检索结果-内蒙古大学图书馆

2nd International Conference on Multidisciplinary Engineering and Applied Science, ICMEAS 2023

作者： Usman, Tiwalade Modupe Ajibesin, Adeyemi Abel Saheed, Yakub Kayode Nsang, Augustine Shey School of Information Technology and Computing American University of Nigeria Yola Nigeria

ISBN: (纸本)9798350358834

Segmentation of the Optic Disc (OD) is a crucial procedure in detecting potential damage to the optic nerve in the retina. This is vital for the screening of Glaucoma and Diabetic Retinopathy (DR) which are the leading cause of irreversible loss of vision worldwide. However, manual segmentation is inefficient, expensive, time consuming and unsustainable. This paper presents GAPS-U-NET, a novel framework with the potential for revolutionizing clinical practice, especially in the context of early detection of Glaucoma and DR. It is a modified U-Net architecture that adopts CNN models as the backbone of the encoder path and applies the upsampling operation of periodic shuffling convolution with gating attention for fast convergence of the network and accurate segmentation. The proposed method overcomes three major challenges of existing encoder-decoder techniques for image segmentation, which are shallow networks, reduced feature resolution, and localization accuracy. First, we employ pretrained CNN model to gain the major benefits of very deep networks that can learn very complex functions to extract more discriminative features for OD segmentation. Then the gating attention block is added to the skip connections to ignore irrelevant regions and focus on important features of a specific region. Finally, pixel shuffling is added to improve feature resolution and segmentation accuracy. GAPS-U-NET is trained on the Indian Diabetic Retinopathy Image Dataset (IDRID) and yielded IOU of 92.83% and an accuracy of 99.71 % which shows that the proposed method can be incorporated into Glaucoma and DR screening programs. GAPS-U-NET is modular therefore it can be integrated into other medical image segmentation tasks. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Competent Medical Image Steganography using Improved Optimization Algorithm with Huffman Encoding Techniques 7

A Competent Medical Image Steganography using Improved Optim...

引用

7th International Conference on computing Methodologies and Communication, ICCMC 2023

作者： Ramapriya, B. Kalpana, Y. School of Computing Science Department of Information Technology VISTAS Chennai India

ISBN: (纸本)9781665464086

Steganography is considered a reliable solution for avoiding third-party attacks. It is the process of embedding confidential information in another image. So that, they can be sent to the user's end with full security. When it comes to data privacy and authentication, steganography techniques are essential. This proposedmedical image steganography procedure by exploiting Dual Tree-Complex Wavelet Transform based transform and image encryption procedure were proposed in this proposed work. Then an improved SSOAoptimization algorithm is engaged to detect smooth edge blocks. As a result, the selection of pixels for embedding is facilitated. Embedding the Secret data into the cover image is then done using a double matrix XOR encoding. After the embedding process, the stego image is produced. The Stego output image is further compressed with Huffman Coding which produces the stego Compressed image. The stego image is compressed for fast transmission of secret data via the wireless network. Thus, the proposed method shows the best results with high payload capacity, security, and image quality than the existing methods. Testing was performed on PSNR, MSE, IF, and SSIM metrics to verify the performance of proposed methodologies. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey for Privacy-Preserving Biometrics: Recent Approaches, Challenges, and Future Directions

引用

Computers, Materials & Continua 2024年第2期78卷 2087-2110页

作者： Shahriar Md Arman Tao Yang Shahadat Shahed Alanoud AlMazroa Afraa Attiah Linda Mohaisen School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China College of Computer and Information Sciences Princess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

The rapid growth of smart technologies and services has intensified the challenges surrounding identity authenti-cation *** credentials are increasingly being used for verification due to their advantages over traditional methods,making it crucial to safeguard the privacy of people’s biometric data in various *** paper offers an in-depth exploration for privacy-preserving techniques and potential threats to biometric *** proposes a noble and thorough taxonomy survey for privacy-preserving techniques,as well as a systematic framework for categorizing the field’s existing *** review the state-of-the-art methods and address their advantages and limitations in the context of various biometric modalities,such as face,fingerprint,and eye *** survey encompasses various categories of privacy-preserving mechanisms and examines the trade-offs between security,privacy,and recognition performance,as well as the issues and future research *** aims to provide researchers,professionals,and decision-makers with a thorough understanding of the existing privacy-preserving solutions in biometric recognition systems and serves as the foundation of the development of more secure and privacy-preserving biometric technologies.

关键词： Biometric modalities biometric recognition biometric security privacy-preserving security threats

来源：评论

学校读者我要写书评

暂无评论

Ensemble Machine Learning Approach for Detecting and Predicting Diabetes Mellitus Using Bagging and Stacking 4

Ensemble Machine Learning Approach for Detecting and Predict...

引用

4th IEEE International Conference on Smart Technologies in computing, Electrical and Electronics, ICSTCEE 2023

作者： Anusha Priyadharshini, C. Arul Kumaran, G. Reva University School Of Computing And Information Technology Karnataka Bangalore India

ISBN: (数字)9798350384628

ISBN: (纸本)9798350384628

The application of ensemble learning techniques more especially, bagging and stacking for better diabetes diagnosis and prediction is explored in this abstract. Due to their precision and individualized approach, advanced machine learning techniques are advantageous for diabetes, a complex metabolic illness. Here Pima Indian diabetes(PID) dataset for research, collected from the UCI machine learning Repository. The dataset contains information about 768 patients and their corresponding nine unique attributes. A novel ensemble machine learning technique for diabetes prediction such as bagging and a meta model is used in stacking to aggregate predictions from several models. A stacked model is created by combining Random Forest and Support vector machines with feature variables like age, body mass index, blood pressure, skin thickness and biochemical indicators. The accuracy of diabetes diagnosis and prediction has improved by bagging and stacking. They make it possible to identify high-risk patients early and to provide individualized therapies. This research has achieved better accuracy with random forest. As a result, the use of bagging and stacking in diabetes research has the potential to completely transform patient treatment by providing accurate risk assessments and individualized management plans. Realizing these methods' full potential in the treatment of diabetes will require further study, which will focus on improving them and addressing the problems they raise. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Crime Analysis Framework for Predicting Criminal Behavioral Patterns with Machine Learning

Crime Analysis Framework for Predicting Criminal Behavioral ...

引用

2023 IEEE Renewable Energy and Sustainable E-Mobility Conference, RESEM 2023

作者： Sham Venkat, S. Raj, Jeberson Retna Arjun, A. Srinivasulu, Senduru Gowri Jabez Sathyabama Institute of Science and Technology School of Computing Department of Information Technology Chennai India

ISBN: (纸本)9798350311327

Data analytics is critical for businesses and organizations to understand their data's behaviour, patterns and insights. Crime analysis is an important component of controlling crime rates in cities and regions based on historical data. This paper proposes a crime analysis methodology supported by machine learning techniques to predict and analyze criminal behaviour patterns. Machine learning algorithms such as Random Forest, Decision Tree, SVM, XGBoost and Multilayer Perceptron are used on the crime dataset for detailed analysis. The framework consists of three phases: data preprocessing, model training, and prediction and analysis. By analyzing crime data using Kaggle's open-source crime records, our project aims to understand crime patterns, determine the crime's severity, and identify where and when it occurred. We use the abovementioned algorithms to classify crime patterns and compare the performance accurately. Our proposed framework uses various visualization techniques to reveal crime trends and predict crimes using machine learning algorithms. Input features used in the algorithms include time, state, district, year, murder, rape, theft and dowry deaths. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network Framework for Predicting Student Drop Out in Universities 16

A Convolutional Neural Network Framework for Predicting Stud...

引用

16th IEEE AFRICON, AFRICON 2023

作者： Kendagor, Valentine Jemutai Chemwa, Geoffrey Cheruyoit, Wilson School of Computing and Information Technology Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya

ISBN: (纸本)9798350336214

The phenomenon of student attrition is common in almost all universities if not all over the world and its effects are felt at several levels be it at society level or the personal level of students who abandon the university and so forth. Most implemented machine learning frameworks for predicating university student drop-out have data validation points limitations which are not hyper-tuned from datasets used thereby not providing accurate predication of likelihood for student dropouts. Therefore, this research developed a convolutional neural network framework that predicts student attrition in relation to influential factors. The study employed a rigorous methodology to collect and preprocess data from a diverse set of universities, which was then used to train and test the CNN model. The model's performance was evaluated using various metrics, including accuracy, precision, and recall, to ensure its robustness and effectiveness in predicting student dropouts. The findings of this study can serve as a valuable resource for future research in this area. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Crime Prediction Using Decision Trees, Random Forests, and Hybrid Algorithm: A Comparative Analysis 7

Crime Prediction Using Decision Trees, Random Forests, and H...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Mwaniki, Boniface Mwalili, Tobias Ogada, Kennedy School of Computing and Information Technology Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya

ISBN: (纸本)9798350307504

Crime has devastating effects on safety and security at the individual level, community level, national level, and even at the global level. In the face of significant increase in crime rates, and the inefficiencies of traditional crime prediction systems, data mining and machine learning algorithms have emerged as important tools for retrieving, classifying and analyzing crime data. This study assessed tree-based machine learning algorithms (decision trees and random forests) used in crime data classification and prediction, developed and compared the performance of the hybrid tree-based algorithm against decision trees and random forests, using data mined from National Police database and news websites. Results revealed that accuracy of decision tree classifier was 87% on the testing dataset and 94% on the testing set, while the accuracy of random forests was 100% on the training dataset and 78% on the testing dataset. Therefore, decision trees had a higher predictive value than random forests in crime data classification and prediction. The hybrid model had slightly more predictive power (94.4%), compared to decision trees and random forests, indicating potential improvements in processing speed and accuracy as a result of hybridization. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of Computer Science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

A DECOUPLED,LINEARLY IMPLICIT AND UNCONDITIONALLY ENERGY STABLE SCHEME FOR THE COUPLED CAHN-HILLIARD SYSTEMS

引用

Journal of Computational Mathematics 2025年第3期43卷 708-730页

作者： Dan Zhao Dongfang Li Yanbin Tang Jinming Wen School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China College of Information Science and Technology Jinan UniversityGuangzhou 510632China

We present a decoupled,linearly implicit numerical scheme with energy stability and mass conservation for solving the coupled Cahn-Hilliard *** time-discretization is done by leap-frog method with the scalar auxiliary variable(SAV)*** only needs to solve three linear equations at each time step,where each unknown variable can be solved *** is shown that the semi-discrete scheme has second-order accuracy in the temporal *** convergence results are proved by a rigorous analysis of the boundedness of the numerical solution and the error estimates at different *** examples are presented to further confirm the validity of the methods.

关键词： Coupled Cahn-Hilliard system Leap-frog method Scalar auxiliary variable Error estimate

来源：评论

学校读者我要写书评

暂无评论

Data Cleansing to Enhance Quality of Multimedia Data Using Convultional Neural Networks 3

Data Cleansing to Enhance Quality of Multimedia Data Using C...

引用

3rd International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Muthusi, K.A. Cherruyoit, W.K. Rimiru, R. School of Computing and Information Technology Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya

ISBN: (纸本)9781665494007

Determining the clean-up procedures and the new ways of data cleansing for quality improvement is crucial if you want to identify data cleansing errors early and successfully address them. Data cleansing is a well-researched method for removing inaccurate labels from databases. Because of its exceptional performance, data purification technology is a fairly widespread computer technology utilized extensively in many fields. The major goal of the study was to create a framework for data purification that would improve multimedia images' quality. In order to eliminate duplicates, a Convolutional Neural Network (CNN) was used to categorize the objects in photos. The study's findings show how a Convolutional Neural Network framework may handle data purification in multimedia sources. © 2023 IEEE.

关键词： Purification

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：