检索结果-内蒙古大学图书馆

1st International workshop on AI for Research, AI4Research 2024 and 4th International workshop on Democracy and AI, DemocrAI 2024, held in conjunction with 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024

作者： Lee, Jungmin Shin, Huigon Yoo, YoungJoon Choi, Jongwon Kim, Mi Song Department of Advanced Imaging GSAIM Chung-Ang University Seoul Korea Republic of Computer Programming and Analysis School of Information Technology Fanshawe College London Canada Department of Artificial Intelligence Chung-Ang University Seoul Korea Republic of Curriculum Studies Western University London Canada

ISBN: (纸本)9789819795352

Multimodal learning analytics have become increasingly important in enabling a deeper understanding of teaching and learning in educational research. However, in comparison to other multimodal learning data, there is a limited understanding of the trends within gaze learning data. To address this challenge, this study aims to identify latent topics in gaze learning data through topic modeling and scientometric analysis. We analyzed the abstracts of 573 peer-reviewed and conference proceeding papers that used gaze learning data, written in English, and published between 2008 and February 2024. The findings are as follows. First, three main topics were identified through topic modeling analysis: (learning analytics, multimodal learning, and inclusive learning). Second, the scientometric analysis revealed the structure in which diverse clusters in cited references and institutions are connected around the emerging topics. Based on these findings, the study would provide insights into research directions in both educational research and applications using gaze learning data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Autonomously Reconfigurable Robot Coupled with Intelligent Vision and Control System for Rapid Runtime Adaptation

Autonomously Reconfigurable Robot Coupled with Intelligent V...

引用

AI IoT Congress (AIIoT), World

作者： Gvarami Labartkava Nurin Binti Suhaimi Thiago Silva Lev Kirischian Independent Researcher Toronto Canada Department of Computer Programming & Analysis Seneca Polytechnic Toronto Canada Department of Electrical and Computer Engineering Toronto Metropolitan University Toronto Canada

ISBN: (数字)9798350387803

ISBN: (纸本)9798350387810

The widespread integration of robotic technology across diverse sector’s necessitates solutions that embody both adaptability and speed. However, existing systems often exhibit a trade-off between these attributes, lacking swift adaptability. This paper introduces a novel self-reconfiguration system that addresses this challenge. Employing a scissor mechanism for rapid adjustment and an intelligent binocular vision driven by computer vision and reinforcement learning algorithms, the proposed system facilitates swift reconfiguration while effectively managing workload. Real-time perception and understanding of the surroundings enable the robot to promptly identify optimal dimensions and adjust its configuration accordingly. This capability empowers the robot to rapidly respond to new tasks without manual intervention, thereby augmenting its versatility and agility. Experimental validation demonstrates the system’s adeptness in navigating passages of varying widths in under a second, underscoring the efficacy of our approach in training the robot to adeptly adapt to diverse environmental conditions.

关键词： Training Runtime Navigation Machine vision Reinforcement learning Manuals Control systems

来源：评论

学校读者我要写书评

暂无评论

Social Engineering Attacks Detection Approach 13

Social Engineering Attacks Detection Approach

引用

13th International Conference on Dependable Systems, Services and Technologies, DESSERT 2023

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

ISBN: (纸本)9798350396119

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. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Input Data Time Range Impact on Forecast Quality Using Automated Procedures 11

Input Data Time Range Impact on Forecast Quality Using Autom...

引用

11th International Scientific Conference on computer Science, COMSCI 2023

作者： Koparanov, Kiril Andreev Antonova, Elena Ventseslavova Nakov, Ognyan Nakov Minkovska, Daniela Veleva Georgiev, Krasin Krasimirov Stoyanova, Lyudmila Yordanova Technical University of Sofia Faculty of Computer Systems and Technologies Department of Programming and Computer Technologies 8 Kliment Ohridski blvd Sofia1000 Bulgaria Technical University of Sofia Faculty of Computer Systems and Technologies Department of Computer Systems 8 Kliment Ohridski blvd Sofia1000 Bulgaria Technical University of Sofia Faculty of Transport Department of Air Transport 8 Kliment Ohridski blvd Sofia1000 Bulgaria

ISBN: (纸本)9798350325256

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. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Spam Detection With Fasttext Based Features

Spam Detection With Fasttext Based Features

引用

Innovations in Intelligent Systems and Applications Conference

作者： Talha Karadeniz Gül Tokdemir H. Hakan Maraş Department of Software Engineering Çankaya University Ankara Turkey Department of Computer Engineering Çankaya University Ankara Turkey Department of Computer Programming Çankaya University Ankara Turkey

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

Fasttext is a powerful word representation method that creates word representations based on vectors of character n-grams. In this work, we propose a method that utilizes fasttext features for a novel feature engineering model for the spam detection problem. In the feature engineering method, the combination of average, mean of second derivative; mean peak and standard deviation of fasttext features are computed. Finally, tf-idf features are also considered for the modeling process. The success of each feature engineering technique is measured and reported. The combination of the five feature extraction methods, tested on two spam detection datasets, yielded promising results with an accuracy of 0.978 on e-mail spam detection and an accuracy of 0.986 on sms spam classification.

关键词： Technological innovation Accuracy Unsolicited e-mail Computational modeling Feature extraction Vectors Intelligent systems Standards Postal services

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization

引用

computers, Materials & Continua 2023年第2期74卷 2677-2693页

作者： Reem Alkanhel El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Manal Abdullah Alohali Mostafa Abotaleb Doaa Sami Khafaga Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Information Systems Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of System Programming South Ural State UniversityChelyabinsk454080Russia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Applications of internet-of-things(IoT)are increasingly being used in many facets of our daily life,which results in an enormous volume of *** computing and fog computing,two of the most common technologies used in IoT applications,have led to major security *** are on the rise as a result of the usage of these technologies since present security measures are *** artificial intelligence(AI)based security solutions,such as intrusion detection systems(IDS),have been proposed in recent *** technologies that require data preprocessing and machine learning algorithm-performance augmentation require the use of feature selection(FS)techniques to increase classification accuracy by minimizing the number of features *** the other hand,metaheuristic optimization algorithms have been widely used in feature selection in recent *** this paper,we proposed a hybrid optimization algorithm for feature selection in *** proposed algorithm is based on grey wolf(GW),and dipper throated optimization(DTO)algorithms and is referred to as *** proposed algorithm has a better balance between the exploration and exploitation steps of the optimization process and thus could achieve better *** the employed IoT-IDS dataset,the performance of the proposed GWDTO algorithm was assessed using a set of evaluation metrics and compared to other optimization approaches in 2678 CMC,2023,vol.74,no.2 the literature to validate its *** addition,a statistical analysis is performed to assess the stability and effectiveness of the proposed *** results confirmed the superiority of the proposed approach in boosting the classification accuracy of the intrusion in IoT-based networks.

关键词： Feature selection grey wolf optimization dipper throated optimization intrusion detection internet-of-things(IoT)

来源：评论

学校读者我要写书评

暂无评论

Univariate & Multivariate Forecasting of Time Series Through a Contemporary Manner

Univariate & Multivariate Forecasting of Time Series Through...

引用

International Conference on High Technology for Sustainable Development (HiTech)

作者： Kiril Koparanov Daniela Minkovska Elena Antonova Department of Programming and Computer Technologies Technical University of Sofia Sofia Bulgaria Department of Computer Systems Technical University of Sofia Sofia Bulgaria

ISBN: (数字)9798350358100

ISBN: (纸本)9798350358117

Detailed forecasting of time series is one of the fields where the latest advancements in information technology make significant contributions. Operating with financial data poses noteworthy challenges owing to its inherent nature and substantial impact on economic dynamics within society. This study explores the utilization of automated tools as a set of resources for both unifactorial and multifactorial forecasting, drawing conclusions and providing recommendations.

关键词： Economics Accuracy Time series analysis Predictive models Data models Forecasting Sustainable development Information technology

来源：评论

学校读者我要写书评

暂无评论

Direct and Inverse Optimization Problems in a Gas Deposit Model 15

Direct and Inverse Optimization Problems in a Gas Deposit Mo...

引用

15th International Conference Management of Large-Scale System Development, MLSD 2022

作者： Skiba, Alexander Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Design Methods for Developing Systems Department of Mathematical Methods of Regional Programming Moscow Russia

ISBN: (数字)9781665497015

ISBN: (纸本)9781665497015

A continuous dynamic model for the development of a gas field is studied. Two mathematical problems are posed, solved and analyzed. In the direct problem, we are looking for the maximum accumulated profit on a set of temporary functions of a certain type. In the inverse optimization problem, we define the entire set of planning horizons. We subject the assigned tasks to a comprehensive analysis. © 2022 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Liveness Detection Using Deep Learning 9

Fingerprint Liveness Detection Using Deep Learning

引用

9th International Conference on Future Internet of Things and Cloud, FiCloud 2022

作者： Ozkiper, Zeynep Inel Turgut, Zeynep Atmaca, Tulin Aydin, Muhammed Ali Halic University Computer Programming Istanbul Turkey Istanbul Medeniyet University Computer Engineering Istanbul Turkey Institut Polytechnique de Paris Samovar Lab./IMT/Telecom SudParis Evry France Istanbul University Computer Engineering Cerrahpasa Istanbul Turkey

ISBN: (数字)9781665493505

ISBN: (纸本)9781665493505

It has great importance to provide the highest accuracy from fingerprint identification and verification systems, which have a large number of biometric features. Fingerprint recognition systems are more widely utilized than other biometric feature recognition systems. For this reason, a fingerprint recognition system must be fast and reliable to realize the separation of the fake and live fingerprints and provide high accuracy. In this study fingerprint liveness detection system is presented using LivDet2015 dataset. SVM (Support Vector Machine), CNN (Convolutional Neural Network), CNN+SVM methods are used for classification and their performances are compared. Especially the classifying performance of CNN method is analyzed. Before the classification process is performed with SVM, edge enrichment, transformation and feature extraction steps are applied on images as preprocessing steps. The highest accuracy rate is obtained by using CNN-deep learning classifier. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Using LSTM as Intelligent Machine Learning Method to Forecast the Annual Average Relative Humidity: A Case Study for Konya, Turkiye

Using LSTM as Intelligent Machine Learning Method to Forecas...

引用

Intelligent and Fuzzy Systems - Intelligence and Sustainable Future Proceedings of the INFUS 2023 Conference

作者： Mayanja, Abubakar Eryürük, Şule Eryürük, Kağan Graduate School in Science Department of Computer Engineering Selcuk University Konya Turkey Vocational School of Commerce and Industry Department of Computer Programming KTO Karatay University Konya Turkey Department of Industrial Engineering KTO Karatay University Konya Turkey Department of Civil Engineering Necmettin Erbakan University Konya Turkey

ISBN: (纸本)9783031397769

Nowadays, one of the most demanding areas of Artificial Intelligence application is to forecast the weather condition as rapid and accurate as possible. The ratio of air vapor pressure to saturation vapor pressure is defined as relative humidity which is represented by a percentage of how much moisture the atmosphere can hold at the same temperature and pressure. The relative humidity has a significant impact on climate change and global warming which have had a negative impact on agriculture, economy, food security, and public health. In addition, accurate weather information and humidity forecasts are frequently required to warn of natural disasters result from unexpected changes in climatic conditions such as relative humidity. Therefore, recent decades have seen a rise in interest in this field of study. The aim of this study is to use Long Short-Term Memory (LSTM) models to forecast the annual relative humidity in Konya, Turkey between 1931 and 2010 by utilizing the annual average amounts of rain, sunlight, wind speed, and temperature. This paper represents a novel approach to predict annual relative humidity in Konya, which has not been previously explored in this location and between the given dates. As a result, the findings were able to forecast the monthly average humidity for next five years in advance with a mean square error of 0.1705% within 150 episodes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Long short-term memory

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：