检索结果-内蒙古大学图书馆

2nd International Conference on Computer and information Sciences, ICCIS 2020

作者： Bramantoro, Arif Syamsuddin, Irfan Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah Saudi Arabia Politeknik Negeri Ujung Pandang Department of Computer and Networking Engineering Makassar Indonesia

ISBN: (纸本)9781728154671

Today grid computing powered by web service technology has been a research interest for decades. Several grids of language services are available in Internet as part of daily activity. Melayu Grid is proposed to share Indonesian, Malay and regional language resources. To ease the sharing, each language is located as a distinctive concept in language service ontology and eventually measured its semantic closeness to other languages. By utilizing semantic closeness, it is expected that the endangered language resource that has less amount of its speaker can take advantage by replacing it with other language resource that has better resources and speakers. This project implements service grid architecture as a culture grid for Indonesia and Malaysia to balance cultural differences and conflicts in these two neighboring countries. Multicriteria optimization is utilized to adapt the multi culture feature of several language services. It substitutes several regional languages services that are coming from the same language families or having similar linguistic vocabularies, syntax, morphology and semantics. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Denoising Medical Images Using Deep Learning in IoT Environment

引用

Computers, Materials & Continua 2021年第12期69卷 3127-3143页

作者： Sujeet More Jimmy Singla Oh-Young Song Usman Tariq Sharaf Malebary School of Computer Science and Engineering Lovely Professional UniversityJalandharIndia Software Department Sejong UniversitySeoulKorea College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology in RabighKing Abdulaziz UniversityJeddah21911Saudi Arabia

Medical Resonance Imaging(MRI)is a noninvasive,nonradioactive,and meticulous diagnostic modality capability in the field of medical ***,the efficiency of MR image reconstruction is affected by its bulky image sets and slow process ***,to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network(SANR_CNN)for eliminating noise and improving the MR image reconstruction *** proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality,and SARN algorithm is used for building a dictionary learning technique for denoising large image *** proposed SANR_CNN model also preserves the details and edges in the image during *** experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio(PSNR),structural similarity index(SSIM),and mean squared error(MSE).The proposed SANR_CNN model achieved higher PSNR,SSIM,and MSE efficiency than the other noise removal *** proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.

关键词： Medical resonance imaging convolutional neural network denoising contrast enhancement internet of things rheumatoid arthritis

来源：评论

学校读者我要写书评

暂无评论

Intelligent Dynamic Aging Approaches in Web Proxy Cache Replacement

引用

Journal of Intelligent Learning Systems and Applications 2015年第4期7卷 117-127页

作者： Waleed Ali Siti Mariyam Shamsuddin Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Rabigh Kingdom of Saudi Arabia Faculty of Computing Universiti Teknologi Malaysia Johor Malaysia

One of commonly used approach to enhance the Web performance is Web proxy caching technique. In Web proxy caching, Least-Frequently-Used-Dynamic-Aging (LFU-DA) is one of the common proxy cache replacement methods, which is widely used in Web proxy cache management. LFU-DA accomplishes a superior byte hit ratio compared to other Web proxy cache replacement algorithms. However, LFU-DA may suffer in hit ratio measure. Therefore, in this paper, LFU-DA is enhanced using popular supervised machine learning techniques such as a support vector machine (SVM), a naive Bayes classifier (NB) and a decision tree (C4.5). SVM, NB and C4.5 are trained from Web proxy logs files and then intelligently incorporated with LFU-DA to form Intelligent Dynamic- Aging (DA) approaches. The simulation results revealed that the proposed intelligent Dynamic- Aging approaches considerably improved the performances in terms of hit and byte hit ratio of the conventional LFU-DA on a range of real datasets.

关键词： Cache Replacement Web Proxy Server Dynamic-Aging Approaches Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Fog Centre with Balking, Reneging and Retention 5

Performance Evaluation of Fog Centre with Balking, Reneging ...

引用

5th International Conference on information Management and Machine Intelligence, ICIMMI 2023

作者： Sinha, Sameer Patra, Sudhansu Shekhar Dash, Bibhuti Bhusan Mishra, Manoj Ranjan Rout, Suchismita Barik, Lalbihari HCL Technologies Noida India School of Computer Applications KIIT Deemed to be University India Department of Information Systems Faculty of Computing and Information Technology in Rabigh King Abdul Aziz University Saudi Arabia

ISBN: (纸本)9798400709418

Sensors and Internet of Things (IoT) devices are being used for more and more purposes every day. To handle the processing and storage requirements of time-sensitive applications, a new computing paradigm known as "Fog computing"has arisen. It makes use of low-powered end devices that are connected to the IoT and include sensors. The fog nodes' virtual computers (VMs) handle the IoT workloads' instant processing and analysis. Efficiently scaling fog centres to fulfil the maximum amount of client requests that the fog system can fulfil is one of the open research challenges. The service providers want to maintain consumer demands in the fog system by providing efficient services. A multi-server queueing model with a retention plan is modeled in order to assess the fog system's various performance metrics. © 2023 ACM.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Comprehensive analysis of Student’s Academic Failure Classification through Role-Sphere Influence and Flow betwenness centrality

引用

Procedia Computer Science 2017年 116卷 509-515页

作者： Andi Besse Firdausiah Mansur Norazah Yusof Ahmad Hoirul Basori Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Kingdom of Saudi Arabia

Analysing student behavior such as failure or success or even their study pattern is essential for further improvement in E-learning system. This study observed the profile elements of student that contribute to the failures rate of student. There are several factors which are affecting the student behavior such as: relative bond, education schedule, nonattendance, school level of father and mother, period of Voyage and etc. The research that presented in this paper mainly focus on monitoring elements that potential to ruin students performance. Based on the collected data, it will calculate the gap between each factors to measure the flow betwenness and role-influence analysis of students who has high family quality time, free time and gout time tends to High value on efficiency, emergent leader and in the know of influence network. This mean student who has flow great betwenness value among the other will control the flow of network and this person will encourage other member in network and can be act as a leader. It is found that goouttime and freetime as well as study time has strong correlation with catastrophe of study where student that has high flow betwenness tend to spread their influence toward other student. Teacher and School management should aware to this kind of student and take action properly. The result of study is important for learning improvement in the future, whether system or person improvement, so it can drive to better education in the future.

关键词： Students Academic failure Social network mining analysis role-sphere influence Flow betwenness centrality

来源：评论

学校读者我要写书评

暂无评论

ASOS at NADI 2024 shared task: Bridging Dialectness Estimation and MSA Machine Translation for Arabic Language Enhancement 2

ASOS at NADI 2024 shared task: Bridging Dialectness Estimati...

引用

2nd Arabic Natural Language Processing Conference, ArabicNLP 2024

作者： Nacar, Omer Sibaee, Serry Alharbi, Abdullah I. Ghouti, Lahouari Koubaa, Anis Robotics and Internet-of-Things Lab Prince Sultan University Riyadh12435 Saudi Arabia Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9798891761322

This study undertakes a comprehensive investigation of transformer-based models to advance Arabic language processing, focusing on two pivotal aspects: the estimation of Arabic Level of Dialectness and dialectal sentence-level machine translation into Modern Standard Arabic. We conducted various evaluations of different sentence transformers across a proposed regression model, showing that the MARBERT transformer-based proposed regression model achieved the best root mean square error of 0.1403 for Arabic Level of Dialectness estimation. In parallel, we developed bi-directional translation models between Modern Standard Arabic and four specific Arabic dialects—Egyptian, Emirati, Jordanian, and Palestinian—by fine-tuning and evaluating different sequence-to-sequence transformers. This approach significantly improved translation quality, achieving a BLEU score of 0.1713. We also enhanced our evaluation capabilities by integrating MSA predictions from the machine translation model into our Arabic Level of Dialectness estimation framework, forming a comprehensive pipeline that not only demonstrates the effectiveness of our methodologies but also establishes a new benchmark in the deployment of advanced Arabic NLP technologies. ©2024 Association for Computational Linguistics.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

ASOS at KSAA-CAD 2024: One Embedding is All You Need for Your Dictionary 2

ASOS at KSAA-CAD 2024: One Embedding is All You Need for You...

引用

2nd Arabic Natural Language Processing Conference, ArabicNLP 2024

作者： Sibaee, Serry Alharbi, Abdullah I. Ahmed, Samar Nacar, Omer Ghouti, Lahouri Koubaa, Anis Robotics and Internet-of-Things Lab Prince Sultan University Riyadh12435 Saudi Arabia Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9798891761322

Semantic search tasks have grown extremely fast following the advancements in large language models, including the Reverse Dictionary and Word Sense Disambiguation in Arabic. This paper describes our participation in the Contemporary Arabic Dictionary Shared Task. We propose two models that achieved first place in both tasks. We conducted comprehensive experiments on the latest five multilingual sentence transformers and the Arabic BERT model for semantic embedding extraction. We achieved a ranking score of 0.06 for the reverse dictionary task, which is double than last year’s winner. We had an accuracy score of 0.268 for the Word Sense Disambiguation task. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ASOS at ArAIEval Shared Task: Integrating Text and Image Embeddings for Multimodal Propaganda Detection in Arabic Memes 2

ASOS at ArAIEval Shared Task: Integrating Text and Image Emb...

引用

2nd Arabic Natural Language Processing Conference, ArabicNLP 2024

作者： Alhabashi, Yasser Alharbi, Abdullah I. Ahmed, Samar Sibaee, Serry Nacar, Omer Ghouti, Lahouari Koubaa, Anis Robotics and Internet-of-Things Lab Prince Sultan University Riyadh12435 Saudi Arabia Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9798891761322

This paper describes our participation in the ArAIEval Shared Task 2024, focusing on Task 2C, which challenges participants to detect propagandistic elements in multimodal Arabic memes. The challenge involves analyzing both the textual and visual components of memes to identify underlying propagandistic messages. Our approach integrates the capabilities of MARBERT and ResNet50, top-performing pre-trained models for text and image processing, respectively. Our system architecture combines these models through a fusion layer that integrates and processes the extracted features, creating a comprehensive representation that is more effective in detecting nuanced propaganda. Our proposed system achieved significant success, placing second with an F1-score of 0.798. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Secured Data Transmission using Metadata Logger Manipulation Approach 2

Secured Data Transmission using Metadata Logger Manipulation...

引用

2nd East Indonesia Conference on Computer and information technology, EIConCIT 2018

作者： Supriadi Wajiansyah, Agusma Purwadi, Hari Malani, Rheo Yunianta, Arda Pratomo, Adi Department of Information Technology Politeknik Negeri Samarinda Samarinda Indonesia Faculty of Computing and Information Technology Rabigh King Abdulazis University Jeddah Makkah Saudi Arabia Dept. of Informatics Management Politeknik Negeri Banjarmasin Banjarmasin Indonesia

ISBN: (纸本)9781538680483

The telemetry is an automatic communication process where measurements and other data are collected at a remote point or cannot be accessed (called as a remote station) and transmitted to the receiving equipment (called as host station). This system is a data acquisition system in a large enough area which usually equipped with data loggers in the form of an electronic device that records data over time. Even most data loggers equipped with digital processors or computers. Various environmental conditions can affect the telemetry system, especially in the process of transmitting data from remote stations to the host. In this case, data security during transmission becomes very important. In this study, the discussion focused on how to build data packages in such a way that the data packet is not easy to recognize during the transmission process. The concept of the metadata manipulation approach is used to change the arrangement of the data package based on its address index through the transformation of three-dimensional cube-shaped data to become a metadata log. Data stored in the data logger converted into a three-dimensional data structure in the form of several cube-shapes based on its address index. In a certain way, all cube-shaped data transformed into a metadata log and stored in the metadata logger. This metadata log then transmitted to the host station to be converted back into a data log and stored into the host's data logger. The results of this study showed that the generated metadata log log has very different content compared to data log. Similarly, the size of their data bytes. The main key to this concept is how to choose a 3-D form representation of data according to data availability and how to change its orientation during the process of forming metadata logs. © 2018 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

ASOS at Arabic LLMs Hallucinations 2024: Can LLMs detect their Hallucinations:) 6

ASOS at Arabic LLMs Hallucinations 2024: Can LLMs detect the...

引用

6th Workshop on Open-Source Arabic Corpora and Processing Tools, OSACT 2024 with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation

作者： Sibaee, Serry Ahmed, Samar Nacar, Omer Alharbi, Abdullah I. Ghouti, Lahouri Kouba, Anis Robotics and Internet-of-Things Lab Prince Sultan University Faculty of Computing and Information Technology Rabigh King Abdulaziz University Riyadh 12435 Saudi Arabia Jeddah 22254 Saudi Arabia

ISBN: (纸本)9782493814364

This research investigates hallucination detection in Large Language Models (LLMs) using datasets in the Arabic language. As LLMs gain widespread application, they tend to produce hallucinations—grammatically coherent but factually inaccurate content—posing substantial challenges. We participated in the OSACT 2024 Shared-task, which focuses on the Detection of Hallucination in Arabic Factual Claims Generated by ChatGPT and GPT-4. Our approach evaluates several methods for detecting and mitigating hallucinations, employing models such as GPT-4, Mistral, and Gemini within an innovative experimental framework. Our findings demonstrate significant variability in the models’ ability to categorize claims as Fact-Claim (FC), Fact-Improvement (FI), and Non-Fact (NF), highlighting the challenges of dealing with hallucinations in morphologically complex languages. The results underline the necessity for more sophisticated modelling and training strategies to improve the reliability and factual accuracy of the content generated by LLMs. This study lays the foundation for future work on reducing the risks of hallucinations. Notably, we achieved an F1 score of 0.54 in detecting hallucinations with the GPT-4 model. © 2024 ELRA Language Resource Association.

关键词： Large datasets

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：