检索结果-内蒙古大学图书馆

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

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

A Methodical Approach to Healthcare Cybersecurity: Handling Current Risks and Advancements 6

A Methodical Approach to Healthcare Cybersecurity: Handling ...

引用

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

作者： Husain Bathushaw, M. Nagasundaram, S. Department of Computer Applications VELS Institute of Science Technology and Advanced Studies Pallavaram Chennai600117 India

ISBN: (纸本)9798331522667

The methods were evaluated using machine learning-driven interruption detection, blockchain-enhanced access control for inconsistency localization, and structured threat insight data in a simulated healthcare environment. With an accuracy range of 0.88-0.94 and lift specified between 0.75 and 1, knowledge values ranging from.86 to.92, and F1 scores between and above, the test results demonstrated that all computations were possible. BACA strengthened access control with blockchain;ADA surpassed expectations in identifying discrepancies;TIAA succeeded in risk insights management;and ML-IDS achieved outstanding results in intrusion detection. A comparison with related research highlights the significance of these algorithms in tackling specific cybersecurity issues in the healthcare sector. Because the proposed algorithms provide a holistic approach to safeguard confidential health information, ensure the validity of assessment models, and strengthen organizations against a range of dynamic cyberthreats, they are pertinent to the expanding discussion about cybersecurity in the healthcare industry. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Enhancing Car Pooling Systems Transactions using Consortium Blockchain-based Randomized Integrity Distributed Exchange Approach 8

Enhancing Car Pooling Systems Transactions using Consortium ...

引用

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

作者： Wessly, J. Durga, R. VEL'S Institute of Science Technology and Advanced Studies Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798350367904

Ridesharing is a process of optimizing fuel usage by enabling multiple individuals to share a vehicle while traveling along the same route. It allows frequent travelers to share their trips with others, resulting in reduced travel expenses and decreased traffic congestion. Many current vehicle possibilities depend on centralized authority privileges to perform, making systems susceptible to precise points of failure and privacy concerns from internal and external attackers. The centralized model of ride-sharing zones has raised significant concerns about data privacy, security, and transparency. In addition, traditional Car Pooling Systems (CPS) may lead to car owners misusing customer data. In order to tackle this issue, the new approach in the novel introduces the Consortium Blockchain-based Randomized Integrity Distributed Exchange (CB-RIDE) approach for secure CPS information sharing in the network. It starts with the utilization of a Solidarity Route Matching Scheme (SRMS) to identify the same route for CPS. Then, it encrypts the cashless transaction and trip information using the Secure Hash Algorithm 256 (SHA-256) method. Additionally, the key verifies using the Proof of Authentication (PoA) approach to decrypt the CPS information through the peer end. The proposed approach utilizes the decentralized nature of blockchain to protect users' trip and payment information and ensure the immutability of their transactions ledger. The experimental result demonstrates the proposed efficiency in terms of security and authentication performance compared to other methods. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence based Food Nutrients Recommendation System using Enhanced Customer Behavior Learning Approaches 8

Artificial Intelligence based Food Nutrients Recommendation ...

引用

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

作者： Jeyanthi, P. Durga, R. VEL'S Institute of Science Technology and Advanced Studies Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798350367904

Digital marketing has made significant steps in leveraging advanced technologies such as machine learning to provide personalized recommendations to food and nutritional product companies. Artificial Intelligence (AI), a branch of computer science aimed at imitating thought processes, learning abilities and knowledge management, is increasingly used in experimental nutrients recommendation. The food and nutrition product industry, using data science techniques to recommend products based on specific needs and preferences. Previous method analysis the kids' food product analysis failed in feature analysis based on product buying consumer behavior in digital marketing. To overcome further problems, a new method called Spectral Spider Optimization with Fuzzy Neural Network (SSO-FNN) with Support Vectored Neural Networks (SVN2) to advertise the best food items using maximum threshold values for selecting the best features is proposed. The SVN2 is prediction result based on recommendation food, accuracy, precision, recall, f1-score, and error rate and time complexity. These metrics uses confusion matrix evaluation and its outperforms the previous approaches. © 2024 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Predict Cardiovascular Disease with Extra Trees Classifiers and Particle Swarm Optimization 8

A Novel Approach to Predict Cardiovascular Disease with Extr...

引用

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

作者： Ezhilvani, G. Thailambal, G. VEL'S Institute of Science Technology and Advanced Studies Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798350367904

Research indicates a progressive rise in mortality rates associated with Cardio-vascular disease. The primary causes of heart diseases and reduced blood flow through vessels stem from stress and unhealthy lifestyles. The World Health Organization suggests that current mortality rates are elevated due to widespread gadget addiction and persistent stress in daily life. Machine learning-based prediction systems have been proposed for cardiovascular diseases, leveraging their ability to uncover hidden features and complex relationships. However, these systems often lack precision in identifying the exact cause of the observed outcomes. Specifically, the study aims to enhance the predictive accuracy and robustness of the Extra Trees Classifier by employing novel data preprocessing techniques. Preprocessing helps in removing irrelevant and noisy data, thereby improving the signal-to-noise ratio and enhancing the classifier's performance. By preprocessing the data, it becomes feasible to extract and select relevant features, facilitating better discrimination between classes and boosting the classifier's predictive power. To improve features clarity the Novel Extra Trees Classifier (NETC) techniques perform advanced feature selection and data transformation approaches exploring the invisibility, aiming to further improve its predictive accuracy of 9 2. 7 % and generalization capabilities. When combined with other techniques, evaluate PSO optimization's effectiveness in enhancing cardiovascular disease prediction models, including accuracy and ROC curve analysis. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Healthcare Perspectives and In-Depth Strategy for Unifying Diverse Medical Big Data Sources 10

Harmonizing Healthcare Perspectives and In-Depth Strategy fo...

引用

10th International Conference on advanced computing and Communication Systems, ICACCS 2024

作者： Manikandan, A. Thirumal, S. Kumar, N. Vels Institute of Science Technology &advanced Studies Department of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

The healthcare sector has generated vast amounts of data, posing a significant challenge in terms of integration. Recently, deep learning frameworks have gained extensive utilization for forecasting relationships within healthcare systems. Specifically, the success of the Heterogeneous Multi-Layer Deep Learning Network (HMLDN) in seamlessly amalgamating diverse medical data for enhanced diagnostics and storage is explored in this paper. The initial discussion delves into capsule optimized networks and attention maps, laying the groundwork for their application in the formation of HMLDN to achieve efficient data integration. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Mango Disease Prediction for Smart Agiculture using Machine Learning Algorithms 8

A Mango Disease Prediction for Smart Agiculture using Machin...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Lavanya, K. Packialatha, A. Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Chennai Tamilnadu Pallavaram India

ISBN: (纸本)9798350376425

The country's economy relies heavily on agriculture, and the health of the crops is essential to its success. Crop diseases that go undetected can cost the agriculture industry. Thus early detection and identification are crucial. It is possible to avoid crop diseases from destroying the harvest if they are accurately diagnosed and detected. Because healthy and diseased plants appear identical in their early stages, farmers cannot distinguish between the two by watching the crop leaf. India exports vast mangoes, making it an economically and environmentally significant fruit. About 1500 mango species are grown in India, with over 1000 commercial types. There are a lot of diseases that harm mangoes, affecting their look, taste, and economy. The "Prediction of Disease in Mango Fruit Crops"A complex warning system that uses machine learning and IoT. One of the main objectives is to develop a system that can forecast disease outbreaks on mango fruit harvests using historical weather information and crop yield Mango trees in India are plagued by a fungus called Anthracnose, which is the most frequent disease of its kind. Anthracnose, a highly contagious fungus, requires a quick and accurate method of diagnosis. As a result, an in-depth examination of the plants is essential before initiating any control measures. This study examines machine learning(ML) and deep learning (DL) strategies for detecting and classifying mango plant diseases. The performance of ML and DL-based classification models for mango crops and their datasets and feature extraction approachesare examined in this work. Finally, a variety of issues involved in plant disease identification are explored. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Task Scheduling in the Cloud Environment Using Reinforcement Learning and Whale Optimization Algorithm 5

Multi-Objective Task Scheduling in the Cloud Environment Usi...

引用

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

作者： Mahalakshmi, V. Poornima, V. Vel's Institute of Science Technology and Advanced Studies Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798331530013

Cloud computing (CC) enables organizations and individuals to alter and revolutionize the procedure by which people obtain and utilize resources. Due to the growth of the CC, the complexity increases and the cloud systems demand an effective solution for optimal resource allocation. However, effective utilization of resources in CC systems remains a significant problem due to their scale, heterogeneity, and dynamic nature. Artificial Intelligence (AI) has grown up as an effective means to improve management of resources effectively. Task scheduling is one of the major aspects in resource allocation and this study focuses on dynamic task scheduling algorithms to effectively allocate the task to the appropriate Virtual Machines (VMs). This study examines and suggests the reinforcement learning approach with a whale optimization algorithm (RL-WOA) for efficient task allocation in the cloud environment and its performance in terms of efficiency measures in terms of QoS metrics, makespan, CPU utilization and memory usage. The implementation performed using a CloudSim simulator for demonstrating the efficiency of the suggested model. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Cloud Resource Allocation using Deep Learning Techniques-A Study 4

Cloud Resource Allocation using Deep Learning Techniques-A S...

引用

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

作者： Mahalakshmi, V. Poornima, V. Department of Computer Science Vel's Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331515720

The current era of information processing, communication, and technological advances provides resources to clients on demand. The client and service provider determine how much need there is for the resources. The fitness function and resource management strategy determine the best way to allocate cloud resources. Cloud computing (CC) is a popular technology these days with the use of centralised computing facilities. Clients can utilize these resources to finish calculations, and the CC center will provide the user with the program's processed results. CC is useful for both consumer and business users. Users can save computing expenditures by avoiding the need to buy numerous PCs by investing in a cloud server. In huge-scale distributed computing, allocation of resources is essential as networks of machines face challenging optimization issues. This study is to analyse and evaluate the cloud resource optimization techniques such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), (Long Short term memory (LSTM) and Reinforcement learning (RL) for the allocation of resources in cloud. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Utilizing support vector machines for predictive analytics in chronic kidney diseases

引用

Materials Today: Proceedings 2022年 81卷 951-956页

作者： Shanthakumari, A.S. Jayakarthik, R. Department of Computer Science Vels Institute of Science Technology and Advanced Studies Tamilnadu Chennai India

Chronic kidney disease (CKD), due to rising patients, the high probability of deterioration towards end-stage renal disease and inaccurate estimates of morbidity and mortality, constitutes a heavy burden on the sanitary infrastructure. The aim of this research is to build a model for machine-learning, which uses comorbidity and data on drugs and predicts population prevalence. Predictive health care prediction using machine learning is a daunting activity to help clinicians assess the precise therapies for life-saving. In this paper, the study applies machine learning method in combination with ensemble learning for estimation of chronic kidney disease with clinical evidence. They are based on chronic kidney disease datasets and the efficiency of these models is compared to choose the best classifier for chronic kidney disease prediction. The comparative analysis is estimated in terms of various metrics like classification accuracy, f-measure, percentage error, etc. The results of simulation shows that the proposed ensemble machine learning classifier namely Ensemble Support Vector Machine predicts well the chronic kidney disease from the datasets than other existing ensemble methods. © 2021

关键词： Support vector machines

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：