检索结果-内蒙古大学图书馆

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Jamaluddin, Nurussabihah Zain, Nurul Hidayah Mat Diah, Norizan Mat Universiti Teknologi MARA College of Computing Informatics and Mathematics Selangor Shah Alam Malaysia Universiti Teknologi MARA Cawangan Melaka College of Computing Informatics and Mathematics Kampus Jasin Merlimau Melaka Malaysia

ISBN: (纸本)9798331510077

The most popular way of learning Islamic calligraphy is face-to-face, under the supervision of teachers, tutors or trainers. However, finding an expert to teach handwriting Islamic calligraphy is difficult. Therefore, this paper proposed an interactive tutoring in handwriting Islamic calligraphy framework, namely the I-HATIC framework, as a guideline for designing and developing tutoring applications specifically for handwriting Islamic calligraphy. The tutoring application based on the proposed I-HATIC framework describes how human and computer interaction creates good calligraphy or style handwriting in interactive ways. It is motivated by the lack of a well-trained trainer teaching handwriting Islamic calligraphy. This paper discusses the existing frameworks, theoretical foundations, issues, and trends related to handwriting Islamic calligraphy. As a result, the proposed I-HATIC framework can be a guideline in producing up-and-coming handwriting Islamic calligraphy tutoring applications to attract more young generations to explore Islamic calligraphy and solve the problems of limited welltrained trainers. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Water Quality Classification Using Machine Learning 8

Water Quality Classification Using Machine Learning

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Arifin, Fikri Firas Tajul Idrus, Zanariah Halim, Shamimi A. Ahmarofi, Ahmad Afif Ahmad, Khairul Adilah Shah Alam College of Computing Informatics and Mathematics Selangor Shah Alam Malaysia Kedah Branch College of Computing Informatics and Mathematics Merbok Kedah Malaysia

ISBN: (纸本)9798350315516

Water quality is crucial as it directly affects the ecosystem and human health. However, current water quality classification methods are inefficient because they do not compare prediction accuracy between machine learning methods. In this regard, the objective of this study is to classify water quality based on the proposed machine learning tools. To fulfill that, a preliminary study was conducted by collecting related information in the research domain through articles, electronic books, and online databases. The data collection for the prototype's dataset was obtained from an electronic book published by the Pakistan Council of Research in Water Resources 2021. Subsequently, the data pre-processing phase was conducted by using WEKA software which includes the crucial steps to transform the data into a cleaner format and make the model more accurate. The model for each technique was developed using Python in Jupyter Notebook. The results of the accuracy score for each model were also conducted in this phase. The findings of this research show that the Decision Tree model performs excellently with an accuracy of 97.37% compared to the Support Vector Machine and K-Nearest Neighbour models, with an accuracy of 95.69% and 74.72%, respectively. Consequently, implementing a multi-class classification system can help future researchers classify more accurately and reduce the misclassification of water quality. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms Through Visualizations 8

Comparative Analysis of Machine Learning Algorithms Through ...

引用

8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

作者： Ismail, Mohammad Hafiz Razak, Tajul Rosli Noor, Noorfaizalfarid Mohd Aziz, Azlan Abdul Universiti Teknologi MARA College of Computing Informatics and Mathematics Arau Malaysia Universiti Teknologi MARA College of Computing Informatics and Mathematics Shah Alam Malaysia

ISBN: (纸本)9798350315516

This paper presents a visualization technique designed to simplify the process of comparing machine learning classification results and subsequently improving interpretability. The main goal of this study is to construct an end-user interface capable of visualizing the outcomes of classification results generated by multiple machine-learning algorithms. To accomplish this, we conduct an empirical study that assesses the performance of machine learning algorithms on both the standard Iris dataset and a real-world zakat financial aid dataset. Our research involves an examination of the behavior of machine learning algorithms on the Iris dataset, providing practical insights into their functionality. We specifically focused on J48, PARTS, and Random Tree, chosen for their ease of implementation as ruleset in various programming languages. Additionally, we incorporated Neural Network into our study, considering its growing popularity in deep learning and deep neural network research. The interface incorporates interactive charting functionality to visually represent the outcome of each machine learning models. Based on the implementation, the proposed methodology has shown potential in aiding visual comparisons of machine learning algorithms, showcasing both interactivity and usability. The methodology could also prove beneficial for research aiming to optimize user-interface elements that represent input features, addressing concerns about overcrowding users' screens. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Foresight Course Framework for Undergraduates Designing Human-Centric Solutions 10

A Foresight Course Framework for Undergraduates Designing Hu...

引用

10th International HCI and UX Conference in Indonesia, CHIuXiD 2024

作者： Harun, Afdallyna Fathiyah Universiti Teknologi Mara College of Computing Informatics and Mathematics School of Computing Sciences Selangor Shah Alam40450 Malaysia

ISBN: (纸本)9798350380439

The growing complexity of global challenges that advocate human values necessitates a shift towards future oriented, human-centric design approaches. Such thinking is embedded in a foresight-driven coursework, part of the Bachelor of Information Technology (Hons) offered in Universiti Teknologi MARA. It trains students to anticipate future trends and co-create innovative, resilient and sustainable solutions. In this paper we elaborate how foresight methodology, when integrated with participatory design approach, can result in powerful human-centric solutions that are future-proof. Through future tools such as horizon scanning, the seven questions technique, issues paper, driver mapping, futures wheel, SWOT analysis, prototyping and road mapping, students engage with stakeholder to address present and future challenges, equipping them to design adaptable, human-centric technological solutions. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Web-based Management System for Diagnostic Laboratory with Business Process Re-Engineering and Data Analytics 14

A Web-based Management System for Diagnostic Laboratory with...

引用

14th International Conference on System Engineering and Technology, ICSET 2024

作者： Leynes, Jhun-Jhun P. Amorado, Ryndel V. Batangas State University College of Informatics and Computing Sciences TNEU Alangilan Campus Batangas City Philippines Batangas State University College of Informatics and Computing Sciences TNEU Lipa Campus Lipa City Philippines

ISBN: (纸本)9798331504526

Management information systems are a challenge for many small businesses. With fast-changing technology, data management has become an integral part of business processes, especially in the healthcare industry. This study uses Business Process Re-Engineering (BPR) and Data Analytics for a Diagnostic Laboratory to improve its operational efficiency through a web-based management system. The obsolete system, consisting of eight modules, is replaced with a sophisticated system involving twenty-one modules. The goal is to evaluate the impact of technology on business operations and user satisfaction. The results indicate that the most recent technology enables board members to monitor corporate performance from any location using various web browsers. The database securely saves and categorizes all operational data. Transactions, test results, and reports are instantly created in PDF format. Subsequently, the gathered information is utilized by means of descriptive and prescriptive analysis. The system acceptance is also assessed using a questionnaire that adheres to the ISO 25010 standards. With an optimal score of 5.0, the results showed a weighted average of 4.79 ('Strongly Agree'), which is significantly higher than the prior system average of 3.69 ('Agree'). The conclusions emphasize that the system has a crucial role in remote management, efficient database management, improved operational efficiency, and reduced turnaround time. Recommendations encompass the integration of digital payment methods for transactions and advocating the established system as a benchmark for other diagnostic laboratories in the health industry. This research has a significant impact on the improvement of diagnostic laboratory management systems. © 2024 IEEE.

关键词： Web browsers

来源：评论

学校读者我要写书评

暂无评论

Fault Management Cyber-Physical Systems in Virtual Storage Model

引用

Computers, Materials & Continua 2022年第2期70卷 3781-3801页

作者： Kailash Kumar Ahmad Abdullah Aljabr College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Kingdom of Saudi Arabia

On average,every two years,the amount of data existing globally *** development will be affected and improved by Cyber-Physical Systems(CPS).The number of problems remained even though developments helped Information Technology experts extract better value from their storage *** of poor interoperability between different vendors and devices,countless numbers of Storage Area Networks were *** setup used for data storage includes a complex and rigid arrangement of routers,switch,hosts/servers,storage *** have evaluated the performance of routing protocol Transmission Control Protocol(TCP)and Fibre Channel Protocol(FCP)under different network scenario by Network Simulator(NS)-3 *** simulated the Node Failure and NetworkCongestion issuewithDoS attacks and a counter effect on the Packet Distribution Ratio and End-to-End Delay efficiency metrics with different nodes and speed of node *** study is performed for the Simple NetworkManagement Protocol(SNMP)on FCP *** results proved that the proposed method isolates the malicious and congested nodes and improves the Network’s performance.

关键词： CPS data storage virtualization TCP FCP

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Food Detection and Calories Counter

Deep Learning Food Detection and Calories Counter

引用

2023 IEEE International Conference on computing, ICOCO 2023

作者： Ibrahim, Shafaf Arif Aiman Wan Hasnan, Wan Muhamad Md Ghani, Nor Azura Fariza Abu Samah, Khyrina Airin Abu Mangshor, Nur Nabilah Ahmad Fadzil, Ahmad Firdaus Janor, Roziah Mohd School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi Mara Shah Alam Malaysia School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi Mara Melaka Branch Jasin Malaysia

ISBN: (纸本)9798350302684

Monitoring and managing dietary intake plays a vital role in maintaining a healthy lifestyle. However, accurately tracking food consumption and estimating calorie intake can be challenging. This paper presents a deep learning-based approach of You Only Look Once version 4 (YOLOv4) model for food detection and calorie counting. Leveraging the power of deep neural networks, the proposed study automatically detects and classifies food items from images and provides real-time estimation of their calorie content. Seven classes of food which are fried noodles, fried rice, kaya toast, nasi lemak, roti canai, fried chicken, and fried egg were addressed, by training the model on a diverse and well-annotated food dataset. We also tackle the issue of calorie estimation. Experimental evaluations of the proposed YOLOv4 for food detection demonstrates 96.07% of accuracy. Thus, it could be deduced that the proposed deep learning-based food detection and calorie counter have the potential to significantly improve dietary monitoring and contribute to the promotion of healthier eating habits. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Malicious URL Detection with User Notification using Well-known API 22

Automatic Malicious URL Detection with User Notification usi...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Zulkipli, Nurul Huda Nik Fuzi, Mohd Faris Mohd Salni, Muhammad Khairul Ariffin Universiti Teknologi MARA College of Computing Informatics and Mathematics Melaka Malaysia Perlis Malaysia

ISBN: (纸本)9798331510077

This study an innovative automatic malicious URL detection and user notification app using a well-known API. With approximately 3.8 billion users in April 2020, the background study underscores the significant risks posed by deceptive URLs, such as phishing attacks. The problem statement highlights the key challenges: the surge in mobile device usage, the increasing number of suspicious URLs, user awareness gaps, and the limitations of current URL scanners in providing actionable responses. To address these issues, the study introduces a novel approach by designing, developing, and testing an app that detects malicious URLs and allow users to ignore, quarantine, or block these threats. The methods involve leveraging APIs, such as VirusTotal and ***, alongside rigorous validity and functionality tests. Key results demonstrate the app's effectiveness in real-time threat detection and user guidance. The app's unique feature set, including user-friendly notifications and customizable threat responses, set it apart from any existing solutions. The conclusion affirms the app's potential to significantly enhance mobile security, offering a safer digital experience for users. This innovative solution addresses current limitations and provides a proactive approach to mobile security, ensuring users to be better protected against evolving cyber threats. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

STATE:Learning structure and texture representations for novel view synthesis

引用

Computational Visual Media 2023年第4期9卷 767-786页

作者： Xinyi Jing Qiao Feng Yu-Kun Lai Jinsong Zhang Yuanqiang Yu Kun Li College of Intelligence and Computing Tianjin UniversityTianjin 300350China School of Computer Science and Informatics Cardiff UniversityCardiff CF244AGUK

Novel viewpoint image synthesis is very challenging,especially from sparse views,due to large changes in viewpoint and *** image-based methods fail to generate reasonable results for invisible regions,while geometry-based methods have difficulties in synthesizing detailed *** this paper,we propose STATE,an end-to-end deep neural network,for sparse view synthesis by learning structure and texture *** is encoded as a hybrid feature field to predict reasonable structures for invisible regions while maintaining original structures for visible regions,and texture is encoded as a deformed feature map to preserve detailed *** propose a hierarchical fusion scheme with intra-branch and inter-branch aggregation,in which spatio-view attention allows multi-view fusion at the feature level to adaptively select important information by regressing pixel-wise or voxel-wise confidence *** decoding the aggregated features,STATE is able to generate realistic images with reasonable structures and detailed *** results demonstrate that our method achieves qualitatively and quantitatively better results than state-of-the-art *** method also enables texture and structure editing applications benefiting from implicit disentanglement of structure and *** code is available at http://***/faculty/likun/projects/STATE.

关键词： novel view synthesis sparse views spatioview attention structure representation texture representation

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Lightweight Vision Transformers and Deep Convolutional Neural Networks in Detecting Brain Tumors in MRI Scans: An Empirical Approach 8

Performance Analysis of Lightweight Vision Transformers and ...

引用

8th International Conference on Biomedical Imaging, Signal Processing, ICBSP 2023

作者： Montalbo, Francis Jesmar P. Hernandez, Lovely Rose T. Palad, Lanie P. Castillo, Ria C. Alon, Alvin S. De Ocampo, Anton Louise P. College of Informatics and Computing Sciences Batangas State University Philippines

ISBN: (纸本)9798400716584

Vision transformer models began gaining recognition alongside NLP. However, their performance compared to Convolutional Neural Network (CNN) models in this domain still requires more significant investigations. Hence, this article comprehensively analyzes their impact and effectiveness against CNN models in medical imaging. We conducted experiments using ViT, MobileViT, and Swin transformers against a pure CNN ConvNeXt trained on Magnetic Resonance Image (MRI) scans. While our findings show promising advancements in imaging with transformers, we observed challenges in their scalability and deployment due to their cost and complexity. We also noticed that they require more medical data, specifically higher-quality MRI scans, when considering better reliability. Nonetheless, comparing their performance in terms of accuracy, even with such limitations, these visual transformer models have shown better detection and diagnosis of brain tumors in MRI scans compared to pure CNN models selected in this study. © 2023 ACM.

关键词： Biomedical engineering

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：