检索结果-内蒙古大学图书馆

computer Science (COMSCI), International Scientific Conference on

作者： Kiril Andreev Koparanov Elena Ventseslavova Antonova Ognyan Nakov Nakov Daniela Veleva Minkovska Krasin Krasimirov Georgiev Lyudmila Yordanova Stoyanova Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria Department of Computer Systems Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria Department of Air Transport Faculty of Transport Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria

Easy access to time series forecasting provides a strong competitive advantage for any company or organization. As automated forecasting environments become more prevalent in the market, it is crucial to explore their capabilities and features to utilize them competently. This study demonstrates the influence of data coverage on prediction accuracy and validates the initial assumption. Based on the findings, recommendations have been presented to enhance the quality of predictive processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Creating a Dynamic Online Learning Environment with AI Integration

Creating a Dynamic Online Learning Environment with AI Integ...

引用

International computer Sciences and Information Technologies (CSIT)

作者： Oleksandra Bulgakova Zarina Viniarska Viacheslav Zosimov P.M Platonov Educational and Scientific Institute of Computer Engineering Automation Robotics and Computer Programming Odesa National University of Technology Odesa Ukraine Department of Applied information systems Taras Shevchenko National University of Kyiv Kyiv Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

Educational, online learning has become a common practice due to rapid digitalization and recent global events. This study focuses on developing a comprehensive online learning platform that addresses users' needs by integrating advanced AI capabilities for personalized support and adaptive learning. The platform supports user registration and authentication, course and lesson management, and offers interactive features like AI-driven chat support. In this study, we show the importance of creating user-friendly online learning platforms with the implementation of modern AI trends. The development and testing of this platform is ongoing to determine the adaptation of the system to different learning styles.

关键词： Adaptive learning Electronic learning Authentication Passwords Market research Real-time systems Artificial intelligence Information technology Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Application of IoT in the study of biogas release parameters

Application of IoT in the study of biogas release parameters

引用

International Scientific Conference Electronics (ET)

作者： Neven K. Nikolov Anelia I. Tzanova Kiril A. Koparanov Elena V. Antonova Daniela V. Minkovska Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia Bulgaria Department of Chemistry Faculty of Electronic Engineering and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia Bulgaria

This paper describes the development of an IoT device prototype for measuring biogas release parameters. Through the device, measurements are made, and statistics are accumulated based on which calculations are perfor... 详细信息

ISBN: (数字)9798350376449

ISBN: (纸本)9798350376456

关键词： Performance evaluation Heating systems Prototypes Production Sensor phenomena and characterization Biogas Sensor systems Internet of Things Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

The Method of Dynamic Routing in Self-Healing Networks

The Method of Dynamic Routing in Self-Healing Networks

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Shyman Anna Nina Kuchuk Andriy Kovalenko Svitlana Kashkevich Stanislav Partyka Oleksandr Yankovskyi Department of Computer Engineering and Programming National Technical University “Kharkiv Polytechnic Institute” Kharkiv Ukraine Department of Electronic Computers Kharkiv National University of Radio Electronics Kharkiv Ukraine Department of Computerized Management Systems National Aviation University Kharkiv Ukraine

ISBN: (数字)9798350384499

ISBN: (纸本)9798350384505

The report proposes a dynamic routing method for Self-healing Networks (ShN). The method takes into account the specific features of ShN. During routing, the flow of service information is reduced. The search for the optimal route is carried out using a convolutional neural network. The method significantly outperforms existing methods when some network nodes fail.

关键词： Receivers Performance gain Routing Routing protocols Maintenance Convolutional neural networks Standards

来源：评论

学校读者我要写书评

暂无评论

IoT Cyberattack Detection Approach Based on Energy Consumption Analysis

IoT Cyberattack Detection Approach Based on Energy Consumpti...

引用

IEEE International Conference on Dependable systems, Services and Technologies (DESSERT)

作者： Kira Bobrovnikova Oleg Savenko Sergii Lysenko Ivan Hurman Department of Computer Engineering and Information Systems Khmelnitsky National University Khmelnitsky Ukraine Department of Computer Engineering and System Programming Khmelnitsky National University Khmelnitsky Ukraine

ISBN: (纸本)9798350333053

Today, the Internet of Things has been widely used and is becoming an increasingly vital part in various areas of human activity, which helps to effectively solve various real-life tasks and problems. The infrastructure of the Internet of Things includes a lot of heterogeneous devices with limited capacities, which makes it difficult to control them in order to detect cyberattacks. The increase in the number of attacks on the infrastructure of the Internet of Things indicates the relevance of developing new solutions for detecting attacks on the networks of the Internet of Things. One of the possible approaches to identify attacks is to analyze the physical parameters associated with IoT devices that describe the behavior of devices on the network, such as power consumption. Power analysis allows you to detect power-hungry attacks such as crypto mining and denial-of-service attacks. The paper proposes a new method for cyberattack detection in the infrastructure of the Internet of Things that is based on the analysis of energy consumption. In order to improve the accuracy of detecting cyberattacks, the approach also uses the analysis of the actions of the IoT software. The proposed approach makes it possible to detect attacks such as DoS/DDoS with high efficiency with a level of detection up to 99.95%.

关键词： Energy consumption Power demand Software Behavioral sciences Internet of Things Object recognition Data mining

来源：评论

学校读者我要写书评

暂无评论

Word-Based Turkish Lip Reading System with Two Stream 3dcnn and Bilstm

SSRN

引用

SSRN 2023年

作者： Erbey, Ali Barışçı, Necaattin Department of Computer Programming Distance Education Vocational School Usak University Usak64200 Turkey Department of Information Systems Informatics Institute Gazi University Ankara Turkey Department of Computer Engineering Faculty of Technology Gazi University Ankara06500 Turkey

Lip reading is a technique that aims to understand spoken words by analyzing people's lip movements. Deep learning algorithms are used as a powerful tool for detecting and recognizing lip movements more accurately. In this study, we present a lip-reading architecture for the Turkish language. The architecture is trained to recognize Turkish words using 3DCNN (3D Convolutional Neural Network) architecture and two-stream deep learning methods. The model was trained on video data representing lip movements and learned to classify words accurately. The Turkish lip reading system has been trained and tested on a large Turkish lip reading dataset. In the experiments, an accuracy of 87.12% was achieved with the proposed model, indicating successful results in the Turkish language. The proposed model demonstrates high accuracy rates in recognizing Turkish words, showcasing its effectiveness. This paper introduces a novel architecture, a lip-reading system that employs deep learning techniques, providing a robust tool for successful Turkish lipreading applications. © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Methods for Improving the Quality of Classification on Imbalanced Data

Methods for Improving the Quality of Classification on Imbal...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Svitlana Gavrylenko Zozulia Vladislav Nataliia Khatsko Department of Computer Engineering and Programming National Technical University “Kharkiv Polytechnic Institute” Kharkiv Ukraine Department of Information Systems and Technologies National Technical University «Kharkiv Polytechnic Institute» Kharkiv Ukraine

The subject of the study is methods of balancing raw data. The purpose of the article is to improve the quality of intrusion detection in computer networks by using class balancing methods. Task: to investigate methods of balancing classes and to develop a classification method on imbalanced data to increase the level of network security. The methods used are: methods of artificial intelligence, machine learning. The following results were obtained: Class balancing methods based on Undersampling, Oversampling and their combinations were studied. The following methods were chosen for further research: SMOTEENN, SVMSMOTE, BorderlineSMOTE, ADASYN, SMOTE, KMeansSMOTE. The UNSW-NB 15 set was used as the source data, which contains information about the normal functioning of the network and during intrusions. A decision tree based on the CART (Classification And Regression Tree) algorithm was used as the basic classifier. According to the research results, it was found that the use of the SMOTEENN method provides an opportunity to improve the quality of detection of intrusions in the functioning of the network. Conclusions. The scientific novelty of the obtained results lies in the complex use of data balancing methods and the method of data classification based on decision trees to detect intrusions into computer networks, which made it possible to reduce the number of Type II errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uvlhub: A Feature Model Data Repository Using Uvl and Open Science Principles

SSRN

引用

SSRN 2023年

作者： Romero-Organvidez, David Galindo, José A. Sundermann, Chico Horcas, Jose-Miguel Benavides, David Department of Computer Languages and Systems University of Seville Spain Institute of Software Engineering and Programming Languages Ulm University Germany CAOSD ITIS Software University of Málaga Spain

Feature models are the de facto standard for modelling variabilities and commonalities. Concrete models in different domains exist;however, many are in private or sparse repositories or belong to discontinued projects. The dispersion of knowledge of feature models hinders the study and reuse of these artefacts in different studies. The Universal Variability Language (UVL) is a community effort textual feature model language that promotes a common way of serialising feature models independently of concrete tools. Open science principles promote transparency, accessibility, and collaboration in scientific research. Although some attempts exist to promote feature model sharing, the existing solutions lack open science principles by design. In addition, existing and public feature models are described using formats not always supported by current tools. This paper presents UVLHUB, a repository of feature models in UVL format. UVLHUB provides a front end that facilitates the search, upload, storage, and management of feature model datasets, improving the capabilities of discontinued proposals. Furthermore, the tool communicates with Zenodo providing a permanent save of datasets and following open science principles. UVLHUB includes existing datasets and is readily available to include new data and functionalities in the future. It is maintained by three active universities in variability modelling. © 2023, The Authors. All rights reserved.

关键词： Concretes

来源：评论

学校读者我要写书评

暂无评论

A lightweight attention-driven YOLOv5m model for improved brain tumor detection

引用

computers in Biology and Medicine 2025年 188卷 109893-109893页

作者： Muksimova, Shakhnoza Umirzakova, Sabina Mardieva, Sevara Iskhakova, Nargiza Sultanov, Murodjon Cho, Young Im Department of Computer Engineering Gachon University Sujeong-gu Seongnam-si461-701 Korea Republic of Department of Information Systems and Technologies of the Tashkent State University of Economic Tashkent100066 Uzbekistan Department of Systematic and Practical Programming Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi Tashkent100200 Uzbekistan

Brain tumors are regarded as one of the most lethal, devastating, and aggressive diseases, significantly reducing the life expectancy of affected individuals. For this reason, in pursuit of advancing brain tumor diagnostics, this study introduces a significant enhancement to the YOLOv5m model by integrating an Enhanced Spatial Attention (ESA) layer, tailored specifically for the analysis of magnetic resonance imaging (MRI) brain scans. Traditional brain tumor detection methods, heavily reliant on expert interpretation of MRI, are fraught with challenges such as high variability and the risk of human error. Our innovative approach leverages the ESA layer to acutely focus on salient features, significantly improving the method ability to differentiate between common classes of brain tumors—meningioma, pituitary, and glioma tumors. By processing spatial features with enhanced precision, the model minimizes false positives and maximizes detection reliability. Validated against a comprehensive dataset of 3064 T1-weighted contrast-enhanced MRI images from 233 patients, our modified YOLOv5m architecture demonstrates superior performance metrics compared to the standard model, highlighting its potential as a robust tool in clinical applications for automated and precise brain tumor diagnosis. © 2025 The Authors

关键词： Dynamic contrast enhanced MRI

来源：评论

学校读者我要写书评

暂无评论

Social Engineering Attacks Detection Approach

Social Engineering Attacks Detection Approach

引用

IEEE International Conference on Dependable systems, Services and Technologies (DESSERT)

作者： Sergii Lysenko Volodymyr Vorobiov Oleksandr Bokhonko Piotr Gaj Oleg Savenko Jacek Wołoszyn Department of Computer Engineering and Information Systems Khmelnitsky National University Khmelnitsky Ukraine Silesian University of Technology Gliwice Poland Department of Computer Engineering and System Programming Khmelnitsky National University Khmelnitsky Ukraine Department of Informatics and Teleinformatics Kazimierz Pulaski University of Technology and Humanities in Radom Radom Poland

The paper focuses on the problem of technical social engineering attacks that encompass the manipulation of individuals to reveal sensitive information, execute actions, or breach security systems. These exploits frequently capitalize on human psychology, trust, and a lack of vigilance to attain unauthorized entry to networks, systems, or data. In contrast to traditional social engineering tactics that center on psychological manipulation, technical social engineering attacks employ technological means and strategies to manipulate and beguile individuals. The paper presents an attempt to detect social engineering attacks. The approach utilized four machine learning algorithms (decision tree, random forest, K-nearest neighbor, and extreme gradient boosting). The analysis is centered on data collected from network hosts, which may serve as indicators of a potential social engineering attack. The empirical results demonstrated high detection accuracy.

关键词：

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：