检索结果-内蒙古大学图书馆

16th International Conference on Knowledge engineering and Ontology Development, KEOD 2024 as part of 16th International Joint Conference on Knowledge Discovery, Knowledge engineering and Knowledge Management, IC3K 2024

作者： Ondo, Anicet Lepetit Capus, Laurence Bousso, Mamadou Dep. of Computer and Software Engineering Laval University QuebecQCG1V 0A6 Canada Dep. Computer Science Iba Der Thiam University Thies967 Senegal

ISBN: (纸本)9789897587160

A well-designed ontology must be capable of addressing all the needs it is intended to satisfy. This complex task involves gathering all the potential questions from future users that the ontology should answer in order to respond precisely to these requests. However, variations in the questions asked by users for the same need complicate the interrogation process. Consequently, the use of a question-answering system seems to be a more efficient option for translating user queries into the formal SPARQL language. Current methods face significant challenges, including their reliance on predefined patterns, the quality of models and training data, ontology structure, resource complexity for approaches integrating various techniques, and their sensitivity to linguistic variations for the same user need. To overcome these limitations, we propose an optimal classification approach to classify user queries into corresponding SPARQL query classes. This method uses a neural network based on Transformer encoder-decoder architectures, improving both the understanding and generation of SPARQL queries while better adapting to variations in user queries. We have developed a dataset on estate liquidation and Python programming, built from raw data collected from specialist forums and websites. Two transformer models, GPT-2 and T5, were evaluated, with the basic T5 model obtaining a satisfactory score of 97.22%. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A SENSITIVITY ANALYSIS ON THE EFFECT OF HYPERPARAMETERS IN DEEP NEURAL OPERATORS APPLIED TO SOUND PROPAGATION 10

A SENSITIVITY ANALYSIS ON THE EFFECT OF HYPERPARAMETERS IN D...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Borrel-Jensen, Nikolas Engsig-Karup, Allan P. Jeong, Cheol-Ho Technical University of Denmark Dep. of Electrical and Photonics Engineering Denmark Technical University of Denmark Dep. of Applied Mathematics and Computer Science Denmark

ISBN: (纸本)9788888942674

Deep neural operators have seen much attention in the scientific machine learning community over the last couple of years due to their capability of efficiently learning the nonlinear operators mapping from input function spaces to output function spaces showing good generalization properties. This work will show how to set up a per-formant DeepONet architecture in acoustics for predicting 2-D sound fields with parameterized moving sources for real-time applications. A sensitivity analysis is carried out with a focus on the choice of network architectures, activation functions, Fourier feature expansions, and data fidelity to gain insight into how to tune these models. Specifically, a default feed-forward neural network (FNN), a modified FNN, and a convolutional neural network will be compared. This work will de-mystify the DeepONet and provide helpful knowledge from an acoustical point of view. © 2023 Nikolas Borrel-Jensen et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Extraction Framework Based on DNN for Enhancing Mirai Attachment Classification in Machine Learning 2

Deep Feature Extraction Framework Based on DNN for Enhancing...

引用

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

作者： Gharaibeh, Hasan Aljaidi, Mohammad Nasayreh, Ahmad Al-Na'amneh, Qais Jaradat, Ameera S. Samara, Ghassan Emhamed Al Mamlook, Rabia Yarmouk University Dep. Computer Science Irbid Jordan Zarqa University Dep. of Computer Science Zarqa Jordan Applied Science Private University Dep. of Cyber Security Amman Jordan Dep. of Business Administration Trine University IN United States Department of Mechanical and Industrial Engineering University of Zawia Tripoli Libya

ISBN: (纸本)9798350373363

Nowadays, the rapid growth of Internet of Things (IoT) devices has changed many parts of our lives by providing seamless connectivity and automation. However, this expansion has created new challenges and vulnerabilities, especially with regard to security. Mirai botnet, a strain of malware that has severely damaged the IoT ecosystem, is one of the prominent risks to IoT security. This research examines the impact of the Mirai botnet on IoT devices. In this study, we present a hybrid model to detect Mirai attacks. Deep neural networks (DNNs) are used to extract significant deep features, which are subsequently passed to the (Light Gradient Boosting Machine) LGBM algorithm for classification. A dataset from the Canadian Institute 2023 that included several kinds of Internet of Things assaults was used to assess the model. The model achieved excellent feature extraction and promising results with accuracy, recall, precision, and F1-score scoring up to 95 % for all. These accuracy results demonstrated the superior performance of the suggested model over competing techniques, which had scores of 71 %, 85%, and 52%, respectively, for Support Vector Machine (SVM), Light Gradient Boosting Machine (LGBM), and Stochastic Gradient Descent (SGD). Furthermore, the model outperforms the DNN model, which received a score of 65%. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Pre-Trained Models for Automated Analysis of Ophthalmic Imaging in Diagnosing Eye Diseases 24

Fine-Tuning Pre-Trained Models for Automated Analysis of Oph...

引用

24th International Arab Conference on information Technology, ACIT 2023

作者： Al Mamlook, Rabia Emhamed Nasayreh, Ahmad Gharaibeh, Hasan Aljaidi, Mohammad Al-Na'amneh, Qais Alzu'bi, Dalia Bzizi, Hanin Abdeltawab, Abdelrahman Trine University Dep. of Business Administration Indiana United States University Zawia Department of Industrial Engineering Tripoli Libya Yarmouk University Dep. Computer Science Irbid Jordan Zarqa University Dep. of Computer Science Zarqa Jordan Applied Science Private University Dep. of Cyber Security Amman Jordan Concordia University Dep. Information and Systems Engineering Montreal Canada Western Michigan University Dep of Biomedical Science KalamazooMI49008 United States Bani Sweif University Faculty of Pharmacy Bani Suwayf Egypt

ISBN: (纸本)9798350384307

This paper searches into the convergence of such ad-vanced techniques with architectures like DenseNet201, VGG16, InceptionResNetV2, and NasNetMobile. Our focus centers on harnessing deep learning capabilities for the precise detection of eye ailments. Preliminary findings spotlight a notable uplift in diagnostic precision. Among the tested algorithms, the Nas-NetMobile architecture emerged superior, boasting an impressive accuracy rate of 92% on the chosen dataset. Through this work, we extend a significant advancement in the realm of automated eye disease diagnosis, potentially equipping medical professionals with sharper, swifter diagnostic tools. The outcomes presented herein could play a seminal role in sculpting more sophisticated and precise diagnostic approaches within ophthalmology. © 2023 IEEE.

关键词： Deep Learning Eye Disease Fine Tuning Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Genetic Optimization Techniques for Enhancing Web Attacks Classification in Machine Learning

Genetic Optimization Techniques for Enhancing Web Attacks Cl...

引用

2023 IEEE International Conference on dep.ndable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Jaradat, Ameera S. Nasayreh, Ahmad Al-Na'amneh, Qais Gharaibeh, Hasan Al Mamlook, Rabia Emhamed Yarmouk University Dep. of Computer Science Irbid Jordan Yarmouk University Dep. of Computer Science Irbid211633 Jordan Applied Science Private University Dep. of Cyber Security and Cloud Computing Amman Jordan Trine University Dep. of Business Administration IN United States University Zawia Department of Industrial Engineering Tripoli Libya

ISBN: (纸本)9798350304602

Web-based applications are now the preferred approach for delivering a variety of services via the Internet. As a result of the globalization of commerce, web applications have been growing quickly and becoming increasingly complicated. Such applications have a significant security vulnerability in the online environment since they were developed with little experience and without testing or validation. Numerous attackers use this security vulnerability to take control of the program, modify the data, and steal the most crucial information. They may also access all internal, unauthorized items. This work presents a hybrid model that classifies website attacks as benign through the integration of four machine learning algorithms: gradient boost (GB), multilayer perceptron (MLP), logistic regression (LR) and K nearest neighbor (KNN). The work dep.oyed Tree-based Pipeline Optimization Tool (TPOT) that utilizes the Genetic algorithm (GA) to extract the optimal parameter and consequently enhance the model performance. The model underwent evaluation utilizing a data set from the Canadian Institute 2023 that contains various types of attacks. Among these algorithms, GB achieved the best accuracy scores of 95%, 94% and 95% for accuracy, recall and F1-score, respectively. © 2023 IEEE.

关键词： Genetic algorithms

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

Detecting 5G Signal Jammers Using Spectrograms with Supervised and Unsupervised Learning

arXiv

引用

arXiv 2024年

作者： Varotto, Matteo Valentin, Stefan Tomasin, Stefano Dep. of Computer Science Darmstadt University of Applied Sciences Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Italy

Cellular networks are potential targets of jamming attacks to disrupt wireless communications. Since the fifth generation (5G) of cellular networks enables mission-critical applications, such as autonomous driving or smart manufacturing, the resulting malfunctions can cause serious damage. This paper proposes to detect broadband jammers by an online classification of spectrograms. These spectrograms are computed from a stream of in-phase and quadrature (IQ) samples of 5G radio signals. We obtain these signals experimentally and describe how to design a suitable dataset for training. Based on this data, we compare two classification methods: a supervised learning model built on a basic convolutional neural network (CNN) and an unsupervised learning model based on a convolutional autoencoder (CAE). After comparing the structure of these models, their performance is assessed in terms of accuracy and computational complexity. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of Injected Mobility Data on Measuring Data Coverage in CrowdSensing Scenarios

Evaluating the Impact of Injected Mobility Data on Measuring...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Kocian, Alexander Girolami, Michele Capoccia, Stefano Foschini, Luca Chessa, Stefano University of Bologna Department of Computer Science and Engineering Bologna Italy ISTI-CNR Italian National Council of Research Pisa Italy University of Pisa Dep. of Computer Science Italy

ISBN: (纸本)9798350351255

A major weakness of Mobile CrowdSensing Platforms (MCS) is the willingness of users to participate, as this implies disclosing their private data (for example, concerning mobility) to the MCS platform. In the effort to enforce data privacy in the creation of mobility coverage maps using an MCS platform, recent work proposes the use of a spatially distributed approach that, however, is vulnerable to data injection attacks. In this contribution, we define and implement a progressive attacker model following a statistical approach. We propose a novel mitigation strategy based on unsupervised anomaly detection. Accessing the coverage performance with real-world mobility data indicates that the mean value of the attacker's profile determines the probability of being revealed. In particular, we are able to identify the attacker and filter out the data injected by the attackers with high precision. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers Using Spectrograms with Supervised and Unsupervised Learning

Detecting 5G Signal Jammers Using Spectrograms with Supervis...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Matteo Varotto Stefan Valentin Stefano Tomasin Dep. of Computer Science Darmstadt University of Applied Sciences Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Italy

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

关键词： Wireless communication 5G mobile communication Computational modeling Data models Convolutional neural networks Synchronization Jamming

来源：评论

学校读者我要写书评

暂无评论

The Influence of Applying Digital Toolkits to Assist 3D Software Development on Individual Work Performance and Perceived Stress 10

The Influence of Applying Digital Toolkits to Assist 3D Soft...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Wu, Wen-Chuan Lee, Ming-Han National Ilan University Dep. of Computer Science and Information Engineering Yilan City Taiwan National Ilan University Master Program of E-Learning for Multimedia and Network Communications Yilan City Taiwan

ISBN: (纸本)9798350394924

Digital content industry, encompassing areas such as digital games, computer animation, digital audio-visual applications, and digital art, plays a pivotal role in today's and future developmental trends. Maya 3D software stands out as a crucial development tool in these domains. However, the multitude of built-in tools in Maya 3D can lead to overly complex interfaces, impacting development efficiency for software developers. To address this issue, this paper designs a digital toolkit for Maya 3D software, presented in a Menu Bar format. This toolkit offers features like naming, sorting, categorization, and automatic saving to JSON files for future use. Through a crossover experimental design, this paper investigates the impact of this proposed toolkit on 3D software developers' individual work performance, work engagement, and stress perception. Results shows a significant positive influence of that toolkit on software developers, particularly in enhancing work performance. It means that the proposed digital toolkit effectively improves the performance of software developers' work and reduces their stress during the software development process. © 2024 IEEE.

关键词： Digital devices

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：