检索结果-内蒙古大学图书馆

Assessment of Clinical Metadata on the Accuracy of Retinal Fundus Image Labels in Diabetic Retinopathy in Uganda: Case-Crossover Study Using the Multimodal Database of Retinal Images in Africa

引用

JMIR Formative Research 2024年 8卷 e59914页

作者： Arunga, Simon Morley, Katharine Elise Kwaga, Teddy Morley, Michael Gerard Nakayama, Luis Filipe Mwavu, Rogers Kaggwa, Fred Ssempiira, Julius Celi, Leo Anthony Haberer, Jessica E. Obua, Celestino Department of Ophthalmology Mbarara University of Science and Technology Mbarara Uganda Massachusetts General Hospital Center for Global Health Department of Medicine Harvard Medical School Boston MA United States Harvard Ophthalmology AI Lab Massachusetts Eye and Ear Infirmary Harvard Medical School Boston MA United States Ophthalmology Department Sao Paulo Federal University Sao Paulo Brazil Laboratory for Computational Physiology Massachusetts Institute of Technology Cambridge MA United States Faculty of Computing and Informatics Department of Information Technology Mbarara University of Science and Technology Mbarara Uganda Faculty of Computing and Informatics Department of Computer Science Mbarara University of Science and Technology Mbarara Uganda School of Public Health Makerere University Kampala Uganda Division of Pulmonary Critical Care and Sleep Medicine Beth Israel Deaconess Medical Center Harvard Medical School Boston MA United States Department of Biostatistics Harvard T.H. Chan School of Public Health Boston MA United States Department of Pharmacology Mbarara University of Science and Technology Mbarara Uganda

Background: Labeling color fundus photos (CFP) is an important step in the development of artificial intelligence screening algorithms for the detection of diabetic retinopathy (DR). Most studies use the International Classification of Diabetic Retinopathy (ICDR) to assign labels to CFP, plus the presence or absence of macular edema (ME). Images can be grouped as referrable or nonreferrable according to these classifications. There is little guidance in the literature about how to collect and use metadata as a part of the CFP labeling process. Objective: This study aimed to improve the quality of the Multimodal Database of Retinal Images in Africa (MoDRIA) by determining whether the availability of metadata during the image labeling process influences the accuracy, sensitivity, and specificity of image labels. MoDRIA was developed as one of the inaugural research projects of the Mbarara University Data Science Research Hub, part of the Data Science for Health Discovery and Innovation in Africa (DS-I Africa) initiative. Methods: This is a crossover assessment with 2 groups and 2 phases. Each group had 10 randomly assigned labelers who provided an ICDR score and the presence or absence of ME for each of the 50 CFP in a test image with and without metadata including blood pressure, visual acuity, glucose, and medical history. Specificity and sensitivity of referable retinopathy were based on ICDR scores, and ME was calculated using a 2-sided t test. Comparison of sensitivity and specificity for ICDR scores and ME with and without metadata for each participant was calculated using the Wilcoxon signed rank test. Statistical significance was set at P<.05. Results: The sensitivity for identifying referrable DR with metadata was 92.8% (95% CI 87.6-98.0) compared with 93.3% (95% CI 87.6-98.9) without metadata, and the specificity was 84.9% (95% CI 75.1-94.6) with metadata compared with 88.2% (95% CI 79.5-96.8) without metadata. The sensitivity for identifying the presence of

关键词： Africa African AI algorithms artificial intelligence assessment bias clinical images diabetes diabetic diabetic retinopathy image labeling metadata multimodal database retinal images screening screening algorithms sensitivity treatment

来源：评论

学校读者我要写书评

暂无评论

Smart vegetable cutter for Smart Home

Smart vegetable cutter for Smart Home

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Saurabh Singhal Deepak Mangal Rakesh Kumar Bhisham Sharma Imed Ben Dhaou Department of Computer Engineering & Applications GLA University Mathura India Department of Computer Science and IT Jain University Bangalore India Department of Computer Science Hekma School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Modern society strives for simpler, more efficient, dependable, speedier, and more automated lifestyle. Existing vegetable cutters in the market have drawbacks such as high investment costs, additional manpower, and time consumption. Moreover, none of them provide the feature of cleaning, peeling, and cutting in a single machine. The veggies offered in the market have pesticides and chemicals, and many people, in their haste, do not wash them properly, endangering their health. To reduce human labor while also providing good health care, a solution to this problem is required. This paper offers a novel method for developing a vegetable cutter and chopper using an Android application and IoT devices. In addition, smart vegetable cutters clean, peel, and cut veggies all in one piece of equipment. This strategy will assist human society in reducing the amount of additional manpower needed and would save them time.

关键词： Technological innovation Costs Smart cities Smart homes Medical services Choppers (circuits) Cleaning

来源：评论

学校读者我要写书评

暂无评论

Design and development of robotic technology through microcontroller system with machine learning techniques

引用

Measurement: Sensors 2024年 33卷

作者： Chinthamu, Narender Gopi, Adapa Radhika, A. Chandrasekhar, E. Udham Singh, Kamred Mavaluru, Dinesh CTO Forbes Official Technology Council Exclusive Senior Enterprise Architect DallasTX United States Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Dist Andhra Pradesh 522502 India Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Kuniyamuthur Tamil Nadu Coimbatore641008 India Department of Cyber Security and Digital Forensics National Forensic Sciences University Tripura Campus Tripura India School of Computing Graphic Era Hill University Graphic Era Deemed to be University Dehradun248002 India Department of Information Technology College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

Through the integration of AI and IoT, the digital twin transforms industrial sectors by virtually portraying physical systems. Simulation and the application of lifecycle management improve decision-making. In this paper, a virtual prototype system a digital twin framework that integrates robotic devices is proposed. Created using debugging platforms, they track every robotic activity, supported by real-time microcontroller structural design systems. Machine learning methods are the fundamental engine of the digital twin system. Because of this connection, robotic actions may be seamlessly controlled and monitored, guaranteeing effectiveness and adaptability in changing contexts. Robotics has advanced significantly with the combination of digital twin technology, machine learning, and microcontroller systems, offering improved performance and versatility in a range of applications. © 2024 The Authors

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Detecting ICMPv6-Based DDoS Attacks Using Binary Flower Pollination Algorithm

引用

Computer Systems Science & Engineering 2023年第10期47卷 553-574页

作者： Adnan Hasan Bdair Aighuraibawi Selvakumar Manickam Rosni Abdullah Zaid Abdi Alkareem Alyasseri Ayman Khallel Dilovan Asaad Zebari Hussam Mohammed Jasim Mazin Mohammed Abed Zainb Hussein Arif National Advanced IPv6 Centre(NAv6) Universiti Sains MalaysiaPenang11800Malaysia Baghdad College of Economic Sciences University BaghdadIraq School of Computer Sciences Universiti Sains MalaysPenang11800Malaysia Information Technology Research and Development Center University of KufaNajafIraq College of Engineering University of Warith Al-AnbiyaaKarbalaIraq Faculty of Computing and Informatics Universiti Malaysia SabahSabahMalaysia Business Administration College of Administration and Financial SciencesImam Ja’afar Al-Sadiq UniversityBaghdad10001Iraq College of Computer Science and Information Technology University of AnbarRamadi AnbarIraq Department of Computer Science College of ScienceNawroz UniversityDuhok42001Kurdistan RegionIraq

Internet Protocol version 6(IPv6)is the latest version of IP that goal to host 3.4×10^(38)unique IP addresses of devices in the ***6 has introduced new features like Neighbour Discovery Protocol(NDP)and Address Auto-configuration ***6 needed several protocols like the Address Auto-configuration Scheme and Internet Control Message Protocol(ICMPv6).IPv6 is vulnerable to numerous attacks like Denial of Service(DoS)and Distributed Denial of Service(DDoS)which is one of the most dangerous attacks executed through ICMPv6 messages that impose security and financial ***,an Intrusion Detection System(IDS)is a monitoring system of the security of a network that detects suspicious activities and deals with amassive amount of data comprised of repetitive and inappropriate features which affect the detection rate.A feature selection(FS)technique helps to reduce the computation time and complexity by selecting the optimum subset of *** paper proposes a method for detecting DDoS flooding attacks(FA)based on ICMPv6 messages using a Binary Flower PollinationAlgorithm(BFPA-FA).The proposed method(BFPA-FA)employs FS technology with a support vector machine(SVM)to identify the most relevant,influential ***,The ICMPv6-DDoS dataset was used to demonstrate the effectiveness of the proposed method through different attack *** results show that the proposed method BFPAFA achieved the best accuracy rate(97.96%)for the ICMPv6 DDoS detection with a reduced number of features(9)to half the total(19)*** proven proposed method BFPA-FAis effective in the ICMPv6 DDoS attacks via IDS.

关键词： IPv6 ICMPv6 DDoS feature selection flower pollination algorithm anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Reliability-based design optimization of load-sharing systems

Reliability-based design optimization of load-sharing system...

引用

2016 Industrial and Systems Engineering Research Conference, ISERC 2016

作者： Subramaniyan, Arun Bala Pan, Rong Du, Xiaoping School of Computing Informatics and Decision Systems Engineering Arizona State University United States Department of Mechanical and Aerospace Engineering Missouri University of Science and Technology United States

This research aims at developing computationally efficient method for the design optimization of load-sharing systems. In the case of designing a mechanical system with some reliability requirements, especially parallel or mixed systems, the current system reliability evaluation method assumes component's failure probability being constant. For real world applications, this may not be true, as the failure of one component will increase the failure probability for the remaining components when the system load gets redistributed. Primary applications include aerospace systems, bridges, automobiles, etc. In our approach, we consider the dynamic nature of component's failure probability in a load-sharing system. The failure of components are not independent to each other and the first failure may equal-likely happen on any component. The limit-state functions of components are built upon the Stress-Strength Interference theory. We use the Sequential Optimization and Reliability Assessment (SORA) method that decouples optimization from reliability analysis. The advantage of this method is that it allows flexibility in the use of optimization and reliability analysis methods. This methodology also allows the user to decide the optimal number of components required for the system with the given load characteristics. Finally, numerical examples are provided to verify the methodology. © 2016 Proceedings of the 2016 Industrial and Systems Engineering Research Conference, ISERC 2016. All rights reserved.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes

引用

Procedia Computer Science 2023年 218卷 24-34页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai 602105 Tamil Nadu India

In the women's community, Breast Cancer (BC) is a severe disease. The World Health Organization reported in 2020 that 2.26 million deaths occur due to BC. BC is curable if detected early. Since thermal imaging is non-invasive and supports disease detection, it is commonly used in clinics. Compared to other methods, it keeps BC early and accurate. The proposed work aims to evaluate the performance of the Pretrained Deep-Learning Methods (PDLM) in detecting BC using the thermal images collected from the benchmark dataset. It includes the following stages: primary image processing, deep feature mining, handcrafted feature mining, feature optimization using Firefly-Algorithm (FA), classification and validation. Visual Lab thermal images were used in the study. The investigational outcome of this study authenticates that the VGG16, along with the DT, provides better detection accuracy (95.5%) compared to other classifiers used in this study. To justify the significance of the implemented technique, the proposed work not only improved accuracy, but also improved precision, sensitivity, specificity, and F1-Scores.

关键词： Breast cancer Thermal imaging Firefly algorithm Feature optimization Classification

来源：评论

学校读者我要写书评

暂无评论

Arabic Sentiment Analysis of Food Delivery Services Reviews

Arabic Sentiment Analysis of Food Delivery Services Reviews

引用

International Symposium on Networks, Computers and Communications (ISNCC)

作者： Dheya Mustafa Safaa M. Khabour Ahmed S. Shatnawi Eyad Taqieddin Dept. of Computer Engineering Faculty of Engineering The Hashemite University Zarqa Jordan Dept. of Information Systems Faculty of Information Technology and Computer Sciences Yarmouk University Irbid Jordan Dept. of Software Engineering Jordan University of Science & Technology Irbid Jordan Dept. of Cyber Security School of Computing and Informatics Al-Hussein Technical University Amman Jordan

Customer reviews on online platforms have grown to become an important source of insight into a company's performance. Food delivery services (FDS) companies aim to effectively use customers' feedback to identify areas for improvement of customer satisfaction. Although Arabic is becoming one of the most widely used languages on the Internet, only a few studies have focused on Arabic sentiment analysis to date. The present study conducts an extensive emotion mining and sentiment analysis on FDS-related reviews in Arabic, exploiting natural language processing, and machine learning techniques to extract information that reflects customers' subjective viewpoints, recognize their feelings, and determine polarity in the FDS domain. This work begins with collecting the FDS dataset (Talabat), and then extracting and creating a dialects lexicon for Arabic dialects, followed by walking the reader through detailed steps of cleaning and pre-processing a manually annotated dataset. Finally, we examined classification algorithms including Decision Tree (DT), and Support Vector Machine (SVM). We achieved a maximum accuracy of about 82% using the SVM classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Existence analysis of a degenerate diffusion system for heat-conducting gases

引用

Nonlinear Differential Equations and Applications 2021年第4期28卷 1-28页

作者： Favre, Gianluca Jüngel, Ansgar Schmeiser, Christian Zamponi, Nicola Fakultät für Mathematik Universität Wien Oskar-Morgenstern-Platz 1 Vienna 1090 Austria Institute for Analysis and Scientific Computing Vienna University of Technology Wiedner Hauptstraß e 8-10 Vienna 1040 Austria School of Business Informatics and Mathematics University of Mannheim B6 28 Mannheim 68159 Germany

The existence of global weak solutions to a parabolic energy-transport system in a bounded domain with no-flux boundary conditions is proved. The model can be derived in the diffusion limit from a kinetic equation with a linear collision operator involving a non-isothermal Maxwellian. The evolution of the local temperature is governed by a heat equation with a source term that depends on the energy of the distribution function. The limiting model consists of cross-diffusion equations with an entropy structure. The main difficulty is the nonstandard degeneracy, i.e., ellipticity is lost when the gas density or temperature vanishes. The existence proof is based on a priori estimates coming from the entropy inequality and the H^{- 1} method and on techniques from mathematical fluid dynamics (renormalized formulation, div-curl lemma). © 2021, The Author(s).

关键词： Compensated compactness Cross-diffusion Energy transport Renormalized equation Weak solutions

来源：评论

学校读者我要写书评

暂无评论

Users Acceptance Online Attendance Application Using Barcode Scanner: The Case Study in al Buraimi University College (BUC) Students

Users Acceptance Online Attendance Application Using Barcode...

引用

2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2022

作者： Alsideiri, Abir Alsharida, Rawan A. Hammood, Maytham Shakir, Mohanaad Binti Cob, Zaihisma Rashid Al Shamsi, Ibrahim Muttar, Ahmed Kh. Abood, Rehab Sheker, Mustefa Buraimi Information Technology Department Oman Tikrit University Computer Science Department Tikrit Iraq Cob University of Buraimi College of Business Buraimi Oman Universiti Tenaga National College of Computing and Informatics Malaysia Applied Science University College of Administrative Sciences Manama Bahrain Al-Fallujah Secondary School for Girls General Directorate of Anbar Education Fallujah Iraq Department of the Sewage of Fallujah Ministry of Municipalities and Public Works Fallujah Iraq

ISBN: (数字)9781665469197

ISBN: (纸本)9781665469197

Marking students' attendance within a class session is the prime task of the subject requirements since marking the attendance will regulate the students to attend the session. Moreover, it verifies how many students are attending the class. Previously, attendance was recorded manually by pen and paper. This method takes a long time, especially if the number of students is significant and adds workload to the teacher, and sometimes the data may be prone to error. This paper presents a mobile application for student attendance to avoid these issues. This application will ease the process of attending to the students in the registration instead of the traditional ones where the teacher spends time calling students to know who is present or absent. The students will use their mobile to log in to the application and select the current class to open the camera to scan the code provided by the teacher, and automatically their attendance will be registered. This application is mainly designed for Buraimi University College lecturers and students. © 2022 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of KNN-NMF Algorithm for Recommendation Systems in E-Commerce

Evaluation of KNN-NMF Algorithm for Recommendation Systems i...

引用

IEEE Conference on Systems, Process & Control (ICSPC)

作者： Hew Sok Yen Samuel-Soma M. Ajibade Muhammed Basheer Jasser Bayan Issa Yoke Leng Yong Faizah Mohammed Bashir Emmanuel Falude Yakubu Aminu Dodo Department of Computing and Information Systems School of Engineering and Technology Sunway University Bandar Sunway Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) School of Engineering and Technology Sunway University Petaling Jaya Selangor Malaysia Faculty of Informatics Engineering University of Aleppo Syria School of Information and Communication Technology HELP University Persiaran Cakerawala Subang Bestari Seksyen Shah Alam Malaysia Department of Decoration and Interior Design Engineering College of Engineering University of Hail Hail Kingdom of Saudi Arabia Malaysia-Japan International Institute of Technology (MJIIT) Universiti Teknologi Malaysia Jalan Sultan Yahya Petra Kuala Lumpur Malaysia Architectural Engineering Department College of Engineering Najran University Najran Kingdom of Saudi Arabia

ISBN: (数字)9798350391398

ISBN: (纸本)9798350391404

Due to growth in e-commerce, recommender systems have gained importance in providing recommendations to the user to help him or her make a choice. These systems not only assist the users in searching through the extensive product list but also increase businesses’ productivity by recommending products. The aim of this project is to suggest a hybrid recommender system which combines the aspects of collaborative and content-based filtering so as to enhance the efficiency of the recommendation system in e-commerce. In addition, it is to evaluate the performance of this model with the individual collaborative and content-based models. The study involved creating the CF and CBF models with the various algorithms like the Matrix Factorization, KNN, SVD, and the TF-IDF vectorization. The best models from CF and CBF were then combined with a Hybrid Filtering (HF) model by using weighted and switching combination to enhance the model’s effectiveness. The performance of the CF, CBF and the HF models was compared, in order to check if the proposed hybrid approach is better than the existing models. The results of the experiment show that the hybrid switching model provided better results than the CF and CBF models on their own. The hybrid filtering model had also managed to reduce the RMSE to $\mathbf{1. 0 6 5}$ and improved precision to 83.2%. This demonstrates the advantage of the proposed model over the traditional CF and CBF approaches. Our study validates that the hybrid filtering recommender system, especially the switching combination strategy, outperformed the traditional standalone models by integrating the benefits of both collaborative and content-based filtering. This provides a good starting point for future work and there are many directions in which the research can be expanded.

关键词： Productivity Machine learning algorithms Filtering Collaboration Switches Hafnium Nearest neighbor methods Electronic commerce User preference Recommender systems

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：