检索结果-内蒙古大学图书馆

MVLA-Net:A Multi-View Lesion Attention Network for Advanced Diagnosis and Grading of Diabetic Retinopathy

computers, Materials & Continua 2025年第4期83卷 1173-1193页

作者： Tariq Mahmood Tanzila Saba Faten S.Alamri Alishba Tahir Noor Ayesha Artificial Intelligence and Data Analytics(AIDA)Lab College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Information Sciences University of EducationVehari CampusVehari61100Pakistan Department of Mathematical Sciences College of SciencePrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia Shifa College of Medicine Shifa Tameer-E-Millat UniversityIslamabad44000Pakistan Center of Excellence in Cyber Security(CYBEX) Prince Sultan UniversityRiyadh11586Saudi Arabia

Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic *** traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic *** the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data,dual-modal diabetic retinopathy grading methods offer superior ***,the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to multi-scale *** paper addresses these issues by focusing on multi-scale retinal vessel segmentation,dual feature fusion,data augmentation,and attention-based *** proposed model aims to improve comprehensive segmentation for retinal images with varying vessel *** employs a dual-branch parallel architecture that integrates a transformer encoder with a convolutional neural network encoder to extract local and global information for synergistic saliency *** that,the model uses residual structures and attention modules to extract critical lesions,enhancing the accuracy and reliability of diabetic retinopathy *** evaluate the efficacy of the proposed approach,this study compared it with other pre-trained publicly open models,ResNet152V2,ConvNext,Efficient Net,DenseNet,and Swin Transform,with the same developmental *** models achieved approximately 85%accuracy with the same image preparation ***,the proposed approach outperforms and optimizes existing models by achieving an accuracy of 99.17%,99.04%,and 99.24%,on Kaggle APTOS19,IDRiD,and EyePACS datasets,*** results support the model’s utility in helping ophthalmologists diagnose diabetic retinopathy more rapidly and accurat

关键词： Diabetic retinopathy grading retinal vessel segmentation dual-modal deep learning attention mecha-nism health risks

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Machine Learning Approach for Heart Disease Prediction 5

An Unsupervised Machine Learning Approach for Heart Disease ...

引用

5th International Conference on Artificial Intelligence and Data sciences, AiDAS 2024

作者： Loh, Wing Son Lim, Yu Jiun Ling, Lloyd Chin, Ren Jie Lee, Chen Kang Lee, Ming Jie Universiti Tunku Abdul Rahman Department of Mathematical and Engineering Sciences Lee Kong Chian Faculty of Engineering and Science Kajang43000 Malaysia Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Department of Civil Engineering Kajang43000 Malaysia Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Department of Internet Engineering and Computer Science Kajang43000 Malaysia

ISBN: (纸本)9798331528553

Cardiovascular diseases (CVDs) persist as a primary cause of mortality on a global scale, necessitating effective prediction methods. This study presents a novel modelling approach utilizing the Self-Organizing Map (SOM), an unsupervised machine learning approach, for CVD prediction. The SOM model employed to analyze and cluster patient data based on intrinsic patterns without predefined labels, enabling the identification of high-risk individuals. Results demonstrated that the SOM model effectively differentiates between healthy and at-risk patients, offering a robust approach for early detection. The SOM presented to be the best predictive model for the CVD data prediction with the highest accuracy (84.44%);precision (89.13%);recall (82.00%);F1-score (85.42%). The U-Matrix of SOM as a visualization tool provided insightful representations that highlighted two discernible clusters, effectively illustrating the health status of individuals with similar health conditions concerning CVD. This facilitates a better understanding and management of CVD. The research findings suggested the potential of integrating SOM into clinical workflows, offering a potent tool for healthcare professionals in the fight against CVD. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

LIMIT THEOREMS FOR β-LAGUERRE AND β-JACOBI ENSEMBLES

引用

Acta Mathematica Scientia 2022年第5期42卷 2025-2039页

作者： Naqi HUANG Yutao MA Faculty of Electrical Engineering Mathematics and Computer ScienceDelft University of TechnologyMekelweg 42628 CD DelftThe Netherlands School of Mathematical Sciences&Laboratory of Mathematics and Complea Systems of Ministry of Education Beijing Normal UniversityBeijing 100875China

We use tridiagonal models to study the limiting behavior of β-Laguerre and β-Jacobi ensembles,focusing on the limiting behavior of the extremal eigenvalues and the central limit theorem for the two *** the central limit theorem of β-Laguerre ensembles,we follow the idea in[1]while giving a modified version for the generalized *** we use the total variation distance between the two sorts of ensembles to obtain the limiting behavior of β-Jacobi ensembles.

关键词： beta-ensembles largest and smallest eigenvalues central limit theorem total variationdistance

来源：评论

学校读者我要写书评

暂无评论

Teaching pentesting to social sciences students using experiential learning techniques to improve attitudes towards possible cybersecurity careers 22

Teaching pentesting to social sciences students using experi...

引用

22nd European Conference on Cyber Warfare and Security, ECCWS 2023

作者： Melnikovas, Aleksandras Lugo, Ricardo G. Maennel, Kaie Brilingaite, Agne Sutterlin, Stefan Juozapavicius, Ausrius General Jonas Zemaitis Military Academy of Lithuania Lithuania Faculty of Health Welfare and Organisation Ostfold University College Norway School of Information Technology Tallinn University of Technology Tallinn Estonia Institute of Computer Science Vilnius University Vilnius Lithuania School of Computer and Mathematical Sciences The University of Adelaide Adelaide Australia Department of Information Security and Communication Technology Norwegian University of Science and Technology Norway Faculty of Computer Science Albstadt-Sigmaringen University Sigmaringen Germany

ISBN: (纸本)9781914587702

Labor market analysis shows that there is a significant shortage of experienced cybersecurity professionals, and this trend is expected to continue in the future. In addition, young people who are reluctant to choose STEM subjects in school typically do not see cybersecurity as a part of their future because they believe it demands exclusive technical knowledge that is beyond their reach. We aimed to change this perception among students of the social sciences, assuming that by providing social science students with the basics of cybersecurity, it would be possible to raise their awareness and encourage them to consider this field as a potential career option. Our team has designed a concise technical course based on Kolb's model that employs experiential learning to provide students with a basic knowledge of ethical intrusion (penetration testing). During the 32-hour subject, cadet officers with no prior IT education experienced all the steps of hacking both into a remotely accessible and physically accessible computer, including initial reconnaissance, vulnerability scanning, exploitation, and privilege escalation. A hands-on practical task of breaking into a highly vulnerable remote computer allowed for the evaluation of knowledge and skills as well as the reinforcement of learning experiences. In order to assess how the students' perceptions of the cybersecurity profession have changed based on the theory of planned behavior, they were asked to provide feedback immediately after the course and one year later. The results indicate that the short, technically challenging, but practical course based on experiential learning had a significant and positive effect on participants' attitudes: They were substantially more likely to consider cybersecurity as a future career, and some of them began participating in other cybersecurity courses or activities. It is reasonable to assume, therefore, that providing similar technical courses to social science students will enco

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Machine Learning Approaches in Detecting IoT-Botnet Attacks

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第19期17卷 136-146页

作者： Aljammal, Ashraf H. Qawasmeh, Ahmad Mughaid, Ala Taamneh, Salah Wedyan, Fadi I. Obiedat, Mamoon Department of Computer Science and Applications Prince Al Hussein bin Abdullah II Faculty of Information Technology The Hashemite University Zarqa Jordan Department of Information Technology Prince Al Hussein bin Abdullah II Faculty of Information Technology The Hashemite University Zarqa Jordan Department of Engineering Computing and Mathematical Sciences Lewis University RomeovilleIL United States

Botnets are today recognized as one of the most advanced vulnerability threats. Botnets control a huge percentage of network traffic and PCs. They have the ability to remotely control PCs (zombie machines) by their creator (BotMaster) via Command and Control (C&C) framework. They are the keys to a variety of Internet attacks such as spams, DDOS, and spreading malwares. This study proposes a number of machine learning techniques for detecting botnet assaults via IoT networks to help researchers in choosing the suitable ML algorithm for their applications. Using the BoT-IoT dataset, six different machine learning methods were evaluated: REPTree, RandomTree, RandomForest, J48, metaBagging, and Naive Bayes. Several measures, including accuracy, TPR, FPR, and many more, have been used to evaluate the algorithms’ performance. The six algorithms were evaluated using three different testing situations. Scenario-1 tested the algorithms utilizing all of the parameters presented in the BoT-IoT dataset, scenario-2 used the IG feature reduction approach, and scenario-3 used extracted features from the attacker’s received packets. The results revealed that the assessed algorithms performed well in all three cases with slight differences. © 2023 by the authors of this article. Published under CC-BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Exploring Social Ties in Informal Conversations about ASD and ADHD: A Graph-Based Approach

Exploring Social Ties in Informal Conversations about ASD an...

引用

Omni-layer Intelligent Systems (COINS), International Conference on

作者： Naghmeh Jamali Mobin Nesari Zahra Rezvani School of Computer Science Institute for Research in Fundamental Sciences (IPM) Department of Computer Sciences Shahid Beheshti University (SBU) Faculty of Mathematical Sciences School of Computer Science Alzahra University Tehran Iran

Studying society from a network perspective involves examining the relationships and interactions among individuals within a society. Informal conversations about medical issues especially in children's neurodevelopmental disorders (NDD) can build a strong relationship that comes from a common problem. This study assesses the ability of novel graph-based approaches to explore how informal conversations about NDD in question-answering forums can create and grow a substantial dynamic of flows. After preparing and cleaning our dataset, called PerSNA, the network is built based on the questions and answers exchanged. The various features of graphs were extracted based on graph theory. The results indicated that although the number of nodes and edges in these networks is increasing quadratically, the networks are becoming islanded. The utilization of a graph-based analysis technique to examine informal discussions surrounding prevalent topics such as neurodevelopmental disorders represents a novel and promising approach for investigating community behaviors. This analytical method has the potential to facilitate our research efforts and offer a visual means for evaluating the data. Our study followed rigorous protocols to protect the privacy of participants during both data collection and analysis. Our dataset is private but codes are available at https://***/orgs/Persian-SNA/repositories

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-trained language models in Spanish for health insurance coverage 5

Pre-trained language models in Spanish for health insurance ...

引用

5th Workshop on Clinical Natural Language Processing, ClinicalNLP 2023. held at ACL 2023

作者： Aracena, Claudio Rodríguez, Nicolás Rocco, Victor Dunstan, Jocelyn Faculty of Physical and Mathematical Sciences University of Chile Chile Millennium Institute Foundational Research on Data Chile Chilean Safety Association Chile Department of Computer Science Catholic University of Chile Chile Institute for Mathematical and Computational Engineering Catholic University of Chile Chile Center for Mathematical Modeling University of Chile Chile

ISBN: (纸本)9781959429883

The field of clinical natural language processing (NLP) can extract useful information from clinical text. Since 2017, the NLP field has shifted towards using pre-trained language models (PLMs), improving performance in several tasks. Most of the research in this field has focused on English text, but there are some available PLMs in Spanish. In this work, we use clinical PLMs to analyze text from admission and medical reports in Spanish for an insurance and health provider to give a probability of no coverage in a labor insurance process. Our results show that fine-tuning a PLM pretrained with the provider's data leads to better results, but this process is time-consuming and computationally expensive. At least for this task, fine-tuning publicly available clinical PLM leads to comparable results to a custom PLM, but in less time and with fewer resources. Analyzing large volumes of insurance requests is burdensome for employers, and models can ease this task by pre-classifying reports that are likely not to have coverage. Our approach of entirely using clinical-related text improves the current models while reinforcing the idea of clinical support systems that simplify human labor but do not replace it. To our knowledge, the clinical corpus collected for this study is the largest one reported for the Spanish language. © 2023 Association for Computational Linguistics.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Design of the Shewhart Median Scheme with the Percentile-Based Approach 2022

Design of the Shewhart Median Scheme with the Percentile-Bas...

引用

11th International Conference on Software and computer Applications, ICSCA 2022

作者： Chong, Zhi Lin Teoh, Wei Lin Lim, Sok Li Yeong, Wai Chung Chew, XinYing Department of Mathematical and Actuarial Sciences Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Jalan Sungai Long Bandar Sungai Long Kajang43000 Malaysia School of Mathematical and Computer Sciences Heriot-Watt University Malaysia Putrajaya62200 Malaysia Institute of Mathematical Sciences Faculty of Science Universiti Malaya Kuala Lumpur50603 Malaysia School of Mathematical Sciences Sunway University Petaling Jaya47500 Malaysia School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia

ISBN: (纸本)9781450385770

In this article, we examine the design of the Shewhart median scheme using the recently proposed percentile-based (PL) approach and compare it with the average run length (ARL) and median run length (MRL) approaches. The PL approach allows the design of control schemes where practitioners can ensure the desired conditions on the in-control (IC) and out-of-control (OOC) run length (RL) performances satisfied with chosen probabilities. In other words, using the PL approach, we can guarantee the IC and OOC RL performances with desired probabilities. In addition, we examine the IC and OOC performances of the Shewhart median scheme based on the ARL, MRL, and PL approaches in detail. We conclude that the PL approach significantly improves the IC performance of the Shewhart median scheme compared to the ARL approach, without sacrificing much OOC performance when d = 1.5. Moreover, the MRL method can be treated as a particular case of the PL approach, i.e., the MRL is the 50th percentile of the RL distribution. © 2022 ACM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conley-Morse-Forman theory for generalized combinatorial multivector fields on finite topological spaces

引用

Journal of Applied and Computational Topology 2023年第2期7卷 139-184页

作者： Lipiński, Michał Kubica, Jacek Mrozek, Marian Wanner, Thomas Division of Computational Mathematics Faculty of Mathematics and Computer Science Jagiellonian University ul. St. Łojasiewicza 6 Kraków 30-348 Poland Department of Mathematical Sciences George Mason University Fairfax 22030 VA United States

We generalize and extend the Conley-Morse-Forman theory for combinatorial multivector fields introduced in Mrozek (Found Comput Math 17(6):1585–1633, 2017). The generalization is threefold. First, we drop the restraining assumption in Mrozek (Found Comput Math 17(6):1585–1633, 2017) that every multivector must have a unique maximal element. Second, we define the dynamical system induced by the multivector field in a less restrictive way. Finally, we also change the setting from Lefschetz complexes to finite topological spaces. Formally, the new setting is more general, because every Lefschetz complex is a finite topological space, but the main reason for switching to finite topologcial spaces is because the latter better explain some peculiarities of combinatorial topological dynamics. We define isolated invariant sets, isolating neighborhoods, Conley index and Morse decompositions. We also establish the additivity property of the Conley index and the Morse inequalities. © 2022, The Author(s).

关键词： Combinatorial vector field Conley theory Discrete Morse theory Finite topological space Isolated invariant set

来源：评论

学校读者我要写书评

暂无评论

TPFL: Tsetlin-Personalized Federated Learning with Confidence-Based Clustering

arXiv

引用

arXiv 2024年

作者： Gohari, Rasoul Jafari Aliahmadipour, Laya Valipour, Ezat Department of Computer Science Shahid Bahonar University of Kerman Kerman Iran Department of Computer Science Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran Department of Computer Science Faculty of Mathematical Sciences and Statistics Malayer University Malayer Iran Department of Applied Mathematics Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran

The world of Machine Learning (ML) has witnessed rapid changes in terms of new models and ways to process users' data. The majority of work that has been done is focused on Deep Learning (DL) based approaches. However, with the emergence of new algorithms such as the Tsetlin Machine (TM) algorithm, there is growing interest in exploring alternative approaches that may offer unique advantages in certain domains or applications. One of these domains is Federated Learning (FL), in which users' privacy is of utmost importance. Due to its novelty, FL has seen a surge in the incorporation of personalization techniques to enhance model accuracy while maintaining user privacy under personalized conditions. In this work, we propose a novel approach called TPFL: Tsetlin-Personalized Federated Learning, in which models are grouped into clusters based on their confidence towards a specific class. In this way, clustering can benefit from two key advantages. Firstly, clients share only what they are confident about, resulting in the elimination of wrongful weight aggregation among clients whose data for a specific class may not have been enough during the training. This phenomenon is prevalent when the data are non-Independent and Identically Distributed (non-IID). Secondly, by sharing only weights towards a specific class, communication cost is substantially reduced, making TPLF efficient in terms of both accuracy and communication cost. The TPFL results were compared with 5 other baseline methods;namely FedAvg, FedProx, FLIS, IFCA and FedTM. The results demonstrated that TPFL performance was better than baseline methods with 98.94% accuracy on MNIST, 98.52% accuracy on FashionMNIST and 91.16% accuracy on FEMNIST dataset. © 2024, CC BY.

关键词： Federated learning

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：