检索结果-内蒙古大学图书馆

2024 International Conference on Computer and Applications, ICCA 2024

作者： Sherif, Meriam Barakat, Nahla Hamdy, Abeer The British University in Egypt Faculty of Informatics and Computer Science Department of Software Engineering Cairo Egypt The British University in Egypt Faculty of Informatics and Computer Science Department of Artificial Intelligence Cairo Egypt

ISBN: (纸本)9798350367560

The paper proposes 'AdaptVR' a virtual reality (VR) system designed to enhance dental training through realistic real tile simulations and adaptive learning environment, to overcome traditional training challenges in dental education. The system aims to provide personalized learning experiences, facilitating skill development and comprehensive assessments for students. The proposed system was tested by 17 dentistry students and 5 experts. AdaptVR framework is done for operative dentistry which is removing decay especially Class I and Class II of classification of caries. Results from the experiment revealed that 77.3% of participants exceed their expectations, 59.1% saw a positive effect on their dental skills, 90.9% reported higher levels of engagement, and 65% indicated that vibration and force feedback provided students with a genuine sensation. AdpatVR's experimental findings show an average accuracy of 50.85% for Class I, 51.7% for Class II, and 82.09% for the Class II box technique. The error percentage averages 49% for Class I, 48% for Class II, and 18% for Class II box technique. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

An Edge Detection Algorithm of Noisy Image Based on OTSU Adaptive Threshold Segmentation 5

An Edge Detection Algorithm of Noisy Image Based on OTSU Ada...

引用

5th Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2024

作者： Wang, Jingjing Lin, Shiming Zhang, Kang School of Information Engineering Changji College Changji China Xiamen University School of Informatics National Demonstrative Software School Xiamen China

ISBN: (纸本)9798350374407

In order to solve the problem that the traditional edge detection algorithm is not effective in the edge detection of noisy image, this paper proposes an adaptive threshold OTSU based edge detection algorithm of noisy image. The algorithm takes into account the selection of filtering methods and thresholds, replacing the Gaussian filter used in the traditional Canny algorithm with an improved median filter. Secondly, the maximum inter-class variance OTSU is used to self-adapt the segmentation threshold. Firstly, the improved median filter algorithm removes part of the particle noise and preserves the edge to the maximum extent. Then the DoG operator is used to extract the edge information of the image, and finally the adaptive threshold value is calculated to the final binary edge detection image. Experimental results show that compared with traditional algorithms, the proposed algorithm has higher edge detection accuracy and better anti-noise performance. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Diabetes Status Prediction Application Using a Machine Learning Algorithm Approach 9

Implementation of a Diabetes Status Prediction Application U...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Zulkifli, Zulkifli Wahyuningsih, Sri Hendrawan Putri, Adelia Isni Andika, Tahta Herdian Bintoro, Panji Pratiwi, Mida Aisyah University Faculty of Technology and Informatics Department of Informatics Engineering Pringsewu Indonesia UPN Veteran Jakarta Faculty of Medicine Jakarta Indonesia Aisyah University Faculty of Technology and Informatics Department of Software Engineering Pringsewu Indonesia Aisyah University Faculty of Medicine Department of Pharmacy Pringsewu Indonesia

ISBN: (纸本)9798350390025

A rise in blood sugar (glucose) levels above normal ranges is the major sign of diabetes. Diabetes develops when the body's ability to absorb glucose into cells for energy declines, resulting in an accumulation of excess sugar in the blood. Diabetes, if not well treated, can cause serious damage to many organs and tissues. One method to prevent or managing diabetes is to create tools for regularly monitoring blood sugar levels. This study introduces methods that use eight input variables: pregnancy, glucose, blood pressure, skin thickness, insulin, BMI, age, diabetes pedigree function, name, and gender, as well as one output variable, diabetes status. The use of these techniques generates a dataset for measuring the accuracy of diabetes status prediction. The Neural Networks algorithm achieves an accuracy rate of 79.65%, the SVM algorithm 83.69%, and the Random Forest algorithm 74.9%. © 2024 IEEE.

关键词： diabetes neural networks algorithms random forest support vector machines

来源：评论

学校读者我要写书评

暂无评论

Ensemble based unsupervised anomaly detection with concept drift adaptation for time series data 10

Ensemble based unsupervised anomaly detection with concept d...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Li, Danlei Nair, Nirmal Wang, Kevin I-Kai Sakurai, Kouichi University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Kyushu University Department of Informatics Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798331520861

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework's longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability. © 2024 IEEE.

关键词： Anomaly detection Concept drift adaptation Ensemble method Time series Unsupervised method

来源：评论

学校读者我要写书评

暂无评论

Enhancing SEO Compliance of JavaScript Web Frameworks through Automated Testing inside CI/CD Pipelines 11

Enhancing SEO Compliance of JavaScript Web Frameworks throug...

引用

11th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2024

作者： Ágh, Ján Makarova, Irina Dakić, Pavle Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava842 16 Slovakia Faculty of Informatics and Computing Singidunum University Danijelova 32 Belgrade Serbia

This article aims to incorporate search engine optimization validation into the development process of JavaScript-based web applications, thus connecting two sides of optimizations, namely the selection of appropriate practices and their correct implementation. We summarize strategies for achieving search engine optimization (SEO) compliance in single-page applications (SPAs) and propose two distinct testing solutions aimed at addressing SEO concerns in modern web apps. Both approaches are incorporated into CI/CD pipelines, making it possible to enforce existing SEO strategies. The issue of visibility in search engines is especially characteristic for JavaScript-based frameworks. This is because of the way they load and render their content, are mostly unable to achieve satisfactory SEO scores and rankings. Due to the ever-increasing popularity of these frameworks, it is essential to identify and compare available optimization techniques to address this subject adequately. Here, we take a closer look at the SEO-friendly features of *** and *** frameworks and evaluate their capabilities using two mock e-commerce websites as examples. To fulfill our second objective, an approach to continuous SEO testing is presented. We discuss the results of similar CI/CD pipeline setups using distinct technologies and tools, in particular Jenkins and GitHub actions. The results show that by integrating specific tests focused on SEO into CI/CD pipelines, developers can identify crucial shortcomings of their product and eliminate them before they cause harm in the production environment. © 2024 Copyright for this paper by its authors.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Enhancing Virtual Sensors to deal with Missing Values and Low Sampling Rates 11

Enhancing Virtual Sensors to deal with Missing Values and Lo...

引用

11th IEEE International Conference on Mobile Cloud Computing, Services, and engineering, MobileCloud 2023

作者： Anagnostopoulos, Georgios Stavropoulos, Georgios Violos, John Leivadeas, Aris Varlamis, Iraklis Harokopio University of Athens Department of Informatics and Telematics Tavros Greece Department of Software and IT Engineering Montréal Canada

ISBN: (纸本)9798350322798

Nowadays there is an increasing interest from the edge computing and IoT community for virtual sensors due to their advantages of low cost, robustness, easy installation and multi-purpose use. Virtual sensors are software components capable of replacing physical sensors providing aggregations and higher representations of physical measurements. Since virtual sensors rely on taking input and process measurements from external sources of data, they bear their limitations. To this end, in this paper, we tackle the challenges of missing values and low sampling rate. Specifically, our research goal is to design a virtual sensor that operates smoothly even if it misses some input values. Additionally, even if the sampling rate of the external input is low, the virtual sensor will be capable of providing output values in a higher rate. In order to achieve these functionalities we examine and tailor different lightweight deep learning models appropriate for an edge computing setting. For the experimental evaluation we also developed an IoT platform and run a smart home use case with humidity and temperature sensors. Comparing the evaluation outcomes of our methodology with baseline missing values techniques and multi-step approaches, our proposed methodology is proved to be promising and accurate. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Learning Analytics Support in Higher-Education: Towards a Multi-Level Shared Learning Analytics Framework 16

Learning Analytics Support in Higher-Education: Towards a Mu...

引用

16th International Conference on Computer Supported Education, CSEDU 2024

作者： Vierhauser, Michael Groher, Iris Sauerwein, Clemens Antensteiner, Tobias Hatmanstorfer, Sebastian University of Innsbruck Department of Computer Science Innsbruck Austria Johannes Kepler University Linz Institute of Business Informatics Software Engineering Linz Austria

ISBN: (纸本)9789897586972

Assurance of Learning and Competency-Based Education are increasingly important in higher education, not only for accreditation or transfer of credit points. Learning Analytics is crucial for making educational goals measurable and actionable, which is beneficial for program managers, course instructors, and students. While universities typically have an established tool landscape where relevant data is managed, information is typically scattered across various systems with different responsibilities and often only limited capabilities for sharing data. This diversity, however, significantly hampers the ability to analyze data, both on the course and curriculum level. To address these shortcomings and to provide program managers, course instructions, and students with valuable insights, we devised an initial concept for a Multi-Level Shared Learning Analytics Framework to provide consistent definition and measurement of learning objectives, as well as tailored information, visualization, and analysis for different stakeholders. In this paper, we present the results of initial interviews with stakeholders, devising core features. In addition, we assess potential risks and concerns that may arise from the implementation of such a framework and data analytics system. As a result, we identified six essential features and six main risks to guide further requirements elicitation and development of our proposed framework. Copyright © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso

引用

Computer Modeling in engineering & Sciences 2025年第2期142卷 1611-1636页

作者： Irfan Khan Xianchao Zhang Ramesh Kumar Ayyasamy Saadat M.Alhashmi Azizur Rahim School of Software Dalian University of TechnologyDalian116620China Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKampar31900Malaysia College of Computing and Informatics University of SharjahSharjah27272United Arab Emirates Department of Computer Systems Engineering University of Engineering and Applied SciencesSwat19200Pakistan

The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.

关键词： Meta-learning machine learning automated machine learning classification meta-features

来源：评论

学校读者我要写书评

暂无评论

A New RISC-V CPU for Safety-Critical Systems 12

A New RISC-V CPU for Safety-Critical Systems

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Mach, Jan Kohutka, Lukas Cicak, Pavel Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava842 16 Slovakia Institute of Informatics Information Systems and Software Engineering Slovak University of Technology Bratislava842 16 Slovakia

ISBN: (纸本)9798350322910

In this paper, we propose a novel hardening technique against Single Event Effects, which enables high-frequency operation and does not cause large power consumption and area overhead. The protection is based on redundancy, separation of the pipeline into two main sections, and is fully applicable at Register Transfer Level. It provides fast detection of faults, simple recovery by a flush of the pipeline, and allows a large prediction unit to be unprotected. We present the protection scheme at the core with the RISC-V instruction set. Simulations confirm that the protection can handle the injected faults. Synthesis shows that protection lowers the maximum frequency by only 3.9%. The area increase is only 108% and can be even lower. Total power consumption increased by 119%. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Constellation Recognition on Digital Images 17

Constellation Recognition on Digital Images

引用

17th IEEE International Symposium on Applied Computational Intelligence and informatics, SACI 2023

作者： Molnar, Zsuzsanna Kiss, Daniel Óbuda University John von Neumann Faculty of Informatics Budapest Hungary John von Neumann Faculty of Informatics Óbuda University Software Engineering Institute Budapest Hungary

ISBN: (纸本)9798350321104

In this paper, we present an optimization-based approach for star constellation recognition. The main components of the proposed procedure are the processing of digital images and the minimization of the error in point cloud matching by parameter optimization. In the optimization phase, the Nelder- Mead algorithm, the simulated annealing algorithm, and an evolutionary algorithm were used. Also, the behavior of these methods is evaluated and compared in the paper based on their average error values for different test images. Results on our test dataset showed that the Nelder-Mead simplex algorithm was performing the best in solving the recognition task. © 2023 IEEE.

关键词： Image processing

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：