检索结果-内蒙古大学图书馆

2024 IEEE International Conference on computing, ICOCO 2024

作者： Husni, Ainur Aizeah Azman Shuhaili, Nur Dina Radi, Noor Fadhilah Ahmad Mah, Pauline Jin Wee Ghani, Nor Azura Mansor, Mahayaudin M. School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia

ISBN: (纸本)9798331530303

This study investigates the application of advanced statistical models to analyze the Malaysian stock market, with a focus on the ARIMA-GARCH model. Traditional ARIMA models, following the Box-Jenkins approach, are designed to forecast the mean behavior of financial time series, assuming stationarity with constant or seasonally dependent variances. However, these models overlook variations in conditional variance, which are crucial for capturing the nonlinear dynamics often present in financial data. Although the statistical properties of the Malaysian financial market have been widely studied, the adoption of heteroskedastic models that account for non-constant variances remains limited. To address this gap, this research integrates GARCH with ARIMA models to capture both serial dependence and time-varying volatility in daily closing prices. The study focuses on the financial risks of three major Malaysian banks that are Maybank, Public Bank, and CIMB Bank, using a model that effectively reflects market fluctuations. Analyzing daily stock prices from 2000 to 2023, the study employs two key risk measures, namely Value at Risk (VaR) and Expected Shortfall (ES), which help estimate potential losses under adverse conditions. The findings reveal varying risk levels, with Maybank showing a 1.1% VaR, CIMB Bank 1.7%, and Public Bank 0.7%. This research offers valuable insights for enhancing risk management practices within Malaysia’s banking sector and provides a framework that can benefit other emerging markets. ©2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Automatic Pneumonia Detection Through Chest X-Ray Image-Based 4

Automatic Pneumonia Detection Through Chest X-Ray Image-Base...

引用

4th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2023

作者： Ramli, Anis Amirah Binti Zulkifli, Zalikha Ahmad, Samsiah Ghazali, Nurulhuda Sso Cardworks Kuala Lumpur Malaysia College of Computing Informatics & Mathematics Universiti Teknologi Mara Perak Branch Perak Malaysia College of Computing Informatics & Mathematics Universiti Teknologi Mara Melaka Branch Melaka Malaysia

ISBN: (纸本)9798350318432

Pneumonia is a well-known inflammatory lung illness that needs to be diagnosed quickly and correctly to be effectively treated. Chest X-ray diagnosis of pneumonia is difficult, particularly in disadvantaged clinical settings. The confusing radiographic appearance of pneumonia frequently results in incorrect diagnoses and drawn-out diagnostic processes. Hence, this study aims to develop automated pneumonia detection prototype through X-ray image-based which can help in the early and efficient diagnosis of pneumonia, enabling timely treatment and potentially reducing the burden on radiologists or healthcare professionals. To accomplish this, Discrete Wavelet Transform (DWT) and bilateral filter are used to reduce noise from X-ray images. The classification was performed by using Convolutional Neural Networks (CNN) to generate evaluation metrics to determine the learning algorithm's performance. A set of 5,840 X-ray images of a normal chest and a pneumonia-infected chest were used for automation testing using CNN as models to generate the confusion matrix and performance accuracy. The trained CNN model shows encouraging results, categorising both pneumonia-positive and pneumonia-negative cases with outstanding accuracy, recall, and F1-score of 96.0%. This study shows the potential of automated pneumonia diagnosis utilising chest X-ray images, providing a helpful tool to help medical practitioners to make prompt and accurate assessments. The main drawback would be the absence of demographic information. Future suggestions include incorporating demographic data even more and enhancing the model's capacity to consider patients' histories. This study contributes to the development of automated pneumonia diagnosis by utilising deep learning techniques and improving diagnostic precision and effectiveness in clinical practice. © 2023 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Innovative Byzantine Fault Tolerance in Hyperledger Fabric with BDLS 6

Innovative Byzantine Fault Tolerance in Hyperledger Fabric w...

引用

6th International Conference on Blockchain computing and Applications, BCCA 2024

作者： Al Salih, Ahmed Wang, Yongge University of North Carolina at Charlotte College of computing and informatics Software and Information Systems Department CharlotteNC United States

ISBN: (纸本)9798350351538

Decentralized systems are integral to various sectors, including public and private organizations. A key component of these systems is the dissemination protocol. Hyperledger Fabric, a prominent production-ready distribution network, allows for a pluggable consensus protocol, but has historically lacked detailed technical guidance for implementing such modules. Initially, Fabric employed Kafka and later switched to Raft, both Crash Fault Tolerant (CFT) protocols that do not support Byzantine Fault Tolerance (BFT). Recently, Hyperledger Fabric introduced SmartBFT in its 3.0 release, a new BFT solution. However, SmartBFT, based on the PBFT family, suffers from high message complexity that scales poorly with network growth, undermining efficiency for large-scale implementations in industries such as healthcare, finance, and education. Our research demonstrates that the message complexity of SmartBFT grows quadratically with the number of orderer nodes, leading to significant communication overhead. In contrast, our proposed implementation of BDLS maintains linear message complexity, making it more scalable and efficient for large networks. This stark contrast highlights BDLS’s superior scalability and efficiency. Additionally, BDLS consistently outperforms SmartBFT in throughput analysis of Fabric 3.0, achieving significantly higher TPS-40% and 20% of Raft’s TPS in LAN and WAN environments, respectively. All code is available in the GitHub repository: https://***/hyperledger-labs/bdls. © 2024 IEEE.

关键词： Decentralized systems

来源：评论

学校读者我要写书评

暂无评论

Elucidating Theory of Malaysian Data Crisis in Demystifying Dark Data Catalyst 6

Elucidating Theory of Malaysian Data Crisis in Demystifying ...

引用

6th IEEE Symposium on Computers and informatics, ISCI 2024

作者： Ajis, Ahmad Fuzi Md Ibrahim, Ag. Asri Ag Verma, Manoj Kumar UiTM Cawangan Johor Center of Information Science College of Computing Informatics and Mathematics Segamat Malaysia University Malaysia Sabah Faculty of Computing and Informatics Kota Kinabalu Malaysia Mizoram University Department of Library and Information Science Aizawl India

ISBN: (纸本)9798350353853

This article presents the findings of a research on the dark data phenomenon faced by Small and Medium Enterprises (SME) in Malaysia in connection to the features of dark data from SME perspectives. The dark data was found to be influenced by the data shadow in the form of grey and black data which each differentiated by the intensity of data darkness, a condition that influenced data from being found and utilized. In this study, there were 18 samples produced from Inductive Grounded & Emergent Theory Sampling, which was used to discover acceptable samples for the study, were subjected to qualitative research. Using semi-structured interviews that were recorded, transcribed, and analyzed using the Grounded Theory Methodology, data was obtained. The outcomes of the study emphasized on the emergence of Data Crisis which found to be the major factors contributing to the dark data often found in SME archives. The research demonstrates that there is a dearth of literature on dealing with dark data, indicating that dark data epistemology is still emerging. The findings indicated that the Data Crisis is a situation in which a business proprietor is confronted with the repercussions of inadequate data management. On the basis of the experiences of Malaysian SMEs, a model was proposed to elucidate the data crisis. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks 21

CE-QArg: Counterfactual Explanations for Quantitative Bipola...

引用

21st International Conference on Principles of Knowledge Representation and Reasoning, KR 2024

作者： Yin, Xiang Potyka, Nico Toni, Francesca Department of Computing Imperial College London United Kingdom School of Computer Science and Informatics Cardiff University United Kingdom

ISBN: (纸本)9781956792058

There is a growing interest in understanding arguments’ strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument’s strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CEQArg on randomly generated QBAFs. © 2024 Proceedings of the International Conference on Knowledge Representation and Reasoning. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Security: A Comparative Study of CNN and RNN-Based Anomaly Detection Using the CICIoT2023 Dataset

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第5期52卷 1424-1441页

作者： Al-Ghamdi, Amal M. Alansari, Marwah M. at College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Information Technology Department College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

The rapid growth of Internet of Things (IoT) devices has resulted in numerous security challenges. Anomaly detection has become a crucial aspect of IoT security, as it helps identify unusual behaviors and potential threats within IoT networks. Deep learning techniques have shown considerable potential in recognizing anomalies across various domains. However, the dynamic and continuously developing nature of cyberattacks complicates the process of monitoring and identifying among different types of attacks effectively. This study aims to enhance IoT security by conducting a comparative analysis of two deep learning algorithms: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). We deploy these models on the new CICIoT2023 dataset to detect large-scale attacks targeting IoT devices. Our findings reveal that the CNN model outperforms others with an accuracy of 98%, while the BiLSTM model achieves 85%, and the hybrid CNN-BiLSTM model reaches 94%. These results show that CNNs are better at extracting spatial features and that hybrid models might be able to use both spatial and temporal dependencies. By providing insights into model selection and optimization, this research contributes to the development of robust intrusion detection systems for IoT security. © (2025), (International Association of Engineers). All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Transforming Secondary School Chemistry Learning with Virtual Reality 22

Transforming Secondary School Chemistry Learning with Virtua...

引用

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

作者： Chew, Chiou Sheng Zafarin, Muhammad Nabil Shah Zain, Nurul Hidayah Mat Aminuddin, Raihah Tan, Tse Guan Chin, Kim On Universiti Teknologi MARA Melaka Branch College of Computing Informatics and Mathematics Jasin Campus Melaka Malaysia Universiti Malaysia Kelantan Faculty of Creative Technology and Heritage Malaysia Universiti Malaysia Sabah Faculty of Computing and Informatics Sabah Malaysia

ISBN: (纸本)9798331510077

In secondary schools, traditional chemistry instruction often depends on lecture-based approaches and occasional hands-on experiments, which may limit students' grasp of complex concepts like chemical reactions and molecular behaviour. This study addresses the need for enhanced educational tools by introducing a Virtual Reality (VR) application designed to enrich chemistry learning through immersive, interactive experiences. The VR tool allows students to simulate chemical reactions with adjustable parameters, such as temperature and concentration, enabling safe, hands-on exploration of complex processes. Usability was assessed among 30 secondary school students in Malaysia using the System Usability Scale (SUS), a standardized measure that gauges user experience across factors like functionality and ease of use. Findings showed a strong average SUS score of 91.25, indicating high usability and positive engagement from users. These results suggest that incorporating VR into the chemistry curriculum can help make challenging topics more accessible and engaging, supporting the modernization of science education. Future studies will look to expand the sample size and investigate additional chemistry topics to validate the tool's educational benefits further. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Quantification of Liberica Coffee Morphology in Lipa City 11

Machine Learning Quantification of Liberica Coffee Morpholog...

引用

11th International Conference on Electrical Engineering, Computer Science and informatics, EECSI 2024

作者： Balazon, Francis G. Alvaro, Jonh Vincent M. Fabregas, Mike Clarence F. Sabado, Brian Jerome E. Batangas State University The National Engineering University Lipa College of Informatics and Computing Sciences Batangas Lipa City Philippines

ISBN: (纸本)9798350355314

Investigating the morphological characteristics of Liberica green coffee beans presents challenges due to their irregular shapes and potential overlaps within images. This study aimed to develop a robust image analysis pipeline for quantifying green bean morphology and exploring potential variations between farms within the Lipa City region. A comprehensive coffee bean collection protocol was established, and a diverse image dataset was created. Image preprocessing, including normalization, augmentation, and enhancement techniques, optimized the data for analysis. A U-Net convolutional neural network was developed for semantic segmentation, achieving remarkable performance with an accuracy of 99.83% and an IoU score of 0.985. This enabled the precise extraction of morphological features from individual bean instances. Principal Component Analysis (PCA) revealed the primary contributors to morphological variance, and Multivariate Analysis of Variance (MANDVA) demonstrated statistically significant differences in the overall combination of morphological features between farms. These findings suggest that farm origin, potentially due to variations in environmental conditions, cultivation practices, or bean varieties, influences the physical characteristics of Liberica green coffee beans. This study provides a powerful framework for future investigations into the relationship between morphology, quality assessment, and optimization of processing techniques within the coffee industry. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lightweight Facial Emotion Recognition Systems for Visually Impaired People 12

Enhanced Lightweight Facial Emotion Recognition Systems for ...

引用

12th IEEE Conference on Systems, Process and Control, ICSPC 2024

作者： Shehada, Dina Turky, Ayad Rabie, Tamer Hussain, Abir University of Dubai College of Engineering and IT Dubai United Arab Emirates University of Sharjah College of Engineering Department of Electrical Engineering Sharjah United Arab Emirates University of Sharjah College of Computing & Informatics Department of Computer Science Sharjah United Arab Emirates University of Sharjah College of Computing & Informatics Department of Computer Engineering Sharjah United Arab Emirates

ISBN: (纸本)9798350391398

Facial expressions are a vital component of human communication, conveying emotional information that enhances the social experience. However, for individuals with visual impairments, perceiving and interpreting facial expressions can be challenging, hindering their ability to engage fully in social interactions. This paper presents an enhanced facial emotion recognition system specifically designed to aid visually impaired individuals. Two enhanced approaches for facial emotion recognition systems are proposed. The first approach consolidates negative emotions (anger, fear, sadness, disgust) into a single class, while the second approach incorporates diverse training datasets from real-world environments. The negative emotion consolidation approach achieved 90.9% and 94.7% accuracy on the FER2013 and CK+ datasets, respectively. While, the diverse dataset integration approach achieved 84.9% and 70.6% accuracy on FER2013 and CK+ datasets, respectively. This is a significant improvement when benchmarked with other approaches available in the literature. The feasibility of the enhanced proposed systems as assistive technology for the visually impaired indicated its ability to be applied in real-world applications. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Utilising the YOLOv3 Algorithm for the Student Posture Recognition System in Classroom Settings 8

Utilising the YOLOv3 Algorithm for the Student Posture Recog...

引用

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

作者： Nazaruddin, Mohamad Nazmi Zharfan Afirdaus Zainal Abidin, Nor Aminuddin, Raihah Samah, Khyrina Airin Fariza Abu Ibrahim, Asma Zubaida Mohamed Yusoh, Syarifah Diyanah Mangshor, Nur Nabilah Abu Nasir, Siti Diana Nabilah Mohd College of Computing Informatics Mathematics Malacca Malaysia MARA University of Technology College of Computing Informatics Mathematics Malacca Malaysia City University Selangor Malaysia Multimedia University Malacca Malaysia Hull University England United Kingdom

ISBN: (纸本)9798350315516

Effective student-teacher interaction helps transfer knowledge, clarify concepts, and create a conductive learning environment the effectiveness of the interaction can be seen through students' behaviour and various factors, such as pos- ture and gestures in the classroom. However, educators face significant difficulties in tracking each student's performance and behaviour during class therefore, this study focuses on student posture recognition in classroom settings, which is essential for monitoring student behaviour and engagement during lectures the proposed system utilises the YOLOv3 machine learning model for real-time detection. A dataset of student postures was collected from Google Images, and the data was used to train a deep neural network the model was then tested on classroom images and compared to manual annotations the results showed that the model can accurately recognise student postures with high precision, recall, F1-score, and mean average precision (mAP), achieving an average precision of 88%, recall of 89%, F1-score of 88%, and mAP of 95.20% the real-time processing capability of YOLOv3 allows for immediate posture detection during lectures in a classroom;this may help educators monitor student behaviour and engagement. © 2023 IEEE.

关键词： Students

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：