检索结果-内蒙古大学图书馆

Information Security Models and Algorithms Using Generative-Adversarial Neural Networks and User data

Information Security Models and Algorithms Using Generative-...

2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Udilov, Nikita S. Ural Federal University Department Of Big Data Analytics And Methods Of Videoanalysis Ekaterinburg Russia

ISBN: (纸本)9798350362893

In this article, the author reminds about the relevance of information security in the context of digitalization and active development of machine learning technologies. Also, the author emphasizes the popularity of users' use of weak passwords containing personal information about the user, which are vulnerable to hacking. To effectively identify such passwords, the author describes and proposes an approach to generating password lists based on a generative-adversarial neural network and known data about the user (such as full name, date of birth, hobbies, names of relatives, etc.), which can be used in information security audits to identify vulnerable passwords, penetration testing, as well as to solve some problems in forensic computer forensics. To train the neural network, it is proposed to use publicly available data from open sources that became known as a result of various personal data leaks, including compromised passwords, as well as information from various search engines and social networks such as «Vkontakte», «Odnoklassniki», and others. © 2024 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection and Prevention System AI Based Features with Random Forest

Intrusion Detection and Prevention System AI Based Features ...

引用

2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Al-Doori, Mohammed B. Komotskiy, Evgeny I. Ural Federal University Department Of Big Data Analytics And Methods Of Videoanalysis Ekaterinburg Russia

ISBN: (纸本)9798350362893

The research addresses sophisticated methods for Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS), leveraging AI-based feature optimization and diverse machine learning strategies to bolster network intrusion detection and prevention. The study primarily utilizes the NSLKDD dataset, an enhanced version of the KDD Cup 1999 dataset, chosen for its realistic portrayal of various attack types and for addressing the shortcomings of the original dataset. The methodology includes AI-based feature optimization using Particle Swarm Optimization and Genetic Algorithm, focusing on maximizing information gain and entropy. This is integrated with the use of Random Forest (RF) to reduce class overlapping, further enhanced by boosting techniques. Grey Wolves Optimization (GWO) is combined with Random Forest. This innovative approach, supplemented by grey wolf hunting strategies, is employed for classification tasks on the NSL-KDD dataset. The performance metrics for each intrusion class are meticulously evaluated, revealing that the GWO-RF combination achieves an accuracy of 0.94, precision of 0.95, recall of 0.93, and an F1 score of 0.94. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

U-NET with Extreme Learner Approach in Retinal Vessel Image Segmentation

U-NET with Extreme Learner Approach in Retinal Vessel Image ...

引用

2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Chekhomov, Igor Mashhadani, Abbas FadhilSalih Al Ural Federal University Department Of Big Data Analytics And Methods Of Videoanalysis Ekaterinburg Russia

ISBN: (纸本)9798350362893

Retinal diseases are a visual disorder that can cause human vision problems, such as blindness and low vision. Early detection of this disease is important to prevent visual impairment. The identification of diseases relies heavily on the accurate separation of blood vessels inside the retina. Additionally, it is beneficial to administer prompt therapeutic interventions for life-threatening illnesses. In ophthalmology, segmentation of blood vessels is a major component of color retinal fundus images analysis for monitoring and diagnosing retinal diseases, like diabetic retinopathy, hypertensive retinopathy, age-related macular degeneration and arteriosclerotic. This process is effective to identify retinal diseases more accurately. This paper helps in segmentation of blood vessels in retinal images as it proposes a new method which is effective in removing noise and makes blood vessels in images clearer using machine learning techniques. This paper proposes the use of U-net with Extreme Learning Approach for blood vessel segmentation of retinal images. Moreover, this approach suites for processing small and unbalanced datasets. © 2024 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Web Usability Segmentation - Applying K-Means Clustering to the System Usability Scale

Web Usability Segmentation - Applying K-Means Clustering to ...

引用

2023 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2023

作者： Agbozo, Ebenezer Ural Federal University Department of Big Data Analytics and Methods of Videoanalysis Yekaterinburg Russia

ISBN: (纸本)9798350336054

With the growing demand in platforms that serve as a medium to connect businesses with clients, as well as for users to interact with each other, there is a high desire for quality user interface (UI) and user experience (UX). System usability plays a vital role in ensuring UX and UI quality. A widely accepted standard for evaluating usability is the system usability scale (SUS) survey which provides an overview on how usable a given system is. Since data-driven techniques and algorithms abound in today's fast-paced world, it is pertinent that system owners leverage on such tools to understand their users and provide quality UX and UI. The data-driven methodology popularly known as segmentation techniques have been applied in numerous fields such as market segmentation, customer relations management, supply chain and production, to better understand the requirements for providing quality customer experience. This study proposes the use of one of such tools, usability segmentation, achieved by applying the k-means clustering algorithm to SUS data. The study contributes to theory and practice. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing data security through an integrated approach of multiple key cryptography and steganography in the wavelet domain 4th

Enhancing data security through an integrated approach of mu...

引用

4th International Conference on Computational methods in Science and Technology, ICCMST 2024

作者： Hashem, Al-Fariji Ahmed Hussein Medvedeva, Marina A. Agbozo, Ebenezer Department of Big Data Analytics and Methods of Video Analysis Ural Federal University Ekaterinburg Russia

ISBN: (纸本)9781032911571

The quantity of data that may be incorporated and the picture quality must be compromised in order to embed data within an image. As a direct result of this increased distortion, the quality of the stego picture that is generated when more data is hidden within a carrier image will decrease. One thing may be taken into consideration is the difficulty of optimizing the process of embedding a substantial amount of data into an image. This article aims to provide an overview of the many methods of picture steganography and to present the several attempts that have been made to achieve image steganography via the use of deep learning and machine learning techniques. This work concluded with several potential directions for future photo steganographic-based deep learning research, and it indicated that these new directions may be investigated soon. The suggested approach ensures that even comparable letters are encrypted differently by encrypting data using a series of pseudorandom keys created from a single 16-bit seed. By using this strategy, the communication is not only more hidden but also safer against attempts at unauthorized decryption. After encryption, matrix encoding, which is made feasible by discrete wavelet transformation, embeds the encrypted data into the high-frequency sub-band of a cover image. The robust Peak Signal-to-Noise Ratio (PSNR) readings, which often exceed the 40 dB threshold, attest to the cover picture’s preservation as a result of this steganographic technique. These PSNR values, which exhibit relatively minimal optical distortion, will make the stego-image unnoticeable. In tests of performance, the proposed method demonstrated excellent imper-ceptibility, with PSNR values continuously over 46 dB and a low Bit Error Rate (BER) of around 3%, indicating a high degree of fidelity in the recovered data. © 2025 the Author(s).

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection and Prevention System AI Based Features with Random Forest

Intrusion Detection and Prevention System AI Based Features ...

引用

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)

作者： Mohammed B. Al-Doori Evgeny I. Komotskiy Department of Big Data Analytics and Methods of Videoanalysis Ural Federal University Ekaterinburg Russia

ISBN: (数字)9798350362893

ISBN: (纸本)9798350362909

关键词： Accuracy Prevention and mitigation Feature extraction NSL-KDD IP networks Particle swarm optimization Task analysis

来源：评论

学校读者我要写书评

暂无评论

U-NET with Extreme Learner Approach in Retinal Vessel Image Segmentation

U-NET with Extreme Learner Approach in Retinal Vessel Image ...

引用

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)

作者： Igor Chekhomov Abbas FadhilSalih Al Mashhadani Department of Big Data Analytics and Methods of Videoanalysis Ural Federal University Ekaterinburg Russia

ISBN: (数字)9798350362893

ISBN: (纸本)9798350362909

关键词： Image segmentation Visualization Accuracy Blood vessels Retina Feature extraction Retinal vessels

来源：评论

学校读者我要写书评

暂无评论

Information Security Models and Algorithms Using Generative-Adversarial Neural Networks and User data

Information Security Models and Algorithms Using Generative-...

引用

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)

作者： Nikita S. Udilov Department of Big Data Analytics and Methods of Videoanalysis Ural Federal University Ekaterinburg Russian Federation

ISBN: (数字)9798350362893

ISBN: (纸本)9798350362909

In this article, the author reminds about the relevance of information security in the context of digitalization and active development of machine learning technologies. Also, the author emphasizes the popularity of users’ use of weak passwords containing personal information about the user, which are vulnerable to hacking. To effectively identify such passwords, the author describes and proposes an approach to generating password lists based on a generative-adversarial neural network and known data about the user (such as full name, date of birth, hobbies, names of relatives, etc.), which can be used in information security audits to identify vulnerable passwords, penetration testing, as well as to solve some problems in forensic computer forensics. To train the neural network, it is proposed to use publicly available data from open sources that became known as a result of various personal data leaks, including compromised passwords, as well as information from various search engines and social networks such as «Vkontakte», «Odnoklassniki», and others.

关键词： Social networking (online) Forensics Information security Passwords Machine learning Search engines Computer crime

来源：评论

学校读者我要写书评

暂无评论

Web Usability Segmentation - Applying K-Means Clustering to the System Usability Scale

Web Usability Segmentation - Applying K-Means Clustering to ...

引用

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)

作者： Ebenezer Agbozo Department of Big Data Analytics and Methods of Videoanalysis Ural Federal University Yekaterinburg Russia

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating environmental quality among G20 nations: The impacts of environmental goods and low-carbon technologies in mitigating environmental degradation

引用

Geoscience Frontiers 2024年第1期15卷 84-96页

作者： Ernest Baba Ali Samira Shayanmehr Riza Radmehr Richard Bayitse Ebenezer Agbozo Department of Economics University for Development StudiesTamale P.O.Box TL1350Ghana Department of Agricultural Economics Ferdowsi University of MashhadIran Council for Scientific and Industrial Research Institute of Industrial ResearchAccra P.O.Box LG 576Ghana Department of Big Data Analytics and Methods of Video Analysis Ural Federal University19 Mira Str60002 EkaterinburgRussia

Environmental goods and low-carbon technologies have long been identified as having the potential to drive long-term economic progress without compromising environmental quality. However, their exact role in mitigating environmental degradation are yet to be unravelled. In addressing this shortfall, the extant literature relied on research funding and patent application as proxies for green technologies. Having established the weaknesses in the use of these variables as proxies for green technologies, this study explored the role of trade in environmental goods and low-carbon technologies in boosting environmental quality among G20 nation using a panel dataset from 1994 to 2018. The study employed the Method of Moment quantile regression for the model estimation and the Ridge regression, Discroll-Kraay standard error, and the Newey-West standard error estimators to test the robustness of our findings. Our findings indicate that whereas environmental goods promote environmental quality, low-carbon technologies decrease same. Also, the study found economic growth to exert an aggravating effect on environmental quality, while foreign direct investments, natural resource rents, human capital development, and renewable energy consumption exert positive influence on environmental quality. Based on the findings of the study, G20 nations are encouraged to improve green market structures to improve the trade in environmental goods and low-carbon technologies. Also the share of renewable energy sources in the overall energy basket must be improved to help improve environmental quality.

关键词： Environmental quality Environmental goods Low-carbon technology G20 nations

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：