检索结果-内蒙古大学图书馆

Automated Brain Tumor Diagnosis Using Deep Residual U-Net Segmentation Model

computers, Materials & Continua 2023年第1期74卷 2179-2194页

作者： R.Poonguzhali Sultan Ahmad P.Thiruvannamalai Sivasankar S.Anantha Babu Pranav Joshi Gyanendra Prasad Joshi Sung Won Kim Department of Computer Science and Engineering Periyar Maniammai Institute of Science and TechnologyThanjavur613403India Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharjSaudi Arabia Department of Computer Science and Engineering Jain Deemed to-be UniversityBangalore560069India Department of Neurology Annapurna Neuro HospitalKathmandu44600Nepal Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-siGyeongbuk-do38541Korea

Automated segmentation and classification of biomedical images act as a vital part of the diagnosis of brain tumors(BT).A primary tumor brain analysis suggests a quicker response from treatment that utilizes for improving patient survival *** location and classification of BTs from huge medicinal images database,obtained from routine medical tasks with manual processes are a higher cost together in effort and *** automatic recognition,place,and classifier process was desired and *** study introduces anAutomatedDeepResidualU-Net Segmentation with Classification model(ADRU-SCM)for Brain Tumor *** presentedADRUSCM model majorly focuses on the segmentation and classification of *** accomplish this,the presented ADRU-SCM model involves wiener filtering(WF)based preprocessing to eradicate the noise that exists in *** addition,the ADRU-SCM model follows deep residual U-Net segmentation model to determine the affected brain ***,VGG-19 model is exploited as a feature ***,tunicate swarm optimization(TSO)with gated recurrent unit(GRU)model is applied as a classification model and the TSO algorithm effectually tunes *** performance validation of the ADRU-SCM model was tested utilizing FigShare dataset and the outcomes pointed out the better performance of the ADRU-SCM approach on recent approaches.

关键词： Brain tumor diagnosis image classification biomedical images image segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Efficacy of Machine Learning Methods in Phishing Detection: A Comparative Analysis 3

Evaluating the Efficacy of Machine Learning Methods in Phish...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Saraswathi, P. Keerthi, S. Reshmika, K.S. Gourav Pritham, G.R. Prabha, M. Dhiyanesh, B. Velammal College of Engineering and Technology Department of Information Technology Madurai India Srm Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354348

In the field of cybersecurity, the ongoing issue of phishing attacks is still of utmost concern because it puts both individuals and companies at serious risk. In order to prevent these fraudulent efforts and protect sensitive data, it is essential to implement effective detection and mitigation mechanisms. This research undertakes a thorough comparative evaluation of various machine learning models designed for phishing detection. Through a review of the literature on phishing detection techniques, we highlight the need for a methodical comparison analysis to identify the most effective strategies. In order to close this gap, we carefully assess the effectiveness of well-known machine learning methods, including Neural Networks, Gradient Boosting, XGBoost, Decision Trees, Random Forests, Support Vector Machines (SVM), and Logistic Regression. Using datasets from reliable sources, such as the PhishTank open-source service and the University of New Brunswick's dataset, we create a balanced dataset with 5000 authentic URLs and the same amount of phishing URLs. Our approach includes thorough feature extraction and preprocessing steps to guarantee the accuracy and applicability of the dataset. To evaluate each model's effectiveness, key performance indicators such F1-score, precision and recall are used. Our findings highlight subtle variations in the models' functionality and provide insight into their advantages and disadvantages for phishing detection. Additionally, we use visualisation approaches to explain each model's outputs, which offer deeper insights into the operational dynamics of each model. Our results reveal subtle differences in the performance of the models, explaining their various advantages and disadvantages in the field of phishing detection. The resulting comparative study provides useful information about the effectiveness of machine learning techniques, which helps decision-makers in practical deployment settings. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

ASMA: An Advanced Secure Messaging Application

引用

Recent Advances in computer science and Communications 2022年第5期15卷 786-793页

作者： Gupta, Ankur Prabhat, Purnendu Sharma, Arun Department of Computer Science and Engineering Model Institute of Engineering and Technology Jammu India

Background: User-generated digital content, typically from mobile devices, can be of a personal nature. There have been several instances in which this personal content, including but not limited to, photographs, videos, messages and personal information, has been misused by the recipients. The misuse has ranged from violating privacy through unauthorized sharing to manipulating/modifying the original content and finally forgery and fraud. Objectives: The study aims to create an Advanced Secure Messaging Application (ASMA), allowing personal digital content to be shared across mobile devices in a secure, controlled and privacy-preserving manner. The application allows the user to explicitly specify a micro-policy to control the way digital content sent by the user, is consumed, shared or modified by the recipient(s). The users should be able to check the veracity of a shared news item besides controlling group formation and enforcing content sharing guidelines within a group. Methods: A micro-policy based novel mechanism is introduced for exercising fine-grained control over the manner in which digital content generated by users is shared and distributed among their contacts. Fact-checking is supported by cross-checking the message content against credible news sources. Results: Measurements of message throughput show a consistent and manageable overhead, due to a per-message micro-policy travelling with the message data compared to traditional message sharing applications. The high user-ratings received from users in a pilot test establish acceptance of the app and the need for its advanced features. Moreover, the overheads in implementing additional security features are imperceptible at the user level. Conclusion: ASMA is a highly secure and privacy-preserving messaging application, as demonstrated by experimental results and the pilot usability study. It offers novel security and content control features, which are not available in existing mobile messaging appl

关键词： Digital devices

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Sentiment Analysis: Unlocking Insights in Topic-Specific Twitter Conversations 24

Deep Learning-Driven Sentiment Analysis: Unlocking Insights ...

引用

6th Asia Conference on Machine Learning and Computing, ACMLC 2024

作者： Taggu, Amar Dubey, Chetana Paul, Rosy Department of Computer Science and Engineering North Eastern Regional Institute of Science and Technology Nirjuli India

ISBN: (纸本)9798400710018

The current work introduces an advanced deep learning (DL) approach to perform sentiment analysis on Twitter, focusing on topic-specific contexts. Traditional sentiment analysis models often fall short in accurately interpreting the diverse and context-sensitive nature of social media language. The proposed approach utilizes cutting-edge neural network architectures, including convolutional neural networks (CNNs) and bidirectional long short-term memory networks (BiLSTMs), to effectively capture the complex linguistic patterns and sentiment nuances within tweets. By incorporating topic modeling techniques, the model's ability to discern sentiment in relation to specific subjects is enhanced. Extensive experiments using a variety of datasets demonstrate that this method significantly outperforms existing baseline models in terms of accuracy and robustness. Use of deep learning yields better accuracy in both topic detection (96% (DL) vs 86% [6] vs 82% (basline)) and sentiment analysis (87%(DL) vs 82% [3] vs 76% (basline)). The results suggest that this deep learning-based approach not only improves sentiment classification but also offers valuable insights into public opinion on various topics. © 2024 Copyright held by the owner/author(s).

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Adaptable Individualized Investment Recommendation System

Adaptable Individualized Investment Recommendation System

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Sabiyath Fatima, N. Noor Alleema, N. Mahesh, C. Umanesan, R. Senthil, K. Santhosh Kumar, P. B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Information Technology Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798331522988

Internetization has played a massive role in the rapid development and growth of the financial investment industry. Due to the rapid development, there is a demand for more financial knowledge services to help make well-informed investments. Accessing and conducting investments through online financial platforms has made the field highly accessible. This has made the investment recommendation system a popular research area. Personalized recommendations will help the user make investments that are safe for their financial situation and also suit their particular needs and interests. This work proposes a method where investment recommendations are given based on three key factors. The user interest sectors, risk appetite-based clustering, and market sentiment of the stock. These factors will be calculated by the use of Lasso regression, SVM, stepwise regression, generalized boosted regression, random forest, ridge regression and fuzzy clustering. Based on these three factors, the proposed method results in investment recommendations made for users that are personalized to the specific user. This allows existing investors to gain new opportunities and new investors to start investing with lower amount of risk using the information available. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Effectiveness of Collaborative Filtering Similarity Measures: A Comprehensive Review 2

Evaluating the Effectiveness of Collaborative Filtering Simi...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Chowdhury, Pradipto Sinha, Bam Bahadur Department of Computer Science and Engineering Kalinga Institute of Industrial Technology Orissa 751024 India Department of Computer Science and Engineering Indian Institute of Information Technology Ranchi Jharkhand834010 India

Recommendation systems play a pivotal role in assisting users in fnding items, services, or products that align with their preferences. These systems typically rely on personal parameters, user reviews, or a combination of both to make apt recommendations. This survey article delves into the topic of similarity measures in collaborative recommender systems, with a particular emphasis on exploring various existing measures and their implications. The article examines different similarity measures namely "Pearson Correlation Coefficient, Vector similarity, Adjusted Cosine, Jaccard, few distance-based metrics, PIP similarity, and Bhattacharyya measure", the heart of collaborative filtering. The PCC similarity metric outperformed other approaches as per the comparative analysis results. This paper covers the mathematical basis, practical applications, limitations, and implications of the aforementioned approaches for recommendation systems. The paper emphasizes the critical role of selecting the right measure, as it directly influences the recommendation process's accuracy and effectiveness. © 2024 Elsevier B.V.. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Customized Movie Recommendation for Enhanced Entertainment

Customized Movie Recommendation for Enhanced Entertainment

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Minu, M.S. Talapalli, Srikar Chevuri, Saahithi Medhasri, T.S. SRM Institute of Science and Technology Department of Computer Science Engineering Ramapuram Chennai India SRM Institute of Science and Technology Department of Computer Science Engineering with Specialization in Big Data Analytics Ramapuram Chennai India

ISBN: (纸本)9798331542344

The surging popularity of online movie databases has created a challenge for viewers: choosing a film from a massive library can be overwhelming. In this paper, it proposes to design a new hybrid movie recommendation powered by machine learning techniques as a solution to improve user experience. Among those techniques, two are combined into this paper: content-based filtering, using the real features of a movie such as genre and a director, and collaborative filtering, which uses the rating provided by users. This hybrid approach thus improves the intrinsic weaknesses that reside in both these methods individually. On the other hand, content-based filtering tends to reduce exploration to movies of the exact type one is doing well at, whereas, inversely, collaborative filtering settings often mean that a user will be exposed only to films within his or her already-recognized taste profile. It is expected that the proposed hybrid system will solve both problems by balancing this line between exploring familiar cinematic territory and making new recommendations based on both user preferences and the entire collective intelligence of the user base. The approach would aim to enrich user satisfaction by facilitating the selection of movies and providing a richer and more diversified movie-viewing experience. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Contemporary Framework for Detection of Phishing Website for Cyber Societal Safety

引用

SN computer science 2025年第4期6卷 1-10页

作者： Lakshmi, B.N. Dhanalakshmi, B.K. Reddy, K. Tharun Department of Computer Science Engineering BMS Institute of Technology and Management Karnataka Yelahanka Bangalore 560064 India

In today’s digital age, phishing is a significant threat. It is a clever approach in which propagation of a website is done, and customers are enticed to a false website where customers are asked to enter critical personal information. Phishing website detection is clever and successful method that uses data mining algorithms to categories and associate websites. Detecting phishing websites is challenging since most of these methods are unable of making a dynamically right judgement about whether an encountered website is a phishing website or not. To determine efficiency, accuracy, the rules created, and speed, all rules and variables for grading phishing websites, also their relationships, were described and categorized. These algorithms are created. To identify phishing websites, we utilize a hybrid approach that includes developing description framework models for resource and categorizing websites using group learning algorithms. We utilize supervised learning methods to train our software. This strategy receives a high favorable rating, which is certainly noteworthy. We also used software to eliminate features that would allow us to estimate the frequency of each job in the dataset, a random forest classifier to cope with missing data sets. Our method will detect by utilizing the URL of website as input, helping us to have a good understanding of the factors that influence detection. The approach should be chosen as it increases accuracy in most situations. We get promising accuracy when our system investigates the strength of the Random Forest Algorithm and ensemble learning techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cyber safety KNN Learning techniques Random forest algorithm Society SVM Web phishing

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Detecting Malware Using Autoencoder

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第8期51卷 1051-1059页

作者： Panchagnula, Venu Madhav Satya Keerthi, N.V.L.Ch. Surekha, S. Sujatha, R. Veeraiah, Duggineni Ramesh, Eluri Lakshmi, B. Electronics and Communication Engineering Department Prasad V Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada India Computer Science and Engineering Department Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur India AIML Department Vignana Bharathi Institute of Technology Ghatkesar Hyderabad India Information Technology Department M. Kumarasamy College of Engineering Karur India Computer Science and Engineering Department Lakireddy Bali Reddy College of Engineering Andhra Pradesh Mylavaram India Computer Science and Engineering Department R.V.R & J. C. College of Engineering Guntur India Electronics and Communication Engineering Department Rajiv Gandhi University of Knowledge Technologies Andhra Pradesh Nuzvid India

Research in the field of malware detection is currently leaning toward methods based on artificial intelligence algorithms due to the increasing limitations of traditional detection methods and the increasing accuracy of these methods. This study therefore introduces a novel approach to malware detection. This method integrates a deep learning model's autoencoder network with a grayscale graphic depiction of malware. By looking at the autoencoder's reconstruction error, we may assess if the grey-scale picture approach is feasible to use for malware detection. Additionally, it differentiates between malicious and safe software by utilizing the autoencoder's dimensionality reduction capabilities. Using the Android dataset, our newly introduced detection model attained a 95% accuracy and maintained a consistently high F-score of approximately 95%. This outperformed more conventional methods of machine learning detection. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

IDedupNet: A MobileNetV3-Based Deep Learning Framework for Efficient Image Deduplication in Cloud Computing Environments

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 143-162页

作者： Mohiuddin, Mohd Hasan Tamilselvan, Latha Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India Department of Information & Technology B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India

Image deduplication is becoming increasingly important for cloud storage infrastructures to handle the increasing amount of multimedia material. Through increased storage efficiency, effective picture deduplication may optimize resources and save expenses. It also improves performance by facilitating quicker access, utilizing less bandwidth, and enhancing data integrity. Although heuristic-based classical deduplication techniques work well in various storage infrastructures, they cannot keep up with the dynamic nature of cloud storage resources. This study presents IDedupNet, a revolutionary DL-based framework that improves infrastructure performance in cloud computing by efficiently detecting duplicate and near-duplicate photos. Our approach leverages MobileNetV3 for feature extraction and CNN-based encodings for image deduplication, enabling it to manage duplicate photos in highly dynamic contexts efficiently. Additionally, we provide a Learning-Based Image Deduplication (LBID) approach that improves deduplication performance by extending the use of the IDedupNet model. Experimental evaluation demonstrates a high accuracy of 98.68% on benchmark datasets, consistently outperforming existing models. The underlying technique and deep learning framework may be easily integrated into real-time cloud storage systems to increase customer satisfaction and infrastructure efficiency. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Cloud storage

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：