检索结果-内蒙古大学图书馆

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Krishna, Nerella Venkata Anil Rama Devendra, Vicharapu Krishna, Dogiparthi Leela Srikanth, Godavari Haritha, D. Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350349900

This paper presents a thorough way to disease prediction that integrates powerful machine learning algorithms with microarray analysis of cancer gene expression. The loading, recording, and cleaning of genetic microarray data is the primary stage in the study's approach. A collection of genes crucial for illness prediction is discovered when traits are chosen based on statistical significance. The research evaluates how many classifiers, such as Gaussian Naive Bayes, Decision Tree, K-Nearest Neighbors, Multi-layer Perceptron, and Extra Trees, are influenced by increasing the number of individual genes. The selecting of essential genes and models is lead by extensive evaluation methodologies and crossvalidation procedures. The research also provides a theoretical framework, underlining the relevance of gene expression patterns in understanding and identifying disorders. The relevance of feature selection and how it influences model performance are underlined in the research. It also looks at the selected strategies and how well they function with genetic data management. The methodology's success is proved by a comparative analysis of error rates and the choice of the bestperforming software and gene set. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Analyzing AprioriTID, Apriori Hybrid, and FP Growth for Association Rules in Movie Recommender Systems 8th

Analyzing AprioriTID, Apriori Hybrid, and FP Growth for Asso...

引用

8th International Conference on Inventive Communication and Computational Technologies, ICICCT 2024

作者： Chowdary, Garapati Gaman Sai Raju, Eluri Charan Joshitha, Pala Anusree, Sunkara Shaik, Mohammed Gouse Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9789819777099

This research investigates and compares the performance of three widely used association rule mining algorithms—FP-Growth, Apriori Hybrid, and AprioriTID in the domain of movie recommender systems. The study aims to assess the efficacy of these algorithms in generating meaningful association rules and subsequently providing personalized movie recommendations based on user preferences. The experimental methodology involves the utilization of a diverse dataset encompassing user ratings, genres, and historical viewing patterns. The implications of these results are discussed, providing a foundation for further research and advancements in the field of association rule mining for personalized content recommendations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Apriori Hybrid AprioriTID Association rule mining FP-Growth Movie recommender systems Performance analysis

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis on Traffic Prediction Methods for Real-World Deployment: Challenges, Cause and Scope

A Comprehensive Analysis on Traffic Prediction Methods for R...

引用

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

作者： Sneharika, Pendyala Anvitha, Boddu Charitha Sri Sai Kumar, Arthimalla Manoj Pradeep, T. Devi, M. M. Yamuna Kumar, Sandeep Koneru Lakshmaiah Education Foundation Department Of Computer Science And Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350366846

This study provides a comprehensive overview of modern traffic analysis and congestion prediction methodologies, identifying some limitations inherent in current approaches, spanning data adequacy to algorithmic performance. It examines environmental factors and public transit disruptions as contributors to traffic congestion, emphasizing the complexity of urban traffic management. By addressing these challenges, the study aims to enhance the efficiency and adaptability of traffic management systems. Proposed solutions include predictive traffic management with AI, dynamic traffic signal control, and optimization strategies utilizing deep learning algorithms. It underscores the significance of integrating advanced technologies such as machine learning and AI into transportation infrastructure for improved accuracy and reliability. Overall, the findings offer valuable insights for future research and development in this critical field, shedding light on the current state of traffic analysis and congestion prediction. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

A comprehensive framework for secure keyword search in cloud databases through hybrid attribute-based encryption (HABE)

引用

International Journal of Information Technology (Singapore) 2025年 1-6页

作者： Arundathi, J.V.S. Satyanarayana, K.V.V. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation (KLEF) Vaddeswaram Guntur District Andhra Pradesh Guntur India

Efficient keyword search in encrypted databases is critical in cloud computing due to its computational memory and time constraints. Traditional keyword search methods often employ plaintext attributes and policies within the ciphertext policy attribute based encryption (CP-ABE) scheme, which pose security risks. Thus, the given paper introduces a hybrid integrity-based approach that enhances the CP-ABE scheme by incorporating hidden attributes and policy construction. Utilizing a novel non-linear chaotic hash algorithm alongside a hybrid attribute-based encryption (HABE) model, this framework significantly optimizes runtime and search efficiency. Experimental results demonstrate superior keyword search performance in terms of accuracy (95.47%) as compared to conventional models, proving the efficacy of the proposed approach in maintaining data security and integrity in cloud environments. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Attribute-based encryption Cloud data security Hash functions Keyword search Secret key distribution

来源：评论

学校读者我要写书评

暂无评论

Exploring Alzheimer's Disease Risk Prediction: A Data-Driven Approach with RandomForestClassifier 8

Exploring Alzheimer's Disease Risk Prediction: A Data-Driven...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Jampani, Pallavi Javvadi, Varun Raj Nandi, Varun Sai Tanuku, Sai Varun Amarendra, K. Benarji, Bejjam S. N. Koneru Lakshmaiah Education Foundation Department of Computer Science and Information Technology Andhra Pradesh Vaddeswaram India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350386578

In this work, we employ a sophisticated machine learning technique based on the RandomForestClassifier model to examine Alzheimer's disease risk prediction. The '***' and '***' full datasets, which comprise both cross-sectional and longitudinal data, serve as the basis for our study. Our research project's major purpose is to create and assess a prediction model that may identify a person's chance of getting Alzheimer's disease based on clinical and demographic characteristics. Our method entails substantial data preparation, including feature engineering, imputation of missing values, and normalization. Feature engineering is a discrete stage. Stratified cross-validation approaches are used to train and modify the RandomForestClassifier model, establishing the validity of the performance metrics. Several important results from our work include evaluations of model correctness, a thorough assessment of prediction abilities, and insights into critical components that contribute to the risk assessment of Alzheimer's disease. In this chapter, we underline how machine learning may increase Alzheimer's disease research and clinical practice, and we analyze the implications of our results for early detection and therapeutic possibilities. This paper contributes a large quantity of information to the growing corpus in the realm of Alzheimer's disease prediction. It illustrates the advantages of data-driven methods and the importance of applying powerful machine learning algorithms in order to enhance healthcare results. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Boosting Algorithms to Detect the Fake User Profiles on Instagram

Machine Learning Boosting Algorithms to Detect the Fake User...

引用

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Naik, Ds Bhupal Navya Sri, S. Meenakshi Priya, G. Satya Priya, P. Vignan's Foundation for Science Technology and Research Computer Science and Engineering Guntur India Vignan's Foundation for Science Technology and Research Department of Computer Science and Engineering Guntur India

ISBN: (纸本)9798350314946

Social media use has become a significant part of every person's daily life during the past several years. These social media sites support in the three Cs: creating, connecting, and communicating with others. Nearly 4.8 billion people use social media globally, according to use data. There are millions of individuals worldwide that spend the majority of their time on social networking websites. A variety of threats, such as bogus profiles, account hacking, safety and security problems, might arise with an increase in usage. The most popular and broadly used social networking site is Instagram. The purpose of the following paper is to identify phoney accounts of people on Instagram using machine learning boosting techniques. We developed a new set of algorithms described as ADB-CB, which includes extra tree classifier, cat boost, and Ada boost, for recognising or detecting these false user profiles. Additionally, various feature selection and reduction strategies are then used. Kaggle Instagram datasets were taken into account when evaluating the model. Catboost, Adaboost, and the extra tree classifier all performed with accuracy ratings of 96, 91.87, and 93.78 respectively. Of all boosting algorithms, the Catboost had the highest level of accuracy of 96. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Robust Hybrid Approaches for Brain Tumor Classification in Magnetic Resonance Images

引用

Journal of The Institution of Engineers (India): Series B 2023年 1-15页

作者： Krishna, S. Rama Ravela, Chittibabu Mantena, Srihari Varma Sirajuddin, Mohammad Deol, G. Joel Sunny Hyderabad India Computer Science and Engineering Koneru Lakshmaiah Education Foundation K L University Vaddeswaram India Department of Computer Science and Engineering SRKR Engineering College Bhimavaram India Department of Information Technology Kallam Haranadhareddy Institute of Technology Dasarapalem India Department of Computer Science and Engineering Kallam Haranadhareddy Institute of Technology Andhra Pradesh Dasarapalem India

Classification of brain images is a very challenging problem among the most helpful and commonly employed procedures in the medical system. Deep learning, a subset of artificial intelligence, has pioneered new techniques for automatic medical image investigation. The goal of this study was to create two deep learning-based hybrid models to segment and classify brain MRI data. The first hybrid model is a combination of Fully Convolutional Networks and Residual Networks for segmentation and classification. The second is a hybrid of SegNet for segmentation and MobileNet for classification. The analysis is based on a labelled dataset containing images of glioma, meningioma, pituitary, and no tumor. The hybrid models proposed above are built using Python. The suggested models exhibit a high accuracy of 93.9% and 91.3% for a brain MRI dataset, respectively. Furthermore, the proposed models were compared and evaluated against other existing hybrid models in terms of dice score, Positive predictive value, False predictive value, precision, recall, specificity, and F1 score. As a result, the proposed deep-learning technique can assist doctors as well as radiologists in detecting brain tumors early. © 2023, The Institution of Engineers (India).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis for Advancements in Brain Tumor Detection Model by using Machine Learning Techniques 8

Design and Analysis for Advancements in Brain Tumor Detectio...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Gulhane, Ashwini Velmurugan, A.K. Koneru Lakshmaiah Education Foundation Vaddeswaram India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India

ISBN: (纸本)9798350386578

Brain tumors pose a significant threat due to their uncontrolled cell proliferation, necessitating timely and precise treatment. Despite notable advancements, accurate segmentation and classification of brain tumors remain challenging, given the complexity of tumor characteristics such as location, shape, and size. This research study explores into the complexities of brain tumor detection using Magnetic Resonance Imaging (MRI), including discussions on tumor shape analysis, data repositories, image enhancement techniques, segmentation methodologies, feature extraction, and classification algorithms. Furthermore, this study explores the emerging field of Machine Learning (ML), including deep learning, transfer learning, and quantum machine learning, within the field of brain tumor research. By considering relevant scholarly works, this research study interprets the benefits, limitations, recent advancements, and potential opportunities for brain tumor detection. Achieving sufficient tumor segmentation accuracy, reducing false positives, and accurately categorizing tumors into benign and malignant classes holds the potential to improve patient care and treatment outcomes. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Data Redundancy, Data Phishing, and Data Cloud Backup 5

Data Redundancy, Data Phishing, and Data Cloud Backup

引用

5th IEEE International Conference on Electrical, computer and Communication Technologies, ICECCT 2023

作者： Lokesh, M. Devi, A.Keerthi Chowdary, U Dinesh Lakshmi, P.V.N.S. Divya Rao, G.Rama Koteswara Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India

ISBN: (纸本)9781665493604

Data today is extremely complex and massive in size. By taking these factors into account, machine learning and ETL techniques will find it much easier to separate useful data from unusable raw data. In web technology, OLTP and OLAP are used to manipulate data on a daily basis. During the transaction, a massive amount of data is maintained in the database or data warehouse. There was no Cloud storage to back up data in the past. Because of the significant increase in internet usage, people are sharing more of their personal information online. Cybercriminals can now access a vast amount of personal data and financial activities. Phishing is one instance of a very efficient type of cybercrime that allows offenders to trick users and obtain crucial data. Phishing has advanced into a more complex attack vector since the first known instance was published in 1990. One of the most common online fraud types now is phishing. Phishing attacks can cause serious losses for their victims, including the theft of confidential information, identities, businesses, and state secrets. This article evaluates these attacks by addressing existing phishing techniques and discussing the current state of phishing. Phishing attacks have been classified in studies based on common phishing methodologies and defences, ignoring the importance of the entire phishing lifecycle. This article provides a new, in-depth model of the anatomy of phishing attacks, including attack phases, attacker types, threats, targets, attack media, and attacking strategies. The suggested physiology would also help readers understand the lifecycle of a phishing attack, which would aid in the development of a comprehensive anti-phishing system. This will improve public awareness of phishing attacks and the methods used. New approaches are also proposed, and certain preventive measures are investigated. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Hybrid Binary Dragonfly Algorithm with Grey Wolf Optimization for Feature Selection 6th

Hybrid Binary Dragonfly Algorithm with Grey Wolf Optimizatio...

引用

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Moturi, Sireesha Vemuru, Srikanth Tirumala Rao, S.N. Mallipeddi, Sneha Ananya Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur India Department of Computer Science and Engineering Narasaraopeta Engineering College Guntur India

ISBN: (纸本)9789819933143

The curse of dimensionality produced by the fast proliferation of information science will have a detrimental impact on the machine learning model's performance. In the data mining process, feature selection is often thought of as a preprocessing technique for finding an optimal subset of features from a given collection of all features. Grey Wolf Optimizer (GWO) suffers with the problem of global optimal solution and Dragonfly Algorithm (DA) suffers from local optima. To combine the benefits of these two algorithms, an enhanced New Levy Updated Dragonfly Algorithm (NL-DA) and Grey Wolf Updated Dragonfly Algorithm (GWU-DA) are developed in this article as a wrapper-based strategy for finding the best subset of features. An improvement is made in the Levy Flight Mechanism (LFM), food and predator to improve the algorithm's randomisation, probabilistic behaviour and searching behaviour. The fitness function of NL-DA and GWU-DA is evaluated with a hybrid classifier, such as Support Vector Machine (SVM) and Deep Belief Network (DBN). The suggested NL-DA is compared to three existing algorithms and GWU-DA is compared to nine existing algorithms over eighteen datasets from the University of California, Irvine (UCI). Various evaluation metrics are utilised to assess how well the proposed algorithms perform. According to the results, enhanced NL-DA and GWU-DA are superior in terms of enhancing prediction accuracy and lowering the number of selected features. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

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：