检索结果-内蒙古大学图书馆

IAENG International Journal of Computer Science 2024年第3期51卷 301-307页

作者： Alia, Nurul Anis Yusof, Mohd Kamir Safei, Suhailan Universiti Sultan Zainal Abidin Faculty of Informatics and Computing TerengganuBesut 22200 Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing TerengganuBesut 22200 Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing TerengganuBesut 22200 Malaysia

To solve the problem of universal data schema in data integration, a native JSON+ method based on JSON is proposed to provide a universal data schema to improve the performance of data insertion response time and query processing response time. A native JSON+ provides a universal schema to allow data exchange or data sharing among applications. First, data is converted into JSON format. Second, elements and attributes are stored into relational database management systems (RDBMS). Third, each element and attribute are mapping to the data in JSON format. Based on the experiments have been done by using three different datasets (SigmodRecord, NASA and DBLP), the results indicate a native JSON+ performance in term of data insertion response time and query processing response time are better compared to NXD. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

On detecting stock price manipulation attacks: a comprehensive systematic literature review

引用

Multimedia Tools and Applications 2025年 1-78页

作者： Alfajeer, Amal Altaweel, Ala Bouridane, Ahmed Mouheb, Djedjiga Aslam, Sidra College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Stock market is pivotal to economical systems. It is a platform where listed stocks of companies can be bought/sold by market participants to gain profit. In 2020, the total capitalization of all markets reached $95 trillion. Within such profiting platforms, malicious attacks like stock price/market manipulation are conducted. Stock price manipulation attack refers to the strategic act of trading either a stock, a future (derivative financial contracts), or a security (financial instrument) to increase or decrease their prices. Hence, making significant profits. Manipulation types vary by sources and/or exploited methods. To detect and deter such attacks/practices, extensive research have been conducted. To further assist the future studies, in this paper, we conduct a systematic literature review to extract research articles relevant to stock price/market manipulation attacks and their state-of-art detection systems/solutions. To the best of our knowledge, this is the first systematic literature review that is based on a predefined search methodology and systematically collects the relevant articles that were published between 2011 and 2021. After applying the systematic search methodology, we extracted and surveyed 66 articles and classified them into four main detection approaches. Namely, statistical-based, Machine Learning based, system-based/artefacts, and visualization-based/observation-based. We provide a thorough comparison among the detection systems in terms of utilized datasets, leveraged features, employed optimization techniques, and applied performance measures. Our survey also identifies and discusses a set of existing research gaps such as generality of detection approaches, near/real-time detection capability, validity of real/synthesised datasets, etc. We concluded our survey by proposing several research topics and recommendations to be investigated and addressed by future works. © The Author(s), under exclusive licence to Springer Science+Busine

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Recognition of Facial Movements of App Designed for Rehabilitation of People with Facial Paralysis

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第13期18卷 112-129页

作者： Corrêa, Ana Grasielle Dionísio Ravaglio, Anna de Souza Cruz Navikas, Flávio Hergersheimer Do Amaral, Jucelio Delmondes Filho, Paulo César Machado Cunha, Daniela Vieira Silva, Matheus Gois de Lima Rodrigues, Bruno da Silva Faculty of Computing and Informatics and the Postgraduate Program in Applied Computing Mackenzie Presbiterian University São Paulo Brazil

Peripheral facial paralysis (PFP) causes deficits in muscle and sensory functions of the face due to damage to the facial nerve. In this study, we evaluated the effectiveness of the "Fisiobem" app in rehabilitating patients with PFP through facial mimicry exercises. The app uses the device’s camera to identify the user and measure the range of motion during the exercises, applying the ARKit framework to quantify the intensity of the movements. We conducted a usability study with 34 participants unaffected by PFP, performing mimics with different amplitudes. Results show that glasses did not affect recognition accuracy in exercises such as raising eyebrows, frowning, and closing the eyes tightly. As for wrinkling the nose exercise, glasses impacted higher intensities. As for the beard or mustache, lower lip protrusion, compressing the lips, smiling, showing teeth and blowing out filling cheeks were not affected. However, when smiling with lips together, beard and mustache influenced intensities above 75%. It is important to highlight that this study has limitations, such as the sample size and lack of consideration for ethnic diversity among participants. Future research with larger and more diverse samples is needed to validate and generalize these findings and explore the nuances of interactions between facial features and facial recognition algorithms. Despite these limitations, the approach facilitated by the "Fisiobem" application offers significant benefits, especially for patients with PFP who face challenges in accessing specialized therapists. It allows patients to complement their treatment by performing guided facial mimicry exercises at home. The application helps individuals accurately perform the exercises and effectively track the progress of their rehabilitation. © 2024 by the authors of this article.

关键词： Glass

来源：评论

学校读者我要写书评

暂无评论

DySARNet: a lightweight self-attention deep learning model for diagnosing dysarthria from speech recordings

引用

Multimedia Tools and Applications 2024年 1-49页

作者： Montalbo, Francis Jesmar P. College of Informatics and Computing Sciences Batangas State University Bantangas Philippines

Dysarthria, a neurological condition impairing speech, has garnered significant research interest in Deep Learning (DL). Curent studies underscore DL’s potential in automating dysarthria diagnosis and severity classification, utilizing well-known benchmark datasets like TORGO and UA-Speech. However, existing DL for dysarthria diagnosis, like Deep Neural Networks, are often computationally expensive, complex, and lack context awareness. This paper addresses these issues by proposing a Densely Squeezed-and-excited Attention-gated Residual convolutional neural Network (DySARNet) designed for dysarthria diagnosis and severity estimation. DySARNet aims to provide a cost-effective solution compatible with various devices, including mobile phones. DySARNet made this possible by integrating a Lean Separable Dense Block (LSDB) that enhances feature reuse while preventing a massive parameter increase through separable depthwise convolutions (SDWConv). For improved context understanding and awareness, DySARNet employs a Squeeze-and-Excited Lightweight Residual Attention-gated (SELRA) mechanism, a tailored self-attention mechanism that offers robust attention at a low cost by squeezing additional parameters through SDWConv and depthwise convolutions. DySARNet achieves 99.03% and 98.77% accuracy in diagnosing dysarthric and non-dysarthric speech recordings and 99.20% and 96.09% in classifying dysarthria severity using the TORGO and UA-Speech datasets. With only 33 K parameters and 0.04 G-FLOPs, DySARNet surpasses most state-of-the-art models in cost-effectiveness and overall performance. In conclusion, DySARNet, with its SELRA and LSDB components, reveals significant promise in enhancing dysarthria diagnosis by automatically recognizing the presence of dysarthria and classifying its severity more efficiently. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Audio signal processing

来源：评论

学校读者我要写书评

暂无评论

Classifying Fake Profiles on X with Multinomial Naïve Bayes 10

Classifying Fake Profiles on X with Multinomial Naïve Bayes

引用

10th IEEE Information Technology International Seminar, ITIS 2024

作者： Azmin, Nur Akifah Zainuddin, Nurulhuda Mohamad, Masurah College of Computing Informatics & Mathematics Melaka Malaysia College of Computing Informatics & Mathematics Perak Malaysia

ISBN: (纸本)9798331521295

Online social networks have experienced rapid growth, facilitating massive connections among users. However, this expansion has also led to a significant increase in fake users, putting user privacy at risk as these deceptive entities exploit the platform's accessibility to gather and misuse personal data. The proliferation of fake profiles poses a serious threat to the social fabric of the X world, potentially undermining user interactions. This research aims to classify fake profiles that mimic genuine accounts, making detection challenging. The proposed solution utilizes a Multinomial Naïve Bayes model, offering an innovative method to combat the issue of fake profiles. The model demonstrates promising results, achieving 94.67% accuracy, 90% precision, 90% recall, and a 95% area under the curve (AUC). The study concludes by calling for further research to expand the range of training examples for the model, enhancing its ability to accurately differentiate between fake and genuine X profiles. It also emphasizes the importance of maintaining key features within the model to ensure an accurate representation of the subtle differences between genuine and fake profiles. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction

引用

Neural computing and Applications 2024年第27期36卷 16911-16940页

作者： Abu Talib, Manar Bou Nassif, Ali Azzeh, Mohammad Alesh, Yaser Afadar, Yaman Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics Sharjah United Arab Emirates King Hussein School for Computing Sciences Princess Sumaya University for Technology Amman Jordan

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A QoS-Aware Energy Optimization Framework for Mobile Devices Using DRL and Edge computing 4

A QoS-Aware Energy Optimization Framework for Mobile Devices...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Mokgethi, Chandapiwa Sigwele, Tshiamo Selvaraj, Rajalakshmi Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

The proliferation of computationally intensive mobile applications like Augmented Reality (AR), Speech Recognition, and Mobile Gaming has led to an alarming rise in mobile energy consumption, raising the need for frequent recharging of mobile devices. This frequent recharging leads to degradation of mobile device's battery health resulting in reduced battery capacity, shorter usage cycles, and ultimately increased costs associated with battery replacements. The current mobile energy optimization frameworks are unable to effectively handle the dynamic and realtime nature of mobile environments with unpredictable variables. This research proposes a Deep Reinforcement Learning (DRL) model to optimize energy efficiency in mobile devices using Mobile Edge computing (MEC) to handle varying workloads and dynamic environment while maintaining Quality of Service (QoS) where computationally intensive applications are optimally offloaded to edge cloud servers. The result shows that the proposed outperforms current works by reducing energy consumption and average latency by 27.5% and 35% respectively. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Investigating Developer Experiences with UI Components in Flutter: Challenges and Implications

Investigating Developer Experiences with UI Components in Fl...

引用

2024 International Visualization, informatics and Technology Conference, IVIT 2024

作者： Donglan, Zou Bin Darus, Mohamad Yusof Ramli, Azlin Binti College of Computing Informatics and Mathematics Malaysia

ISBN: (纸本)9798350354447

The rapid proliferation of smartphones, particularly those using the Android operating system, has positioned Android as the leading platform in the mobile market. With the advent of various mobile app development frameworks such as Ionic, Flutter, Corona SDK, and Xamarin, developers face the challenge of selecting the optimal framework for their projects. This study focuses on the Flutter framework, a cross-platform development tool by Google, exploring developers' experiences with User interface (UI) construction, specifically in handling common components such as network images and animations. A comprehensive survey was conducted, targeting Flutter developers from diverse backgrounds, including engineers, university students, and instructors. The survey aimed to identify the challenges associated with using Flutter's NetworkImage feature and Animation component. Results indicate significant issues with performance, network connectivity, image quality, dependence on third-party libraries, cache management, and traffic consumption for network images. Similarly, animations in Flutter pose challenges related to memory insufficiency, varying effects across different devices, and performance impacts on user experience. The findings highlight the necessity for enhanced support and innovative solutions within the Flutter framework to address these limitations. This study serves as a resource for developers to better understand and navigate the complexities of Flutter, and it underscores the importance of further research to improve mobile application development technologies. Future investigations should broaden the scope to include more diverse application cases and larger sample sizes to build on these initial insights. © 2024 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

A Gap Analysis On Blockchain Frameworks For Managing Academic Transcripts 4

A Gap Analysis On Blockchain Frameworks For Managing Academi...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bayani, Pelontle Sigwele, Tshiamo Kuthadi, Venumadhav Department of Computing and Informatics Palapye Botswana

ISBN: (纸本)9798331518981

Academic transcript systems have traditionally been managed independently by educational institutions, leading to challenges in interoperability, security, and data integrity. Blockchain technology, characterized by decentralization, immutability, and transparency, presents a promising solution to these issues. The introduction of blockchain technology offers a transformative approach to managing academic transcripts, providing a unified, secure, and transparent platform. This literature review examines current blockchain based academic transcript frameworks then critically and graphically analyses them based on the identified research objectives and gaps. The review's critical analysis resulted in significant trends, patterns and insights as follows. The current research's major objectives and their adoption percentages are enhancing security (33%), improving scalability (27%), ensuring transparency (23%) and addressing interoperability (17%). The major gaps identified are lack of interoperability (42%), security issues (42%) and high cost (11%) and others. Based on these insights, this work recommends current researchers to concentrate more on enhancing security and interoperability in academic transcript frameworks. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Annotating Activity Data with Transformer-based Deep Learning Model 24

Annotating Activity Data with Transformer-based Deep Learnin...

引用

7th International Conference on Information Management and Management Science, IMMS 2024

作者： Salehi, Parsa Chua, Sook-Ling Foo, Lee Kien Faculty of Computing and Informatics Multimedia University Malaysia

ISBN: (纸本)9798400716997

There are many activity recognition systems based on supervised learning that have been proposed over the years. One problem with supervised learning is that it requires sufficient number of labelled data for training. The majority of the labelling tasks are done manually by the user themselves. This process is rather time-consuming and tedious. Although there are studies that attempt to use active learning-based methods to assist in the annotation process, these methods still require some amount of effort from the user and are impractical, especially when implementing a home for the elderly. In this paper, we propose an automated labelling approach using a transformer-based deep learning model to label the daily activities. Our method leverages on spatio-temporal information for class annotation. We evaluated our method on publicly available datasets. © 2024 Owner/Author.

关键词： Self-supervised learning

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：