检索结果-内蒙古大学图书馆

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Srivastava, Swati GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

Automatic image captioning is a complex research area whose objective is to generate descriptions in natural language from a query image. It has significantly advanced with deep learning with applications in humancomputer interaction, medical image captioning, traffic analysis, industrial quality control, and assistive systems for the visually impaired. Image captioning task includes visual features extraction and generate syntactically and semantically correct descriptions of the image. Deep learning techniques are proficient in handling the multifaceted relationships among image objects. This work explores 14 popular image captioning datasets used in the evaluation of deep learning models for automatic image captioning. The ultimate goal of this work is to provide better understanding of image captioning datasets which may benefit the related research communities. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Exploring AI Techniques for Yoga Image Classification: A Focus on Machine Learning and Deep Learning 1

Exploring AI Techniques for Yoga Image Classification: A Foc...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Duggal, Anjali Kumar, Satish Tripathi, Pooja Panjab University Department of Computer Science and Applications Chandigarh India Swami Sarvanand Giri Regional Centre Panjab University Department of Computer Science and Applications Hoshiarpur India Inderprastha Engineering College Aktu Department of Information Technology Lucknow India

ISBN: (纸本)9798331529246

Machine Learning (ML) has become essential for developing intelligent systems, providing critical Artificial Intelligence (AI) capabilities. ML involves teaching computers to solve problems by analyzing data, creating analytic models automatically, and performing associated tasks. Deep Learning (DL), a sophisticated branch of ML, utilizes neural networks to simulate AI and often surpasses traditional ML models and data analysis techniques, especially in applications like image classification. This study investigates ML and DL techniques with a particular focus on image classification applications. A novel experiment was conducted using the CNN and VGG16 model, with variations in batch size configurations to optimize yoga posture classification. The methodology involved a comprehensive review of existing approaches and experimental evaluation to assess the model's performance under different configurations. The experimental results demonstrated significant improvements in classification accuracy, achieving up to 86% in recognizing yoga postures. This represents a notable advancement in precision compared to existing methods, showcasing the effectiveness of DL models such as VGG16 in tackling complex image classification challenges. These findings underscore the potential of DL in achieving high accuracy in specialized domains like yoga posture recognition. The study provides a strong foundation for further research and application in related fields, highlighting the efficacy of advanced DL models in addressing domain-specific image classification problems. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Information in QR Codes Through Steganographic Technique 3

Safeguarding Information in QR Codes Through Steganographic ...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Bhardwaj, Jyotsana Panwar, Ruby Gla University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798331528201

The act of concealing data within a different message or object in order to avoid detection is referred to as steganography. Steganography can hide various types of digital content such as text, images, audio, and video. Upon arrival, the hidden information is subsequently exposed. Employing a form of steganography called QR Image Steganography, in which a secret message is encoded into a QR code and subsequently hidden within an image to provide effective and efficient security. To safeguard the secret communication, encoding is carried out on the sender's end, and decoding is done on the recipient's end. This paper is focused on the idea that, in order to maintain confidentiality and prevent a third party from spotting the hidden message in the stegano image, the cover image should not be significantly altered when concealing the QR code containing the secret message. Additionally, the PSNR values of the cover picture and the stegano image were used to verify this;they were fairly high, showing that the cover image had slight distortion. In order to determine the pixel value change where the distortion is not apparent, the sample histograms of the cover and stegano picture were also plotted. © 2024 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Machine Learning Algorithms for Predicting Stroke 7

Performance Enhancement of Machine Learning Algorithms for P...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Jain, Vinod Mangal, Anuj GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350372816

Stroke is very common heath problem now. Early prediction of stroke is very essential to decrease the impact of this disease. Machine Learning (ML) algorithms are very useful in making predictions for various diseases. In this paper, the power of machine learning algorithms is used for stroke prediction. Even after a lot of research the accuracy of machine learning algorithms is a challenging issue. Many researchers worked on improving the accuracy of ML models. Machine learning models worked on data sets. For stroke prediction using machine learning, a well-known data set is considered in this paper. The data set consist of many important factors which may affect the chances of stroke in a person. Logistic Regression, Decision Tree and Random Forest are three machine learning algorithms which are very popular and effective in prediction of stroke. In this work these three machine learning algorithms are applied for stroke prediction and their performance is checked and compared. From the results it is observed that the performance of Logistic Regression is best with 95.34% accuracy. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Design of real time intelligent system for women safety

引用

Recent Patents on engineering 2024年第3期18卷 77-83页

作者： Kohli, Priyanka Singh, Kawaljeet Sidhu, Brahmaleen Kaur Department of Computer Science & Engineering Punjabi University Patiala India University Computer Centre Punjabi University Patiala India

Background: Even the technology has advanced a lot in these modern times, women's safety is still a massive issue. Women are not safe anywhere. Their safety is an essential and decisive issue in today’s world. They face extreme troubles when they are alone, travelling on lonely roads and at workplace. Education is essential for everyone and especially for women. It is a powerful weapon to end poverty. Government and NGOs have made many rules and regulations but the crime against women has not ended. There are many instances of harassment, abuse, eve-teasing, kidnapping, domestic violence and rape. Women are working equally as men but still their safety is a big challenge. With the boom in the IT and corporate sector, many women are now working and even during nightshifts. Objectives: A Real Time Intelligent System for Women Safety has been proposed to overcome these limitations. Methods: In this paper, many women's safety systems that were proposed or developed have been discussed. Major drawbacks in the current system, devices or applications have been highlighted. Latest technologies like machine learning, artificial intelligence or data science have been ignored. Results: The proposed system will be highly sophisticated with the latest techniques and women will feel safe in all situations. It will predict the safe route while moving alone. Conclusion: Moreover, it will record the evidence and will also suggest the rights of women. © 2024 Bentham science Publishers.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Segmentation with Recurrent Neural Network Architectures 2

Enhancing Medical Image Segmentation with Recurrent Neural N...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Masson, Palak Sharma, Deepak Yadav, Kanchan Sethi, Tarun Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Srm Institute of Science and Technology Department of Computer Applications UP Modinagar India Gla University Department of Mechanical Engineering UP Mathura India Iamr Department of Computer Applications UP Ghaziabad India

ISBN: (纸本)9798350371055

Scientific imaging is a swiftly evolving and developing vicinity of healthcare. Greater accurate segmentation of clinical images is paramount for correct diagnosis. Recent breakthroughs in profound mastering studies have allowed researchers to faucet into a powerful but unstructured information form - images. With the usage of recurrent neural network architectures (RNNs), researchers are exploring the capacity of this shape of facts to acquire better consequences from scientific photograph segmentation. RNNs are regarded for their flexibility in encoding temporal relationships and processing established statistics. In medical image segmentation, this flexibility aids in recognizing complicated styles in photographs and helps the model to localize features inside the image better. Furthermore, the networks can run on images of various sizes, ensuring that models can handle photos created using unique imaging modalities. Additionally, RNNs can examine large annotated datasets and, consequently, help supply meaningful segmentation outcomes. Recent advances in using RNNs for medical photo segmentation have shown promising effects. RNNs have been used to phase colon anatomy, mind tumors, and lymph nodes. U-internet-primarily based segmentation fashions that include RNNs and feature-achieved high segmentation accuracy for medical photograph segmentation responsibilities have also evolved. Within destiny, RNN-based total models will remain superior and could be implemented in various medical imaging segmentation tasks. As such, RNNs will make scientific imaging segmentation extra green and accurate, allowing faster and more accurate analysis and treatment. © 2024 IEEE.

关键词： Achieved Recognizing Relationships Segmentation

来源：评论

学校读者我要写书评

暂无评论

Spam Message Identification Using Machine Learning Approach 2

Spam Message Identification Using Machine Learning Approach

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Mohan, Narendra Jain, Vinod Gla University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350368413

Spam message detection has become an essential task in modern digital communication systems due to the exponential growth of unsolicited messages. Traditional rule-based spam filters, though initially effective, have become inadequate in handling the sophisticated techniques employed by spammers. Consequently, machine learning algorithms are used for spam detection because of their ability to learn the data and these algorithms can improve their performance by providing new data. This research paper explores various ML algorithms utilized for spam detection. Supervised learning methods are predominantly highlighted, focusing on how these models are trained using labeled datasets where messages are classified as spam or non-spam. Additionally, the paper addresses challenges such as the evolving nature of spam, imbalanced datasets, and the need for real-time detection solutions. The paper concludes by exploring the outcome results of ML models for spam detection with Support Vector Classifier (SVC) as best ML model with 97.48% accuracy. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Novel Quality of Service Aware Video Streaming on Demand System for the Internet of Thing Enabled MANET

Development of a Novel Quality of Service Aware Video Stream...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Agrawal, Navin Kumar Kumar, Sandeep Bisht, Girish Singh Srivastav, Akanksha Bansla, Vandna Jain, Arpit Gla University Department Of Computer Engineering And Applications U.P. Mathura India Tula's Institute Department Of Computer Science And Engineering Uttarakhand Dehradun India Shivalik Engineering College Department Of Computer Science And Engineering Uttarakhand Dehradun India Koneru Lakshmaiah Education Foundation Department Of Computer Science And Engineering AP Vaddeswaram India

ISBN: (纸本)9798350366846

A mobile ad hoc network (MANET) uses mobile devices and wireless networking to stream video. Several methods have been developed to address the challenges associated with video streaming over MANETs. This paper designed a new protocol for Mobile Video of Demand (MVOD) system architecture over the MANET environment. The proposed MVOD Model is used to improve the QoS parameters of the video system in wireless ad-hoc networks. The MVOD protocol uses client caching algorithms and a staggered broadcasting method, and it compares its performance with that of an existing traditional protocol for three-tier architecture. When compared to QoS parameters such as service delay and bandwidth utilization, the proposed MVOD model performs better than the traditional approach when compared with various scenarios. Based on the importance and complexity of evaluating the techniques, we conclude that comparability problems exist in research. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Webcam-Based OCR System with Text-to-Speech Conversion 5

Webcam-Based OCR System with Text-to-Speech Conversion

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Nair, Rekha R Babu, Tina Kishore, S. Poornima, J. Sambasivudu, Madduru Bhargavi, Manchikalapudi Alliance School of Advanced Computing Alliance University Department of Computer Science and Engineering Bengaluru India Department of Computer Applications Mangalore India Brindavan College of Engineering Department of Information Science and Engineering Bengaluru India Malla Reddy College of Engineering and Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331530013

The project develops an OCR system that converts webcam-captured text to speech, featuring user registration for personalized experiences. Key components include image capture via webcam, text extraction using OCR, database storage, and text-to-speech conversion. The system employs Python, OpenCV for image processing, Tesseract for OCR, and Google Text-to-Speech for audio output. Main objectives are to streamline text digitization and assist visually impaired users. The modular design allows for future enhancements like language translation. Comprehensive testing ensures reliability and effectiveness. The system demonstrates an efficient solution for converting printed text to digital and audio formats, with applications in document digitization, education, and accessibility services. It reduces manual effort in text digitization and improves access to written information for visually impaired individuals, showcasing potential across various fields. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Use of Blockchain for Fake Product Detection 5

Use of Blockchain for Fake Product Detection

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Kumar, M. Sunil Vani, M. Sowmya Pavithra, N. Chandana, R. Jhansi, N. School of Computing Department of Computer Applications AP Tirupati India Sree Vidyanikethan Engineering College Department of Computer Applications AP Tirupati India

ISBN: (纸本)9798350383522

Products that are counterfeit pose a serious threat to both consumers and businesses. Our suggested method makes use of blockchain technology to establish an open and trustworthy platform for tracking phone goods all the way through the supply chain. Each product is assigned a unique digital ID stored on the blockchain, along with origin and production details. Stakeholders can scan the ID to verify product integrity. IoT and machine learning enhance identification by providing real-time data and analyzing patterns. Suspected counterfeit cases are flagged for investigation. This blockchain-based system protects brand reputation, revenue, and enables informed purchases. Blockchain's immutability prevents tampering, reducing fake goods prevalence. © 2024 IEEE.

关键词： Blockchain Fake Production Detection

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：