检索结果-内蒙古大学图书馆

1st Arabic Natural Language Processing Conference, ArabicNLP 2023

作者： Almarwani, Nada Aloufi, Samah Dep. of Computer Science College of Computer Science and Engineering Taibah University Saudi Arabia

ISBN: (纸本)9781959429272

Our system, submitted to the Nuanced Arabic Dialect Identification (NADI-23), tackles the first sub-task: Closed Country-level dialect identification. In this work, we propose a model that is based on an ensemble of layer-wise fine-tuned BERT-based models. The proposed model ranked fourth out of sixteen submissions, with an F1-macro score of 85.43. © 2023 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Milk Quality Grades Using the Logistic Model Tree Algorithm

Comparison of Milk Quality Grades Using the Logistic Model T...

引用

2025 IEEE International Conference on Cybernetics and Innovations, ICCI 2025

作者： Suaprae, Phanintorn Janchidfah, Thanakrit Bhatt, Brijesh Phibulsongkram Rajabhat University Dep. Of Business Information Technology Management Phitsanulok65000 Thailand Muban Chombueng Rajabhat University Dep. Of Digital Media Technology Ratchaburi70150 Thailand Dharmsinh Desai University Faculty of Technology Dep. Of Computer Engineering 387001 India

ISBN: (纸本)9798331533267

This study aims to track and categorize milk quality grades using the Logistic Model Tree (LMT) algorithm, based on the analysis of 1,059 milk samples. The focus of the research is to evaluate key factors such as pH value, taste, smell, fat content, concentration, and color, which play a crucial role in determining the overall quality of milk. The goal is to create an efficient and standardized process for sorting cow's milk, which can save significant time and resources in the dairy industry. To identify the most suitable algorithm for this task, the research team initially tested 12 different algorithms, assessing their performance in predicting milk quality. Among these, the Logistic Model Tree (LMT) emerged as the most effective model, achieving an impressive accuracy rate of 99.76%. The LMT algorithm, known for combining the advantages of decision trees and logistic regression, demonstrated its ability to classify milk quality grades with high precision. The results of this study indicate that the LMT algorithm can be a valuable tool for automating the milk quality grading process. By leveraging key attributes such as pH, fat content, and color, it is possible to efficiently sort and grade milk, reducing the need for manual inspection and improving overall productivity in the dairy industry. This method offers a significant improvement over traditional quality assessment techniques and has the potential to be widely adopted for milk sorting and quality control applications. © 2025 IEEE.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Robust Spoofing Detection: A Chi-Square-based Machine Learning Approach 2

Feature Selection for Robust Spoofing Detection: A Chi-Squar...

引用

2nd International Engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Al-Na'amneh, Qais Aljaidi, Mohammad Gharaibeh, Hasan Nasayreh, Ahmad Emhamed Al Mamlook, Rabia Almatarneh, Sattam Alzu'bi, Dalia Suliman Husien, Abla Applied Science Private University Dep. of Cyber Security Amman Jordan Zarqa University Dep. of Computer Science Zarqa Jordan Yarmouk University Dep. Computer Science Irbid Jordan Trine University Dep. of Business Administration Indiana United States University of Zawia Department of Industrial Engineering Tripoli Libya Zarqa University Dep. of Data Science and Artificial Intelligence Zarqa Jordan Concordia University Dep. Information and Systems Engineering Montreal Canada

ISBN: (纸本)9798350373363

Nowadays, the Internet of Things (IoT) system is vulnerable to spoofing attacks that can easily where attackers can easily pose as a legal entity of the network. A 'spoofing attack' refers to a type of cyber-attack when an attacker purposefully impersonates or masquerades as someone or something else to deceive the target or obtain unauthorized access to systems, information, or resources. In such attacks, the attacker alters their name, IP address, or other attributes to fool the victim into thinking they are engaging with a legitimate entity. Spoofing attacks can take place via a variety of channels, including, ARP and DNS spoofing. Therefore. Spoofing attacks can have serious consequences. We proposed a new approach based on three machine learning models LightGBM, Gradient Boost, and XGBoost to classify attacks on spoofing, we used Chi-square to select the best features to get the highest performance, and we demonstrated that the results using Chi-square achieved higher results than without Chi-square and improved the result with a rate three percent of accuracy. In terms of results, LightGBM outperformed other models by achieving 89%, 91 %, 87 %, and 89 % for accuracy, precision, recall, and f1-score, respectively. This shows the potential and efficiency of Chi-square to achieve the best performance by selecting the best features, thus providing a secure system and identifying cyber-attacks on systems. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Functional Local Mean K-Nearest Neighbor: introducing a novel metric for improved algorithm performance 6

Functional Local Mean K-Nearest Neighbor: introducing a nove...

引用

6th International Conference on Intelligent Systems and computer Vision, ISCV 2024

作者： Sabri, Mohammed Yahyaouy, Ali Balzanella, Antonio Verde, Rosanna Riffi, Jamal Tairi, Hamid Sidi Mohamed Ben Abdellah University Dep. of Computer Science Fez Morocco University of Campania Luigi Vanvitelli Dep. of Mathematics and Physics Caserta Italy

ISBN: (纸本)9798350350180

Classifying high-dimensional data is problematic due to the curse of dimensionality, which complicates the analysis and accuracy of classification models. This research introduces an innovative classification approach for functional data through a novel functional metric. This metric leverages both the original curves and their derivatives to ascertain the nearest neighbors for new queries. While the classical functional K-nearest neighbor (KNN) classifier is a straightforward and effective nonparametric method for pattern classification, its performance can be compromised by the neighborhood size k and the simplistic majority voting within k-neighborhoods, particularly in scenarios characterized by small sample sizes and the presence of outliers. To address these challenges, this study proposes a locality constrained based KNN, aimed at enhancing the classification efficacy of functional data. A novel K-nearest neighbor technique, utilizing neighborhood local mean, has been developed to improve classification accuracy and decrease dep.ndency on the neighborhood size parameter k. The performance of the proposed Functional Locality Mean KNN (FLMKNN) algorithm is rigorously evaluated against functional KNN methodology across various real functional datasets commonly referenced in scholarly research. Comprehensive experiments underscore the superior performance and robustness of our approach to classifying functional data. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method 41

Gradual Divergence for Seamless Adaptation: A Novel Domain I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Jeeveswaran, Kishaan Arani, Elahe Zonooz, Bahram Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands Wayve Technologies Ltd London United Kingdom

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which refers to the phenomenon of learned representations undergoing changes as the model adapts to new tasks, can help alleviate catastrophic forgetting. In this study, we propose a novel DIL method named DARE, featuring a three-stage training process: Divergence, Adaptation, and REfinement. This process gradually adapts the representations associated with new tasks into the feature space spanned by samples from previous tasks, simultaneously integrating task-specific decision boundaries. Additionally, we introduce a novel strategy for buffer sampling and demonstrate the effectiveness of our proposed method, combined with this sampling strategy, in reducing representation drift within the feature encoder. This contribution effectively alleviates catastrophic forgetting across multiple DIL benchmarks. Furthermore, our approach prevents sudden representation drift at task boundaries, resulting in a well-calibrated DIL model that maintains the performance on previous tasks. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

BEYOND UNIMODAL LEARNING: THE IMPORTANCE OF INTEGRATING MULTIPLE MODALITIES FOR LIFELONG LEARNING 3

BEYOND UNIMODAL LEARNING: THE IMPORTANCE OF INTEGRATING MULT...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Sarfraz, Fahad Zonooz, Bahram Arani, Elahe Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands Wayve Technologies Ltd London United Kingdom

While humans excel at continual learning (CL), deep neural networks (DNNs) exhibit catastrophic forgetting. A salient feature of the brain that allows effective CL is that it utilizes multiple modalities for learning and inference, which is underexplored in DNNs. Therefore, we study the role and interactions of multiple modalities in mitigating forgetting and introduce a benchmark for multimodal continual learning. Our findings demonstrate that leveraging multiple views and complementary information from multiple modalities enables the model to learn more accurate and robust representations. This makes the model less vulnerable to modality-specific regularities and considerably mitigates forgetting. Furthermore, we observe that individual modalities exhibit varying degrees of robustness to distribution shift. Finally, we propose a method for integrating and aligning the information from different modalities by utilizing the relational structural similarities between the data points in each modality. Our method sets a strong baseline that enables both single- and multimodal inference. Our study provides a promising case for further exploring the role of multiple modalities in enabling CL and provides a standard benchmark for future research.1 © 2024 CoLLAs. All Rights Reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Properties of Large 2-Crossing-Critical Graphs

引用

Journal of Graph Algorithms and Applications 2022年第1期26卷 111-147页

作者： Bokal, Drago Chimani, Markus Nover, Alexander Schierbaum, Jöran Stolzmann, Tobias Wagner, Mirko H. Wiedera, Tilo Dep. of Mathematics and Computer Science University of Maribor Slovenia Theoretical Computer Science Osnabrück University Germany

A c-crossing-critical graph is one that has crossing number at least c but each of its proper subgraphs has crossing number less than c. Recently, a set of explicit construction rules was identified by Bokal, Oporowski, Richter, and Salazar to generate all large 2-crossing-critical graphs (i.e., all apart from a finite set of small sporadic graphs). They share the property of containing a generalized Wagner graph V10 as a subdivision. In this paper, we study these graphs and establish their order, simple crossing num-ber, edge cover number, clique number, maximum degree, chromatic number, chromatic index, and treewidth. We also show that the graphs are linear-time recognizable and that all our proofs lead to efficient algorithms for the above measures. © 2022, Brown University. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

AI-driven Risk Assessment and Decision-making in Healthcare Applications Using Machine Learning: A Case Study on Customer Twitter Feeds 2

AI-driven Risk Assessment and Decision-making in Healthcare ...

引用

2nd International Conference on Computational Intelligence and Network Systems, CINS 2024

作者： Darwiesh, Abdelaziz Elhoseny, Mohamed El-Baz, A.H. Atassi, Reem Mathematics Dep. Faculty of Science Damietta University New Damietta Egypt Information Systems Dep. Faculty of Computing and Info University of Sharjah Sharjah United Arab Emirates Computer Science Dep. Faculty of Computers and Artificial Intelligence Damietta University New Damietta Egypt Higher Colleges of Technology Dubai United Arab Emirates

ISBN: (纸本)9798331504106

This study presents an AI-driven strategy for enhancing decision-making in healthcare applications by assessing and managing potential risks through the analysis of customer interactions on social media platforms, specifically Twitter. We propose the use of machine learning models to outperform traditional lexical approaches, addressing the complexities inherent in risk detection. Natural language processing methods are employed to efficiently process and analyze textual data, enabling healthcare institutions to make informed decisions about risk management. By leveraging customer feedback from the X platform, our approach aids in the development of effective healthcare programs by identifying and classifying risks. We create three specialized datasets for risk analysis, risk assessment, and hazard classification to optimize the training and dep.oyment phases. In our case study, which focuses on tweets related to healthcare for US consumers, we find that over 50% of the sample identifies potential risks, with nearly 80% indicating medium levels of risk. Commonly identified risks include financial, operational, and strategic threats. The proposed methodology demonstrates an average accuracy of 82.66% in risk detection, identification, and assessment, confirming its effectiveness in supporting AI-driven decision-making in healthcare application development. ©2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Structural Reliability and Optimization Using Differential Geometric Approaches

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2024年第1期5卷 168-174页

作者： Abed, Saad Abbas Ghassan, Mona Qaes, Shaemaa Fiadh, Mahmood S. Mohammed, Zaid Amer Al -Iraqia University College of Education Computer Science Dep. Baghdad10053 Iraq Al -Iraqia University Economic and Administration College Baghdad10071 Iraq

This study investigates how differential geometry ideas can be used to effectively carry out structural optimization and reliability analysis. Strong mathematical representations and methods for examining intricate surfaces and forms are provided by differential geometry. The basic ideas of differential geometry, such as tensors, manifolds, and curvature, are initially introduced in the work. Then, to account for ambiguities in the geometry, the probability theory in tangent spaces is developed. As a result, structural reliability can be determined using propagating uncertainty. To enable reliability-based design optimization, differential geometry representations are linked with optimization techniques. The proposed differential geometry-based approach is applied in a number of case studies to trusses, airplane wings, car bodies, and ship hulls. The outcomes show a significant increase in productivity and scalability compared to conventional finite element methods. The article offers new tools for dealing with uncertainty. © 2024 College of Education, Al-Iraqia University. All rights reserved.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ML Algorithms for Fraud Detection 4

Comparative Analysis of ML Algorithms for Fraud Detection

引用

4th IEEE International Conference on Smart information Systems and Technologies, SIST 2024

作者： Abitova, Gulnara Abalkanov, Miras Dep. of Eletrical Engineering and Computer Science Dep. of Computer Engineering State University of New York Astana IT University BinghamtonNY United States Astana Kazakhstan Department of Computer Engineeering Astana IT University Astana Kazakhstan

ISBN: (纸本)9798350374865

The challenge of credit card fraud presents a significant threat to both consumers and financial institutions alike, leading to substantial economic detriment. In response, this research applies various machine learning strategies to sift through transactional data for the identification of fraudulent activities. Specifically, we employ logistic regression, decision trees, and random forest algorithms to analyze a compiled dataset of genuine and deceptive transactions. This dataset undergoes segmentation into training and testing phases, allowing for a comprehensive assessment of each algorithm's effectiveness. The determination of accuracy scores across these phases serves as a metric for model evaluation. The findings lay down an essential groundwork for ongoing exploration into leveraging machine learning for the mitigation of credit card fraud. The integration of these analytical models promises to bolster the fraud detection capabilities of both financial entities and individual cardholders, significantly reducing the incidence of financial loss. © 2024 IEEE.

关键词： Logistic regression

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：