检索结果-内蒙古大学图书馆

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Mohan, Vasanthakumar Paramesh, Anandh Sivaguru Panimalar Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350328202

In the modern era, most activities are being digitized. One of the main objectives of AI is to enable human machine interaction. The dialogue systems technology has been utilized by numerous organizations to create a variety of types of personal assistants depending on their applications and domains. Here we introduce the development of a versatile Knowledge Based Personal Assistant for College that leverages advanced technologies, including natural language processing, voice recognition, and text to speech synthesis, to address the diverse and evolving needs of the college community. This AI driven system is designed to facilitate a seamless and efficient user experience, allowing users to interact with the assistant through both voice and text inputs. Alongside core functionalities encompassing academic schedule management, emergency contact assistance, email integration, location based services, and academic inquiries, the assistant provides responses in both voice and text formats. Technical aspects include the integration of state of the art NLP algorithms for query understanding and context aware responses. Users can easily switch between input mode and receive responses, accordingly, offering a flexible and inclusive user experience. The assistant adaptability and expandability are central to its design, featuring modular architecture that facilitates the integration of additional features and services. © 2024 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Enabling secure modern web browsers against cache-based timing attacks

引用

International Journal of Security and Networks 2024年第1期19卷 43-54页

作者： Ganesan, Sangeetha Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Tamil Nadu Tiruvallur India

Web applications have grown to be the foundation of any kind of system, ranging from cloud services to the internet of things (IoT) systems. As a huge amount of sensitive data is processed in web applications, user privacy shows as the most important concern in web security. In the virtualisation system, cache side channel (CSC) attack techniques have become popular to retrieve the secret information of other users. This paper presents a run-time detection and prevention mechanism, called browser watcher (BW), for time-driven CSC attacks. The computation overhead of the proposed BW java script engine is monitored and tabulated for the different domains. The average cache miss rate is measured from 23% to 89%. Once the BW system identifies the attacker, then it prevents stealing the secret information of the victim. This makes it very hard for the attacker to find the memory access pattern of the victim. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Yoga Posture Analysis and Feedback System Using Mediapipe

Yoga Posture Analysis and Feedback System Using Mediapipe

引用

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

作者： Snigdha, D. Tejasree, S. Rithvik, N. Shanmuagasundaram, Hariharan Motikar, Siddharth Reddy, S. Srinivas Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India

ISBN: (纸本)9798331509828

This project integrates Mediapipe with Python to implement a yoga posture analysis system for evaluating and providing efficacious feedback on human poses. The system establishes ideal joint landmarks using reference images, which are compared with uploaded analysis images over multiple simulated epochs. Angles of key joints, such as the elbow, shoulder, hip and knee are calculated and annotated onto the analyzed images for visual feedback. Deviations of analyzed images are identified and corrective suggestions are provided. Comprehensive graphs of accuracy and loss for each epoch are displayed to visualize the trends in accuracy and pose improvement. Accuracy reflects how well the model predicts the correct output, while loss indicates areas for improvement. In addition, for easy reference, all epoch data are tabulated to summarize overall performance, and a final model accuracy percentage is computed. The project also gives visual presentations of accuracy and loss over each epoch. The system serves as an effective tool for posture correction, making it suitable for fitness applications, physiotherapy, and ergonomic evaluations, with its detailed visual and numerical feedback. © 2025 IEEE.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Automated Anomaly Detection in Pregnancy: AI-Driven Ultrasound Analysis 2

Automated Anomaly Detection in Pregnancy: AI-Driven Ultrasou...

引用

2nd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Revathi, K.P. Mahesh, Indusha Makitha Sree, K. Deepthi, Nadiminti Easwari Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350327533

This research explores the application of AI-driven techniques for automated anomaly detection in ultrasound scans during pregnancy. Leveraging a substantial dataset of labeled ultrasound images, this study delves into robust data collection, preprocessing methodologies, meticulous model selection, and comprehensive model training techniques. The combination of U-Net for image segmentation and ResNet for image classification was selectively chosen, followed by an in-depth analysis of their adaptability to medical imaging tasks. The study concludes by proposing a hybrid approach using both segmentation and classification for more accurate anomaly detection in ultrasound images. This study delves into a comprehensive survey of AI methodologies applied to fetal ultrasonography during the second trimester. By leveraging curated datasets and innovative AI techniques, this research navigates the evolving landscape of automated anomaly detection, aiming to enhance diagnostic capabilities and bridge accessibility gaps in prenatal care. © 2024 IEEE.

关键词： Anomaly Detection Techniques artificial intelligence Automated Anomaly Detection Image Classification Image Segmentation Model Training Pregnancy Residual Neural Networkt U-Net Ultrasound Analysis

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm Powered Bivariate Function Encryption for Robust data Security 4

Genetic Algorithm Powered Bivariate Function Encryption for ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Hariharan, N.R. Ritheshwar, R.Sai Suseendran, R. Meena, R. Kalaiselvi, T. Easwari Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331523923

This paper introduces a new encryption technique which bases its operations on advanced bivariate mathematical functions and uses a genetic algorithm to optimize these along with random key generation techniques. This, in turn, allows for the enhancement of cryptographic complexity and better security features with fortified protection against any possible attacks. The encryption mechanism integrates random keys along with the evolved bivariate functions, and RSA protocol is employed for securing the channel of exchanging keys, ensuring confidentiality at each stage of the transmission process. The integration of these methodologies has created a two-layer security framework that combines the efficiency of symmetric encryption with the robustness of RSA. Advanced symmetric encryption combined with RSA significantly increases the security measures provided by defending against brute force attacks, cryptanalysis, and intercept threats. Through the combination of symmetric encryption and an asymmetric key exchange protocol, this strategy fully addresses the disadvantages of the typical cryptographic system. It forms an effective solution in meeting the contemporary security demands for digital communication environments. © 2025 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Breast Cancer Detection: Leveraging EfficientNetB3 for Accuracy and Scalability 3

Revolutionizing Breast Cancer Detection: Leveraging Efficien...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Bhuvaneswari, S. Dhivya, G. Veronica Philo Vimal, J. Veera Anusuya, V. Kalaivani, V. National Engineering College Department of Artificial Intelligence and Data Science Kovilpatti India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509675

One of the largest health issues facing women worldwide is breast cancer, with a growing need for early and accurate diagnosis to improve the patient outcome. Traditional approaches like mammography and biopsy often come with limitations like interpretive variability and accessibility issues. In this paper, let's approach the identification of breast cancer using CNN by focusing on the EfficientNetb3 architecture. The proposed method utilizes the advanced feature extraction capabilities and computational efficiency of EfficientNetb3 to analyze mammographic images. The model achieves high accuracy and sensitivity with class imbalance and overfitting issues using a well-structured dataset and robust preprocessing techniques. This study opens the door for more efficient and widely available AI-driven healthcare solutions by showcasing the potential of EfficientNet - based CNN models to improve diagnostic precision and scalability. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MusiciAI: A Hybrid Generative Model for Music Therapy using Cross-Modal Transformer and Variational Autoencoder 2

MusiciAI: A Hybrid Generative Model for Music Therapy using ...

引用

2nd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Venkatachalam, Nirmala Raghuram Karthic Ganesh, V. Hari Vigneshwaran, S. Easwari Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350327533

Music has long been recognized for its therapeutic potential, offering emotional and psychological benefits. In the contemporary landscape, the intersection of artificial intelligence and music therapy introduces innovative applications. MusiciAI introduces an advanced generative model designed to harness the healing power of music through a novel hybrid approach. Combining a Cross-Modal Transformer and a Variational Autoencoder, MusiciAI interprets textual prompts and generates diverse, emotionally resonant music. The proposed model is trained on a carefully curated dataset, incorporating language models for precise annotation. MusiciAI integrates user interaction, allowing prompt-based music generation and user adjustments for a personalized therapeutic experience. Through a comprehensive exploration of the hybrid model's architecture, training, evaluation, and user-centric features, and contributes to the evolving landscape of generative AI in music therapy. © 2024 IEEE.

关键词： artificial intelligence Cross-Modal Transformer Emotional Resonance Generative AI Hybrid Modal Language Models Music Therapy Personalized Music User Interaction Variational Autoencoder

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calorie Burn Estimation for Enhanced Physical Activity Monitoring 2

Machine Learning-Based Calorie Burn Estimation for Enhanced ...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Santhiya, S. Senthamarai, M. Jayadharshini, P. Juber, B. Akshay, J. Aneesh, S. Department of Artificial Intelligence Kongu Engineering College Erode India Department of Artificial Intelligence and Data Science Nandha Engineering College Erode India

ISBN: (纸本)9798331541217

The rapid pace of technological advancements has created a multitude of prospects and challenges, especially in regard to mental health and personal fitness. More often than not, the fast pace of modern living forces people to make unhealthy food choices that are more readily available, leading to increased caloric intake, which represents one of the primary causes of the growing rates of obesity. This situation strongly emphasizes the urgent need for effective control over calorie intake and expenditure along with other resources to promote healthier lifestyle habits. The study takes a comprehensive approach to these issues by propounding intricate methods in machine learning designed to calculate caloric expenditure incurred during various phases of physical activity. It primarily helps people by providing information to maintain consistency in their exercise routines and promote healthy eating habits. The model proposed in this study combined complex algorithms like XGBoost, Decision Trees, and Support Vector Regression (SVR) for a highly massive dataset of over 15,000 data points. Interestingly, XGBoost reflected an observed mean absolute error of as low as 1.48, thus improving the accuracy of calorie expenditure estimation and encouraging users to engage in regular physical activity. This approach is much more impactful than just analyzing caloric intake. The Machine Learning algorithm, as it learns and evolves from experience with its user, can output thematic insights and recommendations that nudge individuals toward active fitness and nutritional oversight management. The findings highlight the impact of technology on constructive behavioral modification and the potential for improving lives as individuals transition to healthier lifestyles. © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

OpenAI-Enhanced Personal Desktop Assistant: A Revolution in Human-Computer Interaction 2

OpenAI-Enhanced Personal Desktop Assistant: A Revolution in ...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Benny, Rijo Muralidharan, Ashwin Subramanian, Malathi Panimalar Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350328202

The creation of a natural conversation between humans and machines is the primary objective of artificial intelligence (AI). One of the greatest advancements in AI that has the potential to significantly alter people's way of life are voice assistants. We know that the role of AI based voice assistants is to recognize the input human voice and respond to the given input via integrated voices. A lot of IT based organizations have been using dialogue systems technology to create various types of Virtual Personal Assistants (VPAs) based on their application requirements and areas for increasing interaction between human and a machine, for example, Apple's Siri, Microsoft's Cortana, Amazon Alexa and Google Assistant. By early 2023, Amazon Alexa was used daily by approximately 70% of users, yielding satisfaction levels surpassing 70%. Google Assistant boasted a global user base of 500 million per month, enjoying satisfaction rates over 80%. Apple Siri similarly engaged around 500 million users monthly, maintaining a satisfaction rate of about 78%. Microsoft Cortana had limited usage data but attained satisfaction rates around 60-65%. Roughly 60-70% of users across platforms expressed worries regarding data privacy and security when utilizing these desktop assistants. So, the main objective of our work is to create a personalized desktop assistant embedded with the OpenAI technology and improvement in security. Like the Microsoft's Cortana (which was discontinued by Microsoft), we aim to design a more efficient and personal desktop assistant, enhanced with OpenAI solely for Windows using Python, which can be accessed using any of the Windows Explorer like Windows 7,8,9,10,11. Here we use Python as the major programming language as it has a lot of inbuilt libraries that could make the task even easier. The way of developing a personal desktop assistant without requiring cloud services is discussed in this paper, which will also allow the future extension of such devices. ©

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Ultrasound Images based and Convolutional Neural Network 6

Breast Cancer Detection using Ultrasound Images based and Co...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Langote, Meher Hiwase, Kunal Wande, Radha Tale, Abhay Kalekar, Harsh Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Maharashtra Sawangi India

ISBN: (纸本)9798331522667

Breast cancer forms one of the most common types of cancer among women worldwide;therefore, it highlights the importance of having rapid and timely diagnosis methods. Here, we will survey the use of convolutional neural networks (CNNs) for mutually exclusive cancer detection in ultrasound images using detectors. A dataset of benign and malignant breast tumors visualized via ultrasound is taken as the base for the training and testing of the CNN model. The CNN architecture is arranged to select valuable features from the ultrasound pictures only, but not malignant lesions. The performance and the evaluation of the CNN model are done through metrics like accuracy, precision, recall, and F1 score. The findings confirm the efficiency of using the CNN here, as it shows the extent and solidity of reading textures with excellent precision and quick performance in breast cancer screening. This investigation is the advancement of computer-aided diagnostic tools for breast cancer screening. As medical practice sees these benefits, the efficiency of healthcare delivery and patient outcomes are bound to be optimized. © 2025 IEEE.

关键词： Ultrasonic imaging

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：