检索结果-内蒙古大学图书馆

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Akilesh, S. Sekar, Rajeev Tulasi Raman, R. Suganya, R. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529833

This paper presents a personalized diet recommendation system that leverages a graph database and retrieval-augmented generation (RAG) with large language models (LLMs) to provide accurate and tailored nutritional plans. The system focuses on vegetarian Indian dishes and analyzes individual health metrics such as physical activity levels, weight age and height to generate customized diet plans. A Neo4j graph database, built from scraped recipe data, stores dish names, ingredients, and nutritional values, enabling precise information retrieval via LLMs. Additionally, the system provides nutritional details and overall health assessments of the dishes. To enhance overall health, the system also suggests basic workout plans based on users' physical metrics and dietary recommendations. This approach aims to provide a low-cost, accessible alternative to traditional diet consultations while mitigating hallucinations in AI outputs through RAG and structured data. © 2025 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Navigation and Surveillance System: A Comprehensive Real-Time Solution for Mobility Assistance and Environmental Monitoring

Adaptive Navigation and Surveillance System: A Comprehensive...

引用

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

作者： Dhaarini, G. Sanjai, R. Sandosh, S. School of Computer Science and Engineering Vellore Institute Of Technology Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

The rapidly changing urban landscape introduces unprecedented challenges to mobility and security, especially for the visually impaired and surveillance operators. All existing assistive technologies and monitoring systems significantly lack real-time environmental awareness, detection of obstacles, and comprehensive threats. Current approaches, mainly based on traditional mobility aids and conventional surveillance mechanisms, fail to provide adaptive and intuitive solutions that address the complex needs of navigation and safety in a modern urban environment. The Adaptive Navigation and Surveillance System is thus the innovative technological intervention that seeks to revolutionize environmental monitoring with high-performance ultrasonic sensing, multi-modal feedback mechanisms, and intelligent processing. The servo-mounted ultrasonic sensor features 180-degree scanning capability while also using sophisticated Arduino-based processing as well as a color-coded radar visualization interface, allowing it to take a transformative approach to personal mobility assistance and security infrastructure. The research will develop flexible, context-aware technological frameworks in support of enhancing situational awareness, real-time threat detection, and a more inclusive safer urban experience by bridging those critical gaps in existing assistive and surveillance technologies. Therefore, the system represents a leap forward in addressing the problems of navigation and security in increasingly intricate urban landscapes. © 2025 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiac Health: Machine Learning in Coronary Artery Disease Prediction 6th

Enhancing Cardiac Health: Machine Learning in Coronary Arter...

引用

6th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Vijayaraj, Anu Ragavi Pasupathi, Subbulakshmi School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819780891

The alarming surge in cardiovascular diseases, with a particular focus on Coronary Artery Disease (CAD), is causing premature fatalities. This escalation is exacerbating the inefficiency of the diagnostic process, burdened by both time constraints and the strain on human resources, as more patients endure extended wait times for diagnosis. Addressing this pressing issue calls for the fusion of analytical decision-making with digital patient data, aiming to develop a robust and efficient predictive model for early-stage cardiac illness. Machine Learning (ML) emerges as a promising tool to bolster CAD detection and prognosis within the healthcare sector. This chapter introduces an ML-based approach for CAD prediction, leveraging the Z-Alizadeh Sani dataset sourced from the UCI repository. The classification task is tackled using three distinct ML models—Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The findings underscore the superior performance of ANN, achieving an impressive 89.01 percent accuracy in CAD diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition Using Convolutional Neural Network Based on VGG-16 Deep Learning Approach 5th

Sign Language Recognition Using Convolutional Neural Network...

引用

5th International Conference on Advances in Information Communication technology and Computing, AICTC 2024

作者： Athish, M.J. Sowmya, S. Lakshaya, E. Preetha, S. Rishiya Shankar, S.U. Sendhil Kumar, K.S. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9789819761050

Communication is a significant part of our lives, as it facilitates interaction among individuals. Language serves as a mode of communication for all individuals for expressing their thoughts and interpretations. However, hearing-impaired individuals often face hurdles in using spoken language. The technology for recognizing sign language made a commendable effort to improve communication levels among hearing-impaired individuals. In the current era of deep learning, which is a subset of machine learning, Convolutional Neural Network models have been developed and are now in use for gesture recognition. This recognition is based on the CNN model and VGG-16 model. It is used to hone the temporal features. The dataset used here is American Sign Language Dataset (A–Z and 0–9). The focus of this work is to develop a sign language recognition system to fulfill the need for communication of impaired people in society. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure File Sharing System Using Hybrid Authentication and Secured Key Management Algorithm 4th

Secure File Sharing System Using Hybrid Authentication and S...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Dokania, Aryan Bamb, Anshul Dheeba, J. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9789819751990

When web file sharing is used, users can safely receive and share any files or documents over the web using any of their preferred web browsers. Though the existing cryptographic algorithms perform well in end-to-end encryption, they are not resistant to attacks that extract information from the computer system, such as passwords and encryption/decryption keys. In this paper, a hybrid method is proposed for secure and efficient end-to-end encryption. This paper focuses on secure key exchange, efficient data encryption, and strengthening of passwords, which is achieved by a combination of four cryptographic algorithms. The proposed hybrid cryptographic method is secure against several attacks, including man-in-the-middle attacks and side-channel attacks. The proposed method offers many advantages over traditional end-to-end encryption methods, including security, efficiency, and resistance to side-channel attacks. Extensive analytical and experimental results show that the proposed method is efficient enough to be used in a file sharing system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Advancing Cancer Diagnosis: Federated Learning for Tumor Classification

Advancing Cancer Diagnosis: Federated Learning for Tumor Cla...

引用

Congress on Smart Computing Technologies, CSCT 2023

作者： Upadhyay, Siddharth Singh, Khushi Suganeshwari, G. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819780952

Ensuring data privacy and security is a critical challenge in cancer diagnosis, driving the adoption of Federated Learning as a collaborative and privacy-preserving solution for tumour classification. Tumour classification plays a significant role in enabling precise diagnoses and treatments. However, centrally aggregating medical data raises concerns regarding the privacy and security of an individual. To tackle these challenges, we use Federated Learning, which offers a privacy-preserving approach that involves collaborative model training on decentralized data sources. This paper showcases the research contributions and gaps in the field of healthcare data, focusing on the significance of ethics. This survey introduces the concepts of federated learning, emphasizing healthcare studies highlighting the importance of tumor classification in healthcare decision-making. Moreover, this paper discusses the recent advancements in Federated Learning concerning tumor classification, including a wide variety of data such as medical imaging, genetics, and clinical data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Classifying aquatic organism via evolving residual convolutional neural networks by optimized random vector functional link

引用

Multimedia Tools and Applications 2025年第1期84卷 221-243页

作者： Zhou, Zhiyu Wen, Jingqi Liu, Mingxuan Yang, Junyi School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China School of Mechanical Engineering Hangzhou Dianzi University Hangzhou310018 China

Aquatic organisms serve as crucial indicators of ecosystem health and water quality conditions. Accurate classification and monitoring of aquatic organisms facilitate the timely detection of ecological environmental changes, which is of significant importance for the conservation of biodiversity and environmental protection. Pointing at the issues of fuzzy images and difficult classification caused by the poor lighting conditions of aquatic organisms and many impurities around, we put forward a novel classification model of aquatic organisms with convolution neural network, feedforward network and optimization algorithm. The model first abstracts the traits of aquatic organisms, and then classifies the abstracted features. Through migration learning of ResNet101 neural network on Fish4Knowledge dataset and ISLVRC2012 and some data sets related to aquatic organisms, a network that will be used to abstract features is obtained. The model put forward in the paper firstly uses ResNet101 to abstract the aquatic organism image’s characteristics, and then uses the Golden Eagle optimization algorithm (GEO) optimized by chaos mapping optimization and the RVFL neural network optimized by L2,1 regularization to classify aquatic organisms. The algorithm is compared with other RVFL algorithms optimized by Ant Lion Optimizer (ALO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Harris Hawks Optimization (HHO) and Dragonfly Algorithm (DA). The findings indicate that the methodology introduced in this paper exhibits an improvement over the original ResNet101, with increases of 1.58%, 2.57%, 0.22% and 0.93% in particularity rate, accuracy rate, recall rate and F1 score on ILSVRC2012, respectively. The efficiency and accuracy of this method significantly contribute to the advancement of aquatic organism monitoring and environmental protection efforts. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Predicting Mental Health Issues Indicators in Textual Data Using Enhanced Bidirectional Encoder Representations from Transformers

Predicting Mental Health Issues Indicators in Textual Data U...

引用

International Conference on Computing and Machine Learning, CML 2024

作者： Verma, Naman Majumder, Madhulika Anbarasi, L. Jani School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819778386

Mental health is a major pillar in the overall health of a human being and allows the person to function well in society to fulfill his/her needs, responsibilities, and desires. Yet according to World Mental Health Report (WHO), more than one out of a hundred deaths is caused by suicide, making it a major cause of death among young individuals. With social media platforms serving as an easily accessible platform for a person of any demographic, age or sex, to voice their thoughts, and read unvalidated opinions about sensitive topics like mental health, boundaries between personal expression and potential threats to mental well-being are constantly becoming blurry. With a certain increase in online discussions regarding mental health among various individuals, it becomes important to explore these linguistic nuances of comments and analyze them for better understanding as well as the prediction of mental state of the individual. Using natural language processing techniques, this study aims to establish the patterns and sentiments conveyed by commentary on social media, to better identify potential indicators of mental health issues. Using a bidirectional representation natural learning model (BERT) and a simple three-layer architecture, a dataset containing over 27 thousand text entries, relating to people with anxiety, depression, and other mental health issues social media interactions, was analyzed. The model achieved an accuracy of 87.68% and 85.45% precision. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Feature selection for determining input parameters in antenna modeling

引用

Journal of Systems engineering and Electronics 2025年第1期36卷 15-23页

作者： LIU Zhixian SHAO Wei CHENG Xi OU Haiyan DING Xiao School of Physics University of Electronic Science and Technology of ChinaChengdu 611731China School of Computer and Information Engineering Xinjiang Agricultural UniversityUrumqi 830052China

In this paper,a feature selection method for determining input parameters in antenna modeling is *** antenna modeling,the input feature of artificial neural network(ANN)is geometric *** selection criteria contain correlation and sensitivity between the geometric parameter and the electromagnetic(EM)*** information coefficient(MIC),an exploratory data mining tool,is introduced to evaluate both linear and nonlinear *** EM response range is utilized to evaluate the *** wide response range corresponding to varying values of a parameter implies the parameter is highly sensitive and the narrow response range suggests the parameter is *** the parameter which is highly correlative and sensitive is selected as the input of ANN,and the sampling space of the model is highly *** modeling of a wideband and circularly polarized antenna is studied as an example to verify the effectiveness of the proposed *** number of input parameters decreases from8 to *** testing errors of|S_(11)|and axis ratio are reduced by8.74%and 8.95%,respectively,compared with the ANN with no feature selection.

关键词： antenna modeling artificial neural network(ANN) feature selection maximal information coefficient(MIC)

来源：评论

学校读者我要写书评

暂无评论

A Novel Lightweight IoT Intrusion Detection Model Based on Self-knowledge Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 16912-16930页

作者： Wang, Zhendong Zhou, Renqiang Yang, Shuxin He, Daojing Chan, Sammy Jiangxi University of Science and Technology School of Information Engineering Ganzhou341000 China Nanchang University Software Engineering Institute Nanchang330047 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China City University of Hong Kong Department of Electrical Engineering Hong Kong

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning-based intrusion detection systems have achieved excellent results, but they tend to require high computational resources and storage space, which is not feasible for most IoT devices. In this paper, we propose a lightweight intrusion detection model based on self-knowledge distillation, namely TBCLNN, which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm for dimensionality reduction of traffic features. We use lightweight convolution, such as Tied Block Convolution (TBC), to design lightweight neural network models with residual and inverse residual structures. Moreover, we propose an improved self-knowledge distillation loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low computational resources, making it suitable for resource-constrained IoT intrusion detection. © 2014 IEEE.

关键词： Network intrusion

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：