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Tamilnadu Chennai62 India K. S. Rangasamy College of Technology Department of Computer Science and Engineering Tiruchgode India College Department of Computer Science Erode India Bannari Amman Institute of Technology Department of Computer science and Engineering Sathyamangalam India Kongu Engineering College Department of Computer Technology - Pg Erode Tamilnadu Perundurai638060 India Kongu Engineering College Erode Tamilnadu Perundurai638060 India

ISBN: (纸本)9798350370249

In the increasingly competitive outlook of ecommerce, personalized recommendation systems have emerged as pivotal tools to enhance user experience and drive sales. This paper proposes a novel Fashion Recommendation System (FRS) leveraging deep learning techniques to offer personalized fashion suggestions to users. The system utilizes a combination of convolutional neural networks (CNNs) for image feature extraction. Through a comprehensive analysis of user interactions and preferences, the FRS generates tailored recommendations that align with individual style preferences and current trends. The work proposes a novel approach that utilizes the ResNet50 algorithm to analyze images of fashion items, extracting meaningful features that capture the essence of style, color, and texture. By training the ResNet50 model on vast datasets of fashion images, thereby enhancing its ability to make accurate recommendations. Through the integration of user preferences and historical data, this system can generate personalized fashion recommendations tailored to each user's unique style and preferences, thus enhancing user satisfaction and engagement. By harnessing the power of deep learning and the ResNet50 algorithm, fashion retailers can offer personalized shopping experiences, increase customer retention, and drive sales. © 2024 IEEE.

关键词： Convolutional Neural Networks Deep Learning E-commerce Fashion Recommendation System Fashion Retailers Personalization ResNet50 Algorithm User Experience

来源：评论

学校读者我要写书评

暂无评论

Innovations In Ai and Deep Learning for Scalable Network Data Processing

Innovations In Ai and Deep Learning for Scalable Network Dat...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Kanchibhotla, Chaitanya Kota, Krishna Teja Srinivas, Pattllola Channappa, Sharvani Kumar, Ch. Kishore Katta, Siva Koteswararao Carelon Global Solutions Telangana Hyderabad India Department of Cse Maisammaguda India Ballari Institute of Technology and Management Ballari India Vaagdevi Degree & Pg College Department of Computer Science Warangal India Kitew Department of Mechanical Kakinada India

ISBN: (纸本)9798331508432

The exponential rise of AI in the last several years has altered whole markets and predicted the future of our technological infrastructure. As the use of AI systems increases across many industries, the concept of scalability is becoming more important. In order to offer a thorough grasp of its importance, difficulties, and potential solutions, this research paper explores the complex domain of AI scalability. The article starts by providing background on how the AI landscape is changing so quickly, and how scalability is crucial for meeting the increasing demand for AI-driven solutions. A comprehensive literature analysis served as the basis for our concept of scalability. In order to shed light on the many facets of scalability, including scalable AI models, algorithms, infrastructure, and cloud computing services, we reviewed previous studies. The report acknowledges the potential benefits of scalability, but it mostly addresses the common challenges that corporations and academics have when attempting to develop AI systems. Within this framework, we go over some tried-and-true methods for dealing with scalability concerns, such as optimizing resources and taking system architecture into account. Case studies demonstrating firms that have accomplished scalability in their AI endeavors are presented in the article to demonstrate the real-world impact of scalable AI solutions. The tactics and technology used in these case studies shed light on the revolutionary consequences of scalability on AI initiatives, which are very helpful. © 2024 IEEE.

关键词： AI-driven solutions Data Processing Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Road Safety with Real-Time Helmet Detection and E-Challan Issuance using YOLO and OCR 1

Enhancing Road Safety with Real-Time Helmet Detection and E-...

引用

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

作者： Deepa, S. Vinoth Kumar, C.N.S. Duraivelu, Vivek Easwaran, Balamurugan Suguna, R. Aparna, H. Kongu Engineering College Department of Computer Technology-PG Tamilnadu Erode638060 India Srm Institute of Science and Technology College of Engineering and Technology Department of Networking and Communications Tamilnadu Chennai India B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Narsapur502313 India Texila American University School of It Zambia Bannari Amman Institute of Technology Department of Computer Science and Business Systems Tamilnadu Sathyamangalam India Kongu Engineering College Perundurai Tamilnadu Erode638 060 India

ISBN: (纸本)9798350372748

This study proposes an integrated system combining Optical Character Recognition (OCR) and YOLO (You Only Look Once) for enforcing helmet laws and improving traffic safety. A user-friendly PyQT GUI facilitates vehicle registration, creating an organized CSV database for future reference. YOLOv5, an advanced object detection algorithm, identifies key elements like motorcycles, helmets, and number plates from input images. The primary objective is detecting motorcyclists without helmets, followed by OCR extraction of text from license plates. The extracted text is compared with registered bike information in the CSV file, generating e-challans and fines for matches. Automatic email notifications ensure timely communication and compliance with traffic regulations. The system's implementation not only aids helmet enforcement but also acts as a deterrent for future violations, fostering a safer driving environment. With scalability and practicality, this approach can integrate seamlessly into existing traffic control systems, leveraging AI technologies like YOLOv5 and OCR for effective problem-solving and enhanced road safety. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An incremental rough set approach for faster attribute reduction

引用

International Journal of Information technology (Singapore) 2023年第2期15卷 1-15页

作者： Nandhini, N. Thangadurai, K. Department of Computer Science Periyar University Salem 636011 India PG and Research Department Department of Computer Science Government Arts College (Autonomous) Karur 639005 India Department of MCA SNS College of Technology Autonomous Sathy Main Road Vazhlampalayam Pirivu Coimbatore 641035 India

In the view of performance improvement in machine learning algorithms it is essential to feed them with minimal and most relevant features. Feature selection is one of the evident preprocessing step followed by most of the learning algorithms for choosing the relevant features towards reducing the dimensionality of the dataset as well as to improve the classification accuracy. Among various feature selection techniques, Rough Set Theory has its own major contributions in feature selection domain. However, the conventional Rough Set based Feature Selection (RSFS) procedure takes up to O(kn²) time and space complexity, where k is the number of objects and n is the total number of attributes, which is further reduced to O(kn). In this paper, an incremental approach of RSFS is proposed to reduce the time complexity of the algorithm to O(k log n) time. Here the indiscernibility relation is estimated in an incremental fashion rather than calculating them in conventional way, hence the overall attribute reduction time is reduced significantly when compared to conventional roughest approach. The performance of the proposed Incremental Rough Set (InRS) approach is evaluated with QuickReduct feature selection algorithm. The simulation results indicate that the InRS approach is able to find the reduct with minimal time complexity than the existing rough set methods. © 2019, Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： InRS Machine learning Quick reduct Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Internet of things-Machine Learning: Development of Traceable System for Multi Purposes 3

Blockchain-Internet of things-Machine Learning: Development ...

引用

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Kowsalya, K. Rani, R. Paritala Jhansi Ritu Bhiyana, Malika Saini, Manisha Patil, Pravin P Srm Institute of Science and Technology Computer Science and Applications India Koneru Lakshmaiah Education Foundation Computer Science and Engineering Department Andhra Pradesh Vaddeswaram India Kurukshetra University Computer Science India Kurukshetra University Computer Science Govt Pg College Ambala Cantt Kurukshetra India Kurukshetra University Computer Science Govt Pg College Ambala Cantt India Graphic Era Deemed to Be University Department of Mechanical Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350399264

The Iot devices (IoT) and cryptocurrencies may be combined to create a platform that promotes improved and sustainable and credibility. The resulting innovations have been used in a number of industries, most notably in the monitoring of farm products. Particularly Ai devices (such as RFID, GIS, Geolocation, and others) have the capacity to streamline the collection of data pertaining to crucial traceable features. To handle, store, and search for information, data is acquired and put into the public ledger. The data security that enters the system may be ensured via a dispersed, randomized, and noninflatable cryptocurrency. Nonetheless, IoT devices could produce aberrant data as they gather *** study evaluates the entire beverage distribution network from sowing to sales, develops the network topology and each operate effectively, and patterns and enforces a computer vision (Fluid ounces) proof - of - stake tea reputable monitoring system, which considers literally the entire record keeping chain of food goods (MBITTS). This article presents a unique approach based on Internet of Things (IoT) technologies, such as RFID sensors, for enhancing the precision of cryptocurrency source data. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Chic Giza reformed deep attention model (GizRAM) for opinion mining on Twitter with text and emojis

引用

Iran Journal of computer science 2025年 1-17页

作者： Kothandan, Prema Pushpavalli, Rajaram Thirumalaikumari, T. Selvanathan, Pournima Sunitha, Pamarthi Nimmagadda, Padmaja Subburayalu, Gopalakrishnan Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Tamil Nadu Chennai 624622 India PG & Research Department of Computer Science Sri Sarada College for Women (A) Salem Fairlands Tamil Nadu Salem 636016 India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to Be University Tamil Nadu Chennai India Department of Computer Science and Engineering Sona College of Technology (Autonomous) Salem 636 005 India Department of Electronics and Communication Engineering Aditya University Andhra Pradesh Surampalem 533437 India Department of Electronics and Communication Engineering Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Andhra Pradesh Tirupati 517102 India Department of Information Technology Hindustan Institute of Technology and Science Tamil Nadu Chennai 603103 India

Today more than ever, social media like Twitter is significant. However, it has transformed into a public bulletin board where regular people, businesses, and even well-known figures like celebrities regularly post their opinions and take part in discussions. Also, Twitter persists as a useful tool for friends to stay in touch. Despite the widespread adoption of Twitter globally, it is more important than ever to be able to do trustworthy analyses of opinions to assess public opinion and perceptions on a variety of topics. Emojis are often used to convey emotions or thoughts that are challenging to put into words concisely. This paper establishes a new way of analyzing opinions by merging deep learning-based sentiment analysis approaches and integrating them with emojis. In this line of action, we propose the Giza reformed deep attention model for both textual as well as emoji-based feature extraction to classify user sentiments. To construct an enhanced opinion mining, a feature extraction and data preparation process based on multi-sets is carried out, followed by the application of the Giza pyramid construction optimizer to feature selection. It significantly reduces the dimensions to lead toward improved accuracy in predictions. This paper proposes the reformed temporal attention-based gated convoluted network (RefTAC) for effective sentiment classification based on the selected features. We validate the effectiveness of our proposed approach on popular Twitter datasets, and the results show impressive performance: 99.1% accuracy on the Airlines dataset, 99% accuracy on the Crowd Flower dataset, and 99% accuracy on the Apple dataset. Our method is better in terms of accuracy and efficiency than the state-of-the-art methods, which shows that adding emojis to sentiment analysis works well. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： And Giza reformed deep attention model (GizRAM) Deep learning Emojis text Opinion mining Sentiment analysis Social data Twitter

来源：评论

学校读者我要写书评

暂无评论

Paddy Plant Disease Detection using Hybrid Deep Learning Algorithms 8

Paddy Plant Disease Detection using Hybrid Deep Learning Alg...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Suguna, R. Deepa, S. Kanimozhi, T. Chandru, M. Arun, G. Harshini, M. Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam Tamilnadu Erode638401 India Kongu Engineering College Perundurai Department of Computer Technology - Pg Tamilnadu Erode638060 India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore641202 India College Department of Computer Science Erode India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai India Kongu Engineering College Tamilnadu Perundurai Erode638060 India

ISBN: (纸本)9798350367904

Agriculture is the backbone of India's economy, supporting a large portion of the population and establishing the country as a key global player in food production. India ranks as the second-largest producer of both paddy and wheat. However, agricultural productivity is highly susceptible to various plant diseases, which can significantly reduce crop yields and quality. Paddy, one of the most important staple crops, is particularly vulnerable to diseases caused mainly by viral and bacterial related diseases. The climate conditions are also play a vital role in paddy plant diseases. This research work proposes a deep learning-based approach for early detection and classification of paddy diseases. The proposed research devises a hybrid model that combines the VGG19 and ResNet50 algorithms, the system analyses images of both healthy and disease-affected paddy leaves, sourced from the Kaggle repository. This research focuses on predicting four major paddy diseases that can cause yield losses of up to 80%, and in severe cases, can destroy an entire crop: (i) Paddy Blast, (ii) Bacterial Leaf Blight, (iii) Sheath Blight, and (iv) Ufra Disease. The proposed model achieves a high accuracy rate of 98% in predicting paddy diseases and offers a rapid classification process, showcasing the potential of advanced image processing and deep learning techniques to mitigate the impact of paddy plant diseases on agricultural productivity. © 2024 IEEE.

关键词： Crops

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：