检索结果-内蒙古大学图书馆

A Performance Study of Selected Machine Learning Techniques for Predicting Heart Diseases 2nd

A Performance Study of Selected Machine Learning Techniques ...

2nd International Conference on Security and information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Olorunfemi, Blessing Oluwatobi Ogunde, Adewale Opeoluwa Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Li, Chun-Ta Faculty of Natural Sciences Department of Computer Science Redeemer’s University Osun Nigeria Department of Computer Science Bowen University Iwo Nigeria Faculty of Information and Communication Sciences Department of Computer Science University of Ilorin Ilorin240003 Nigeria Faculty of Engineering Department of Electrical and Electronics Engineering University of Lagos Lagos Akoka100213 Nigeria Bachelor’s Program of Artificial Intelligence and Information Security Fu Jen Catholic University New Taipei City24206 Taiwan

ISBN: (纸本)9789819777853

Heart Disease remains a leading cause of mortality worldwide. It alarmingly rises at a quick rate, making early heart disease prediction crucial for effective prevention and timely intervention. Heart disease diagnosis is a difficult process that requires technical skills and accuracy to complete. With improvements in technology, computing has lent its voice to simplify the diagnosis of various health problems. Machine learning uses past or existing history to predict future results. Various machine learning techniques have been developed over the years and used in predicting heart diseases with various levels of performance. Identifying the best-suited machine learning technique to use for prediction purposes can be a challenging task. This research work analyses the performance of seven (7) machine learning techniques, comprising AdaBoost Algorithm, KNN, Logistic Regression, Naïve Bayes Classifier, Random Forest, SVM, and XGBoost. The heart disease dataset was downloaded from the UCI repository and analysed using Python programming language in the Jupyter Notebook environment. A comparative analysis of the seven (7) techniques was performed based on Accuracy, Precision, and Recall. From the results obtained, KNN, Random Forest, and XGBoost showed superior performance over the others with an accuracy of 100%, AdaBoost Algorithm followed with an accuracy of 92.2%, SVM followed with an accuracy of 91.71%, Naïve Bayes Classifier followed with an accuracy of 88.29% while Logistic Regression has the least accuracy of 86.34%. KNN, RF, and XGBoost outperformed AdaBoost, SVN, and LR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Innovative metallization pattern and technique for industrial rear emitter p-type tunnel oxide passivated contact solar cells

引用

Journal of Industrial and Engineering Chemistry 2025年 147卷 628-635页

作者： Khokhar, Muhammad Quddamah Yousuf, Hasnain Rahman, Rafi Ur Aida, Maha Nur Madara, Polgampola Chamani Jony, Jaljalalul Abedin Dao, Vinh-Ai Pham, Duy Phong Yi, Junsin Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Future Energy Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Physics Faculty of Applied Sciences HCMC University of Technology and Education Ho Chi Minh City700000 Viet Nam College of Information and Communication Engineering Sungkyunkwan University Suwon16419 Korea Republic of

In this study, we aim to enhance the efficiency of p-type tunnel oxide passivated contact (p-TOPCon) solar cells by improving charge carrier extraction while achieving higher fill factor (FF) and open circuit voltage (Voc). We explore various potential methods for the photovoltaic industrial procedure, including optimizing metallization patterns and techniques, such as the utilization of a high efficiency grid pattern (HEGP) in place of the conventional straight finger-line pattern (SFLP). Co-firing conditions, peak firing temperature, and belt speed are investigated for their impact on FF enhancement, along with evaluating the effects of single and double print processes. Furthermore, we examine the efficacy of Nafion treatment as a surface modification technique to enhance FF. Experimental results indicate that optimizing co-firing conditions and employing Nafion treatment significantly increased FF to approximately 83.26% in p-TOPCon solar cells. Adjusting peak firing temperature and belt speed, as well as implementing the double print process, demonstrate superior FF enhancement compared to the single print process. Additionally, Nafion treatment contributes to FF improvement by passivating surface defects and enhancing charge carrier collection. Overall, this study provides valuable insights into optimizing co-firing conditions and surface treatment techniques to enhance p-TOPCon solar cell efficiency (Eff) up to 23.50%, thus advancing high-efficiency photovoltaic technology. © 2024 The Korean Society of Industrial and Engineering Chemistry

关键词： Metallizing

来源：评论

学校读者我要写书评

暂无评论

The reliability of deep learning models in assessing the shoulder arthroscopic field's visual clarity in relation to bleeding

引用

JSES International 2025年第3期9卷 864-870页

作者： Tran, Son Quang Bui, Minh Cong Nguyen, Dat Tien Itthipanichpong, Thun Limskul, Danaithep Thamrongskulsiri, Napatpong Tanpowpong, Thanathep Clinical Sciences Program Faculty of Medicine Chulalongkorn University Bangkok Thailand Faculty of Medicine Department of Orthopaedics Cantho University of Medicine and Pharmacy Can Tho Viet Nam Faculty of Computer Science University of Information Technology Ho Chi Minh City National University Ho Chi Minh City Viet Nam Sports Medicine Research Group Faculty of Medicine Chulalongkorn University Bangkok Thailand

Background: The clarity of visualization in shoulder arthroscopy is significantly influenced by intraoperative bleeding. This study aims to develop deep learning models to classify the visual clarity of arthroscopic shoulder images and evaluate their reliability compared to rater assessment. Methods: We retrospectively reviewed videos from 113 shoulder arthroscopies, using 63 patients’ videos to create a 3750-image training dataset and 50 patients’ videos to evaluate the reliability and agreement of the trained models. Images extracted from the videos were assessed for visual clarity with a 3-grade scale. Subsequently, we implemented transfer learning techniques for the pretrained deep learning models involving DensetNet169, DenseNet201, Xception, InceptionResNetV2, VGG16, and ViT. The reliability and agreement of the trained predictive models compared with raters in classifying the visual clarity of shoulder arthroscopic images were reported with percent agreement and weighted kappa coefficients. Similarly, for quantifying the visual clarity of surgical videos, the reliability and agreement were evaluated through intraclass coefficients, bias, and limits of agreement. Results: Most models achieved over 90% accuracy in validation step, with InceptionResNetV2, DenseNet169, and ViT exhibiting good percent agreements of 82.3%, 79.2%, and 77.8%, respectively, and their weighted kappa coefficients above 0.8. DenseNet169 model had the highest reliability for evaluating the visual clarity of surgical videos with an intraclass correlation coefficient of 0.9, a bias of 0.027, and the narrowest limits of agreement. Conclusion: The trained DenseNet169 predictive model was reliable enough to be utilized as an objective measure of the visual clarity of the shoulder arthroscopic field for further research. © 2025 The Authors

关键词： Basic Science Study Bleeding Convolutional neural network Deep learning model Grading scale Shoulder arthroscopy Validation of Artificial Intelligence Software Visual clarity Visualization

来源：评论

学校读者我要写书评

暂无评论

A NEW HOPE: contextual privacy policies for mobile applications and an approach toward automated generation 24

A NEW HOPE: contextual privacy policies for mobile applicati...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Shidong Pan Zhen Tao Thong Hoang Dawen Zhang Tianshi Li Zhenchang Xing Xiwei Xu Mark Staples Thierry Rakotoarivelo David Lo School of Computing Australian National University and Software and Computational Systems Research Program CSIRO's Data61 Software and Computational Systems Research Program CSIRO's Data61 Khoury College of Computer Sciences Northeastern University School of Computing and Information Systems Singapore Management University

ISBN: (纸本)9781939133441

Privacy policies have emerged as the predominant approach to conveying privacy notices to mobile application users. In an effort to enhance both readability and user engagement, the concept of contextual privacy policies (CPPs) has been proposed by researchers. The aim of CPPs is to fragment privacy policies into concise snippets, displaying them only within the corresponding contexts within the application's graphical user interfaces (GUIs). In this paper, we first formulate CPP in mobile application scenario, and then present a novel multimodal framework, named SEEPRIVACY, specifically designed to automatically generate CPPs for mobile applications. This method uniquely integrates vision-based GUI understanding with privacy policy analysis, achieving 0.88 precision and 0.90 recall to detect contexts, as well as 0.98 precision and 0.96 recall in extracting corresponding policy segments. A human evaluation shows that 77% of the extracted privacy policy segments were perceived as well-aligned with the detected contexts. These findings suggest that SEEPRIVACY could serve as a significant tool for bolstering user interaction with, and understanding of, privacy policies. Furthermore, our solution has the potential to make privacy notices more accessible and inclusive, thus appealing to a broader demographic. A demonstration of our work can be accessed at https://***/SeePrivacy/

关键词：

来源：评论

学校读者我要写书评

暂无评论

An automated parameter optimizer for data transfer performance testing

引用

Software Impacts 2025年 24卷

作者： Yun, Daqing Zuo, Liudong Gu, Yi Wu, Chase Computer and Information Sciences Program Harrisburg University Harrisburg 17101 PA United States Department of Computer Science California State University Dominguez Hills Carson 90747 CA United States Department of Computer Science Middle Tennessee State University Murfreesboro 37132 TN United States Department of Data Science New Jersey Institute of Technology Newark 07102 NJ United States

This work presents an automated tool for optimizing control parameters in performance testing of big data transfer over long-fat network connections. Supporting both TCP and UDT protocols, the tool identifies the optimal configurations to enhance the efficiency of large-scale data transfers. A stochastic approximation algorithm is employed for parameter optimization, streamlining the protocol and parameter selection. The tool has been evaluated in various network scenarios, including long-haul connections in real-world high-performance networks. Its modular design also enables straightforward integration of additional data transfer protocols and alternative optimization methods. © 2025 The Author(s)

关键词： Big data transfer High-speed networks Network testing Parameter optimization Stochastic approximation

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

arXiv

引用

arXiv 2025年

作者： Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan

This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-ONU Customers Access Network using Spectrum Slicing and Duplication Techniques

Performance Evaluation of Multi-ONU Customers Access Network...

引用

5th International Conference on Emerging Electrical Energy, Electronics and Computing Technologies, ICE4CT 2024

作者： Rahman, Juwairiyyah Abdul Mugunthan, Sivaguru A.L. Hassan, Hasliza Abu Muslim, Norliana Ab-Rahman, Mohammad Syuhaimi Department of Electrical Engineering Faculty of Engineering and Life Sciences Universiti Selangor Selangor Bestari Jaya45600 Malaysia Department of Computer and Communication Technology Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar31900 Malaysia Department of Electrical Electronics and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Malaysia Electrical and Computer Engineering Program Faculty of Engineering Sohar University PC:311 Sohar Oman

This study aims to increase the number of access users by limiting the sample size to 30 users while ensuring that every Optical Network Unit (ONU) receives data from the Optical Line Terminal (OLT). The proposed solution allows for the determination of power requirements at each ONU based on bus-star topologies, facilitating an increase in user capacity. The power received by each ONU is a critical parameter that system designers must consider when planning the implementation of Fiber to the Home (FTTH), as it impacts the output data in terms of Bit Error Rate (BER) and Signal Quality Factor (QF) for each user. Various parameters were evaluated to ensure that the enhanced network improves scalability while adhering to standard specifications. These parameters included the Q-factor, BER, eye diagram, user count, and received power. The study employed slicing and duplication techniques, utilizing Arrayed Waveguide Grating (AWG) for signal duplication and Wavelength Division Multiplexing for signal slicing. The simulations were conducted using a transmitter operating at a frequency of 1491 nm with a power output of 0 dBm, utilizing the latest version of OptiSystem 20 software. The results highlighted the system's capability to support a total of 73,728 users, meeting stringent performance criteria. Specifically, the system achieved a Q-factor greater than 6, indicating high signal quality, and a bit error rate (BER) lower than 1 × 10-9, ensuring reliable data transmission. For the sampled 30 users, the average Q factor was 8.1527, and the average BER was 5.3648 × 10^-11, with an output power level of -54.278 dBm. Despite an increase in users, the quality of the data supplied to clients remained unchanged. These outcomes underscore the robustness and efficiency of the design in delivering high-capacity, error-resilient optical communication. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Sustainability in Disruption: SC Intelligence, Customer Knowledge Transfer, and the Mediating Role of IS/IT

引用

IEEE Engineering Management Review 2025年

作者： Ratna, Silvia Saide, Saide Rater, Salya Svyazhanovna, Baizakova Saule Herzavina, Herzavina Faculty of Information Technology Department of Informatics Engineering and Department of Information Systems Banjarmasin Indonesia State Islamic University of Sultan Syarif Kasim Riau Universitas Islam Negeri Sultan Syarif Kasim Riau-UIN SUSKA Riau Department of Information Systems Faculty of Science and Technology Indonesia PRO Knowledge Indonesia Pekanbaru Indonesia Universitas Pahlawan Tuanku Tambusai Indonesia Lembaga Enreach UIN Suska Riau Indonesia Politeknik Aceh Selatan Department of Informatics Engineering Aceh Indonesia Information Communication Technologies Robotics in Arkalyk Pedagogical Institute Master of Natural Sciences Educational Program for the Informatics Computer Science Kazakhstan Universitas Pahlawan Tuanku Tambusai Department of Informatics Engineering Indonesia National Taiwan University of Science and Technology Taiwan

Knowledge resource and information system/technology (IS/IT) capability have been considered to improve firm performance, however there is still a gap regarding the sustainability of supply chain to face and recover from disruption (e.g., COVID-19). Questionnaire-based surveys was adopted and received feedback from sixty (160) Indonesian companies or about 28.07% of response rate. © 1973-2011 IEEE.

关键词： customer knowledge transfer disruption information system/technology (IS/IT) responding knowledge management resource-based view (RBV) Supply chain (SC) sustainability supply chain knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Creating user-centered instructions for novice end-users

引用

Reference Services Review 1999年第3期27卷 280-286页

作者： Nahl, Diane University of Hawaii Information Computer Sciences Department Library and Information Science Program Honolulu Hawaii United States

In response to the proliferation of information retrieval systems in academic libraries since the early 1980s, librarians have created many written search aids designed to help users learn how to search database systems. Written instructional material continues to increase in quantity and in importance with the rise of remote users and the advent of asynchronous distance learning. Since many users will have only written instructions to consult, it is crucial to determine the effectiveness of these materials. How useful are these instructions? Do people consult them? Do they help users make progress in their searches? There is a small but useful body of research on the effectiveness of both print and online search aids. This research points to the need to test materials on user groups. The findings from studies of novices using written instructions identify specific guidelines for creating effective materials. © 1999, MCB UP Limited

关键词： Academic libraries End-user computing Human-computer interaction Instructional design Instructional strategy Library users

来源：评论

学校读者我要写书评

暂无评论

information literacy instruction in four Vietnamese university libraries

引用

International information and Library Review 2011年第4期43卷 198-206页

作者： Diep, Kim Chi Nahl, Diane Communication and Information Sciences Program University of Hawaii Honolulu HI 96822 United States Library and Information Science Program Department of Information and Computer Sciences University of Hawaii Honolulu HI 96822 United States

This case study explored the perceptions of academic stakeholders about the development and delivery of information literacy (IL) programs in four universities, and identified elements necessary to establishing IL credit courses in Vietnamese higher education. The following research questions framed this study: 1) How do library administrators, instruction librarians, and faculty perceive the current implementation of information literacy instruction (ILI) programs for undergraduates studies in universities libraries in Vietnam? 2) What are the challenges to including IL as a credit course in the curriculum as perceived by library administrators, instruction librarians, and faculty? Respondents were purposefully recruited from four universities, including library administrators, instruction librarians, and faculty. Three online surveys were distributed to 537 individuals through Survey Monkey with 149 replies and a final receipt of 133 completed surveys. Interview and focus group data collection included 23 face-to-face interviews and nine focus groups. Findings showed IL is considered the domain of librarians and has not influenced Vietnamese campus culture. IL activities at four university libraries take the form of lectures, workshops, and basic IL skills modules. Few ILI activities are subject discipline-related. Respondents reported challenges to an ILI credit course revolve around the lasting impact of teacher-centered instruction and rote learning, misperceptions about the effect of IL on student learning outcomes, degree of support of IL by academic stakeholders, degree of faculty-librarian collaboration, and scarcity of resources. Recommendations are given for academic librarians in Vietnam implementing ILI programs and considering developing IL credit courses. © 2011 Elsevier Ltd.

关键词： Academic libraries Active learning Credit course Developing countries information competency standards information literacy instruction Instruction librarians Vietnamese higher education

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：