检索结果-内蒙古大学图书馆

TOWARDS THE DEVELOPMENT OF BALANCED SYNTHETIC DATA FOR CORRECTING GRAMMATICAL ERRORS IN ARABIC: AN APPROACH BASED ON ERROR TAGGING MODEL AND SYNTHETIC DATA GENERATING MODEL

arXiv

引用

arXiv 2025年

作者： Alrehili, Ahlam Alhothali, Areej Department of Computer Sciences Faculty of Computing and Information Technology King Abdulaziz University Saudi Electronic University Medina Saudi Arabia Department of Computer Sciences Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Synthetic data generation is widely recognized as a way to enhance the quality of neural grammatical error correction (GEC) systems. However, current approaches often lack diversity or are too simplistic to generate the wide range of grammatical errors made by humans, especially for low-resource languages such as Arabic. In this paper, we will develop the error tagging model and the synthetic data generation model to create a large synthetic dataset in Arabic for grammatical error correction. In the error tagging model, the correct sentence is categorized into multiple error types by using the DeBERTav3 model. Arabic Error Type Annotation tool (ARETA) is used to guide multi-label classification tasks in an error tagging model in which each sentence is classified into 26 error tags. The synthetic data generation model is a back-translation-based model that generates incorrect sentences by appending error tags before the correct sentence that was generated from the error tagging model using the ARAT5 model. In the QALB-14 and QALB-15 Test sets, the error tagging model achieved 94.42% F1, which is state-of-the-art in identifying error tags in clean sentences. As a result of our syntactic data training in grammatical error correction, we achieved a new state-of-the-art result of F1-Score: 79.36% in the QALB-14 Test set. We generate 30,219,310 synthetic sentence pairs by using a synthetic data generation model. Our data is accessible to the public1 © 2025, CC BY.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach for Enhanced Vulnerability Detection in Cloud Environments Using NIST and MITRE Frameworks 5

Hybrid Machine Learning Approach for Enhanced Vulnerability ...

引用

5th International Conference on Advanced Research in computing, ICARC 2025

作者： Lasantha, N W Chanaka Maduranga, M.W.P. Abeysekara, Ruvan Tilwari, Valmik Chakraborty, Nilotpal Sharma, Debashree Iic University of Technology Faculty of Graduate Studies Phnom Penh Cambodia University of Sri Jayewardenepura Department of Electrical and Electronic Engineering Nugegoda Sri Lanka Bcas Campus Faculty of Computing Colombo Sri Lanka Indian Institute of Information Technology Department of Computer Science Engineering Guwahati India Indian Institute of Information Technology Department of Electronics & Communication Engineering Guwahati India

ISBN: (纸本)9798331530983

Cloud security is challenged by constant adaptive cyber threats and traditional detection methods lack real time adaptability. In this paper, we propose a new hybrid ML approach stitching data from National Institute of Standards and technology (NIST) and MITRE Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) databases together. In contrast to existing methods, this framework combines, in unique and unprecedented fashion, ensemble ML models and Realtime data processing for increased detection accuracy and reduced false positives. This approach addresses specific challenges in the cloud environments and by leveraging standardised frameworks, it offers actionable audiences for efficient and effective vulnerability management process. The framework is validated by the experimental results which prove its robustness to evolution of the cybersecurity demands. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Deep Learning and Modern Machine Learning Methods for Predicting Australia's Precipitation

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 943-966页

作者： Farman, Hira Mastoi, Qurat-Ul-Ain Abbas, Qaiser Ahmad, Saad Alshahrani, Abdulaziz Jan, Salman Syed, Toqeer Ali Department of Computer Science Iqra University Karachi Institute of Economics and Technology Karachi74600 Pakistan School of Computing and Creative Technologies University of the West of England Bristol United Kingdom Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia Faculty of Computer Science IQRA University Karachi Pakistan Faculty of Computer Studies Arab Open University 512 United Kingdom Islamic University of Madinah CO 42351 Madinah Saudi Arabia

Floods are chaotic weather patterns that cause irreversible and devastating harm to people's lives, crops, and the socioeconomic system. It causes extensive property damage, animal mortality, and even human fatalities. To mitigate the risk of flooding, it is imperative to create an early warning system that can accurately forecast the amount of rain that will fall tomorrow. Rainfall forecasting is essential to the lives of people and is absolutely important everywhere in the world. The rainfall prediction model reduces risk and helps to prevent further human deaths. Statistics cannot reliably forecast rainfall since the atmosphere is dynamic. Due to the preceding factors, this study uses machine learning and deep learning techniques to estimate precipitation. The purpose of this study is to develop and evaluate a prediction model for forecasting rainfall of 5 cities of Australia (Darwin, Sydney, Perth airport, Melbourne, Brisbane). The Dataset was gathered from the national meteo-rological organization of Australia is the Australian Government Bureau of Meteorology, also known as the BOM. To monitor and forecast meteorological conditions, climatic trends, and natural calamities like cyclones, storms, floods, the Bureau of Meteorology is essential. The dataset includes 14, 5460 size, 23 features detailed city-specific monthly averages for Australia from 2008 to 2017(10 years). An effective rainfall forecasting was produced by integration of a number of Machine Learning and Deep Learning techniques, including Random Forest model (RF), Decision Tree (DT) and Gradient Boosting classifier (GBC), Artificial Neural Network (ANN), and Recurrent Neural Network (RNN). The models were trained to forecast rainfall, reducing the potential impact of floods. Results indicate that combining neural networks and Random Forests provides the most accurate predictions. © (2025), (Science and information Organization). All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization for Multi-Label Correlation-based Feature Selection Method 10

Ant Colony Optimization for Multi-Label Correlation-based Fe...

引用

10th International Conference on Digital Arts, Media and technology and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2025

作者： Jungjit, Suwimol Prasitsupparote, Amonrat Nathan, Shelena Soosay Rattanakietkhajorn, Thanawit Thaksin University Faculty of Science and Digital Innovation Phatthalung Thailand Prince of Songkla University College of Computing Phuket Thailand Universiti Tun Hussein Onn Center for Diploma Studies Dept of Information Technology Johor Malaysia Suratthani Rajabhat University Faculty of Science and Technology Suratthani Thailand

ISBN: (纸本)9798331543273

This paper proposes a new ant colony optimization for Multi-Label Correlation-Based Feature Selection (ACO-ML-CFS). This ACO performs a global search within the space of candidate features to identify an optimal subset. The selected feature subset is used by a Multi-Label k-Nearest Neighbors algorithm (ML-kNN), in this paper. The performance of ACO-ML-CFS is evaluated and compared with our previously works;Hill-Climbing algorithm for Multi-Label Correlation-Based Feature Selection (HC-ML-CFS) and Genetic algorithm for Multi-Label Correlation-Based Feature Selection (GA-ML-CFS) across four benchmark multi-label datasets. © 2025 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Barber Optimization Algorithm:A New Human-Based Approach for Solving Optimization Problems

引用

Computers, Materials & Continua 2025年第5期83卷 2677-2718页

作者： Tareq Hamadneh Belal Batiha Omar Alsayyed Widi Aribowo Zeinab Montazeri Mohammad Dehghani Frank Werner Haider Ali Riyadh Kareem Jawad Ibraheem Kasim Ibraheem Kei Eguchi Department of Mathematics Al Zaytoonah University of JordanAmman11733Jordan Department of Mathematics Faculty of Science and Information TechnologyJadara UniversityIrbid21110Jordan Department of Mathematics Faculty of ScienceThe Hashemite UniversityP.O.Box 330127Zarqa13133Jordan Department of Electrical Engineering Faculty of Vocational StudiesUniversitas Negeri SurabayaSurabaya60231Indonesia Department of Electrical and Electronics Engineering Shiraz University of TechnologyShiraz***Iran Faculty of Mathematics Otto-von-Guericke UniversityP.O.Box 4120Magdeburg39016Germany Department of Cybersecurity and Cloud computing Technical EngineeringUruk UniversityBaghdad10001Iraq Department of Medical Instrumentations Techniques Engineering Al-Rasheed University CollegeBaghdad10001Iraq Department of Electrical Engineering College of EngineeringUniversity of BaghdadBaghdad10001Iraq Department of Information Electronics Fukuoka Institute of TechnologyFukuoka8110295Japan

In this study,a completely different approach to optimization is introduced through the development of a novel metaheuristic algorithm called the Barber Optimization Algorithm(BaOA).Inspired by the human interactions between barbers and customers,BaOA captures two key processes:the customer’s selection of a hairstyle and the detailed refinement during the *** processes are translated into a mathematical framework that forms the foundation of BaOA,consisting of two critical phases:exploration,representing the creative selection process,and exploitation,which focuses on refining details for *** performance of BaOA is evaluated using 52 standard benchmark functions,including unimodal,high-dimensional multimodal,fixed-dimensional multimodal,and the Congress on Evolutionary Computation(CEC)2017 test *** comprehensive assessment highlights BaOA’s ability to balance exploration and exploitation effectively,resulting in high-quality solutions.A comparative analysis against twelve widely known metaheuristic algorithms further demonstrates BaOA’s superior performance,as it consistently delivers better results across most benchmark *** validate its real-world applicability,BaOA is tested on four engineering design problems,illustrating its capability to address practical challenges with remarkable *** results confirm BaOA’s versatility and reliability as an optimization *** study not only introduces an innovative algorithm but also establishes its effectiveness in solving complex problems,providing a foundation for future research and applications in diverse scientific and engineering domains.

关键词： Optimization metaheuristic barber hairstyle human-based algorithm exploration exploitation

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Text Classification Algorithms for Dhivehi Language Documents

Performance Analysis of Text Classification Algorithms for D...

引用

Advanced Research in computing (ICARC), International Conference on

作者： Fathimath Rashma Mohamed Prasanna S. Haddela Mohamed Jamaaludhin School Maldives Faculty of Computing Sri Lanka Institute of Information Technology Sri Lanka

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

This study examines the effectiveness of various machine learning algorithms in classifying text written in “Dhivehi,” the official language of the Maldives. As a low-resource language with limited research in text analytics, “Dhivehi” poses unique challenges due to its distinctive linguistic properties. To address these challenges, this research evaluates the performance of algorithms, including Support Vector Machines, Naive Bayes, Decision Trees, Neural Networks, XGBoost, and Random Forest, leveraging a newly curated “Dhivehi” language dataset. The evaluation highlights that K-Neighbors achieved the highest performance, with an accuracy of 64.7% and F1 scores (macro: 0.640, weighted: 0.642), demonstrating a strong balance between precision and recall. Support Vector Machines (accuracy: 63.9%) and XGBoost (accuracy: 62.8%) also showed competitive results, with SVM slightly outperforming XGBoost in F1 metrics. Decision Tree exhibited the lowest performance across all metrics. The findings provide critical insights into improving text classification for low-resource languages and contribute to developing natural language processing tools adapted explicitly for “Dhivehi.” Furthermore, the dataset is publicly available on Mendeley data under the name “Dhivehi Categories data set” to foster future research and innovation in this domain.

关键词： Support vector machines Measurement Accuracy Computational modeling Text categorization Neural networks Nearest neighbor methods Bayes methods Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Forecasting Prices of Strategic Food Products: Time Series Models in the Context of Post-Crisis Market Disruption

Forecasting Prices of Strategic Food Products: Time Series M...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Ahmed Harbaoui Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

In a post-crisis context, anticipating variations in raw material prices is essential for smart cities. At the beginning of this decade, two major global crises disrupted various market sectors: the COVID-19 pandemic and the Russian-Ukrainian war. Wheat is an essential product that contributes to food security in many countries. The price of this cereal fluctuated considerably during the two crises. Russia and Ukraine account for up to 28% of the wheat export market. Today, the wheat market seems to be gradually stabilizing from these disturbances. This paper explores reliable forecasting models to estimate wheat prices and support decision-making in the post-crisis period. To this end, two time-series forecasting techniques are compared: the Autoregressive Integrated Moving Average Model (ARIMA), known for its reliability in financial forecasting, and the Long Short-Term Memory Network (LSTM). The results reveal that the LSTM model achieves an accuracy of 97.49%, outperforming the ARIMA model, which registers an accuracy of 77%. These results underline the effectiveness of deep learning models for forecasting during periods of high price volatility, compared with conventional models.

关键词： Technological innovation Accuracy Smart cities Time series analysis Predictive models Registers Reliability Forecasting Long short term memory Context modeling

来源：评论

学校读者我要写书评

暂无评论

S3GAAR: Segmented Spatiotemporal Skeleton Graph-Attention for Action Recognition

引用

IEEE Transactions on Multimedia 2025年

作者： Ghaseb, Musrea Abdo Elhayek, Ahmed Alsolami, Fawaz Ali, Abdullah Marish King Abdulaziz University Faculty of Computing and Information Technology Jeddah Saudi Arabia University of Prince Mugrin Faculty of Computer and Cyber Sciences Madinah Saudi Arabia

Human motion recognition is extremely important for many practical applications in several disciplines, such as surveillance, medicine, sports, gait analysis, and computer graphics. Graph convolutional networks (GCNs) enhance the accuracy and performance of skeleton-based action recognition. However, this approach has difficulties in modeling long-term temporal dependencies. In Addition, the fixed topology of the skeleton graph is not sufficiently robust to extract features for skeleton motions. Although transformers that rely entirely on self-attention have demonstrated great success in modeling global correlations between inputs and outputs, they ignore the local correlations between joints. In this study, we propose a novel segmented spatiotemporal skeleton graph-attention network (S3GAAR) to effectively learn different human actions and concentrate on the most operative part of the human body for each action. The proposed S3GAAR models spatial-temporal features through spatiotemporal attention for each segment to capture short-term temporal dependencies. Owing to several human actions that focus on one or more body parts such as mutual actions, our novel method divides the human skeleton into three segments: superior, inferior, and extremity joints. Our proposed method is designed to extract the features of each segment individually because human actions focus on one or more segments. Moreover, our segmented spatiotemporal graph introduces additional edges between important distant joints in the same segment. The experimental results show that our novel method outperforms state-of-the-art methods up to 1.1% on two large-scale benchmark datasets, NTU-RGB+D 60 and NTU-RGB+D 120. © 1999-2012 IEEE.

关键词： Sports medicine

来源：评论

学校读者我要写书评

暂无评论

Harnessing Social Robotics and the Internet of Things to Reduce the Risk of Older Adults Developing Hypothermia and Dehydration 25th

Harnessing Social Robotics and the Internet of Things to Red...

引用

25th International Conference on Internet computing and IoT, ICOMP 2024, and 22nd International Conference on Embedded Systems, Cyber-physical Systems, and Applications, ESCS 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied computing, CSCE 2024

作者： Sindi, Hani McCrindle, Rachel Biomedical Engineering University of Reading Reading United Kingdom Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9783031859229

Many older adults are at risk of developing hypothermia or becoming dehydrated, both of which can be dangerous conditions requiring hospitalization. This paper describes the development and evaluation of a novel support system, Hypothermia and Dehydration Advising Companion (HyDeAdCo), that integrates a social robot with off-the-shelf technologies within an IoT infrastructure, to help reduce the risk of older adults becoming hypothermic or dehydrated. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

MOUSSE: A Multimodality-Oriented Unified Semantic Communication System by Contrastive Learning

MOUSSE: A Multimodality-Oriented Unified Semantic Communicat...

引用

IEEE Conference on Wireless Communications and Networking

作者： Tao Zhang Feng Wu Zhiyi Tian Chenhan Zhang Shui Yu Faculty of Engineering and Information Technology University of Technology Sydney Ultimo Australia School of Computing Macquarie University Macquarie Park Australia

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The sixth generation (6G) communication posed higher requirements for the communication system regarding accurate semantic transmission. The existing studies about semantic communication principally concentrate on tackling task-oriented problems, rather than directly design modality-oriented system which is more generic and adaptive to different tasks. To improve the flexibility and robustness of communication system, we propose a Multimodality-Oriented Unified Semantic Communication SystEm (MOUSSE) based on contrastive learning. MOUSSE is designed to firstly orient modality then matches different modalities combination up to various tasks. Existing task-oriented philosophy primarily considers tasks whilst restricting modal versatility. MOUSSE could also intake and output various tasks with multiple modalities while transmit them in a concise and unified representation. Specifically, the system consists of structure-symmetric twin encoder-decoder for modality unification, which cascades joint source-channel coding (JSCC) module and contrastive learning based alignment module. Finally, the experiments verify the validity of proposed MOUSSE by quantitative results from different modalities with their respective tasks. The reliability and robustness are also improved from the point of entire communication system view.

关键词： Deep learning 6G mobile communication Philosophical considerations Adaptive systems Accuracy Contrastive learning Semantic communication Multitasking Robustness Encoding

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：