检索结果-内蒙古大学图书馆

5th International Conference on Information Technology, Applied Mathematics and Statistics, ICITAMS 2023

作者： Ali, Huda H. Yas, Ruwaida M. Abdulameer, Maysaa H. Baghdad Iraq Informatics Institute For Post-Graduation Studies Iraqi Commission For Computer & Informatic Baghdad Iraq

ISBN: (纸本)9798350335118

Botnets constitute a significant cybersecurity threat becoming increasingly sophisticated and challenging to detect. In addition, they are used for various illegal activities, such as spreading viruses, conducting DDoS attacks, click fraud, phishing, and identity theft. This study focuses on the latest advancements in machine learning-based botnet detection research. It initially describes how ML technology is implemented in network security research and describes the properties regarding the botnet's structure prior to the introduction of ML for botnet detection. Next, the study analyzes and summarizes the most commonly used ML algorithms and their security features in botnet detection. Finally, it concludes by summarizing the current ML solutions for describing, detecting, and researching botnets, as well as discussing how to evaluate the accuracy of botnet detection techniques. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cancer Subclassification Using Multi-Omics Clustering and Quantum Cat Swarm Optimization

Iraqi Journal for Computer Science and Mathematics

引用

iraqi Journal for computer Science and Mathematics 2024年第3期5卷 552-582页

作者： Ali, Ali Mahmoud Mohammed, Mazin Abed Informatics Institute for Postgraduate Studies Iraqi Commission for Computers & Informatics Baghdad Iraq Department of Artificial Intelligence College of Computer Science and Information Technology University of Anbar Anbar31001 Iraq

Integrating multiple omics data can significantly improve the accuracy of cancer subclassification, a challenging task due to the high dimensionality and limited sample sizes. The integration of these data sets can enhance model performance. This study addresses these challenges by employing Quantum Cat Swarm Optimization (QCSO) for feature selection, along with K-means clustering and Support Vector Machine (SVM) for classification. Using QCSO, the most significant features were identified, resulting in an increase in accuracy from 81% to 100%. Performance was evaluated using accuracy, F1-score, precision, recall, ROC, and the silhouette metric, all of which confirmed the effectiveness of the feature selection approach. Additionally, this method enhances the classification of samples while making the models more interpretable, providing better insights into the molecular mechanisms of cancer. This work contributes to advancing knowledge in the field of cancer research and biology in general. © 2024 College of Education, Al-iraqia University. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Text Classification using Artificial Intelligence Models 4

A Comparative Study of Text Classification using Artificial ...

引用

4th International Conference on Current Research in Engineering and Science Applications, ICCRESA 2022

作者： Abdulameer, Maysaa H. Abdullah, Mahmood Z. Informatics Institute for Post-Graduation Studies Iraqi Commission for Computer & informatics Baghdad Iraq College of Engineering Al-Mustansiriyah University Baghdad Iraq

ISBN: (纸本)9798350334944

The presented study provides experiments for carrying out empirical studies related to deep learning, especially convolution networks, concerning novel dataset classification (video and audio). The study will utilize the architecture of the text classification problem in the document domain with the datasets related to documents collected from many projects on real document cases. The process of building a new dataset and the existence of such data followed the urgent need that is specialized in educational lectures. Test and evaluate the two new datasets (Audio and Video) with the published dataset Book dataset by using deep learning methods in classification and machine learning algorithms, then compare the Accuracy results for each dataset with both classification methods, which present that new datasets bring better results than Book dataset which are (95% and 90%) for new datasets and 83% for Book dataset by using Deep learning, in machine learning algorithms the results are (91%, 77%, and 46%). Finally, the two classification techniques are used to maximize the benefits of the classification process. In the selection process, the system will choose deep learning for classifying the datasets than using machine learning algorithms. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Developing a method to detect driver drowsiness based on a single EEG channel and discriminated features

引用

International Journal of Intelligent Systems Technologies and Applications 2024年第1期22卷 29-40页

作者： Hussein, Raed Mohammed George, Loay E. Miften, Firas Sabar Iraqi Commission for Computers and Informatics Informatics Institute of Postgraduate Studies Baghdad Iraq Computer Sciences Department University of Information Technology and Communication Baghdad Iraq Computer Sciences Department College of Education for Pure Science University of Thi-Qar Thi-Qar Iraq

Driver drowsiness is one of the leading causes of road deaths and transportation industry dangers. Due to its direct evaluation of neurophysiological brain activity, electroencephalography (EEG) has been regarded as one of the most reliable physiological indicators for identifying driver drowsiness. This study proposes a straightforward, cost-effective method for detecting driver drowsiness using a single channel. The contribution of this research is the discovery of drowsiness using discriminated features [moments features (M1, M2, M3, M4), roughness features (R1, R2, R3, R4), zero crossing rate (ZCR), sample entropy (SE) and median absolute deviation (MAD)] from publicly available datasets. A novel model was introduced in this study, which involved the fusion of wavelet transform Daubechies order 4 (WTDB4) and residue decomposition (RD) techniques for feature extraction. Various classification algorithms, including the least-square support vector machine (LSSVM) and ensemble models were compared in terms of their performance metrics. The algorithm that exhibited superior accuracy with reduced computational time was chosen to classify the driver's status into two groups: awake and drowsy. Notably, the proposed model achieved an impressive accuracy of 97.95%. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Efficient Key Management in Lightweight Cryptography: A New Hashing-Based Approach 8

Efficient Key Management in Lightweight Cryptography: A New ...

引用

8th International Symposium on Multidisciplinary studies and Innovative Technologies, ISMSIT 2024

作者： Al-Mahmood, Haider H. Alsaad, Saad N. Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Mustansiriyah Department of Computer Science College of Science Baghdad Iraq

ISBN: (纸本)9798350354423

Lightweight encryption methods are introduced to overcome the challenges of high-power consumption and high memory usage in the traditional cryptography system. The primary goal of the lightweight encryption technique is to make it suitable for use in devices provided with lower power and small memories. The importance of lightweight cryptosystem is its ability to provide suitable security for data encryption without consuming high level of power and without need for big memories. As the devices with lower battery life and supplied low memory become widespread, encryption key management problems start to emerge. This may lead to a high possibility of an attack on the encryption key and break the encryption system. In this context, this paper proposes a novel hashing- based approach for key generation in lightweight cryptography. The approach involves generating significant hash digits from a seed input to the hashing system, and then using hash code slicing to select different characters and numbers that can be used as a seed for the key generating system. The practical results, which demonstrate that a small seed length can effectively generate a large key length, are a testament to the effectiveness of the proposed approach. These results can be used in the encryption process to reduce the initial total bits, thereby enhancing the efficiency of the system. © 2024 IEEE.

关键词： Cryptographic Algorithms Encryption Key Management Hashing Techniques IoT Security Lightweight Cryptography

来源：评论

学校读者我要写书评

暂无评论

A classifier design for micro bubble generators based on deep learning technique

引用

Materials Today: Proceedings 2023年 80卷 2684-2696页

作者： Qaddoori, Ayman S. Saud, Jamila H. Hamad, F.A. Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq College of Science Mustansiriyah University Baghdad Iraq School of computing Engineering and Digital Technology Teesside University Middlesbrough United Kingdom

This paper aims to study the sizes of bubbles generated by the micro-bubble generator device (MBGs) in the water because of its impact on the dissolved oxygen percentage in the water and we find this in aquaculture where oxygen is important for marine life and in many applications. Where we have designed a classifier for micro-bubbles of different sizes and the effectiveness of the device has been proven in generating bubbles whose size ranges from 20 to 50 and calculating their numbers in the image by converting the image from (RGB) to (HSV), it has proven its effectiveness in maintaining lighting and neglecting color information Which is not important in identifying bubbles in the image, as well as increasing the processing speed, and then finding edges in the image, using canny edge detection, which has proven its great effectiveness in finding weak and strong edges. Where we then used the (Circular Hough Transform) algorithm to identify the tiny bubbles in the image, calculate their average diameter and numbers in the image, and find the overlapping bubbles between them by using (Two Thresholds) one for the edge and the other for the center of the bubble and then making (Segmentation) for these bubbles and inserting them on (Gaussian Normal Distribution) Do not neglect the dark bubbles, because in most cases they are unreal bubbles and may be distortions in the image or reflections in the lighting. And then make (zero paddings) for the extracted images to make them equal in size and avoid the distortion that will happen in the image if another method is used to make all bubbles of equal dimensions to prepare them for classification. And then we calculated the (mean square error) of the resulting bubble images to avoid repeating the same bubble in (datasets). The efficiency of the classifier was calculated by using deep learning technology. Where we built a (Convolution Neural Network) consisting of (15) layers and then we trained these layers on the images resul

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CNN Hyper-Parameter Optimizer based on Evolutionary Selection and GOW Approach for Crimes Tweet Detection 16

CNN Hyper-Parameter Optimizer based on Evolutionary Selectio...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

作者： Abdalrdha, Zainab Khyioon Al-Bakry, Abbas Mohsin Farhan, Alaa K. Informatics Institute of Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq Baghdad Iraq University of Technology Department of Computer Sciences Baghdad Iraq

ISBN: (纸本)9798350381344

Social media is widely utilized for crime, highlighting the need for automated crime detection and prevention systems that can reach a vast audience. There is substantial study on specific social media crimes, but a holistic model to detect them is needed. This article classifies cybercrime tweets using deep neural networks, specifically deep CNNs, a common computer vision method. Although promising, deep neural networks need further research to find their best topology. Manual iteration and intensive testing limit the deep CNN model's practicality. CNN embedding dimensions, dense unit count, learning rate, and batch size affect model performance. Thus, constructing an effective CNN model with little manual intervention and domain expertise is difficult. This study reduces dimensionality and improves model performance by selecting the most relevant and informative dataset features using CNN hyperparameters. Five CNN feature selection methods using optimal hyperparameters are shown. These approaches use CNN, SO-roulette wheel, SO-tournament, SO-linear rank, SO-exponential rank, and Grey Wolf Optimizer to identify and categorize Arabic criminal tweets. The CNN-SO-tournament model recognizes illicit Arabic tweets with 99.60% accuracy. This study substantially improves Twitter crime prevention. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Improving the CNN Model for Arabic Crime Tweet Detection Based on an Intelligent Dictionary 16

Improving the CNN Model for Arabic Crime Tweet Detection Bas...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

ISBN: (纸本)9798350381344

Rising crime rates in Iraq and the Arab World pose significant challenges for law enforcement, exacerbated by vast data on criminal activity, technological advances, and high population density. This research aims to extract credible information from this data to understand crime better and assist in future prevention efforts. One challenge is the complexity of the Arabic language in crime detection. The study introduces an innovative approach using deep learning techniques, including creating an intelligent dictionary for detecting crime-related content in Arabic tweets. This method employs the Aho-Corasick algorithm to address the dynamic nature of language and evolving criminal terminology. The methodology applies deep learning and machine learning techniques, emphasizing natural language processing (NLP) for preprocessing and extracting relevant tweet characteristics. Created a labeled tweet dataset and classified it into various crime-related categories. Deep learning models, such as an improved CNN model based on chi-square testing and Grid search, were trained and evaluated using precision, recall, F1-score, accuracy, and MAP accuracy metrics. The analysis of an Arabic tweet dataset, comprising 18,493 tweets with ten features, demonstrated that the improved CNN model achieved a high accuracy of 99.25% and a macro F1-score of 99.9%. These results indicate that the proposed deep learning model outperforms others regarding accuracy. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

DDoS Cyber-Attacks Detection-Based Hybrid CNN-LSTM 3rd

DDoS Cyber-Attacks Detection-Based Hybrid CNN-LSTM

引用

3rd International Conference on Computing and Communication Networks, ICCCN 2023

作者： Khaleel, Thura Jabbar Shiltagh, Nadia Adnan Iraqi Commission for Computers and Information/Informatics Institute for Postgraduate Studies Baghdad Iraq Computer Engineering Department College of Engineering University of Baghdad Baghdad Iraq

ISBN: (纸本)9789819708918

Protecting software-defined networking (SDN) against cyber-attacks has become crucial in an expanding digital threat environment. Distributed Denial-of-Service (DDoS) attacks are risky since they may seriously interrupt operations. To mitigate these risks, this study introduces an anomaly detection method that utilizes a hybrid convolutional and short-term memory (CNN-LSTM) deep neural network. This model merges the CNN's ability to automatically extract spatial features with the LSTM's proficiency in sequence modeling, thereby enhancing the detection of anomalies in network traffic metadata. The model also integrates an autoencoder structure to facilitate representation learning and reduce dimensionality. The model's effectiveness was tested using publicly accessible SDN datasets, and the results were remarkable. The model identified DDoS attacks with an accuracy rate of over 99%, surpassing the performance of previous shallow learning models. Moreover, the model proved highly adaptable, successfully detecting attacks across various data samples. This deep learning-based detection system is a significant advancement, providing precise and efficient analytics that bolster real-time cybersecurity monitoring. However, it's crucial to continue research in deployment, interpretability, and the potential of combinatorial learning with other advanced technologies. We can only fully harness the great potential of artificial intelligence for adequate cyber protection by looking into these areas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

EAMSA 512: New 512 Bits Encryption Algorithm Based on Modified SALSA20

Iraqi Journal for Computer Science and Mathematics

引用

iraqi Journal for computer Science and Mathematics 2023年第2期4卷 131-142页

作者： Naif, Jolan Rokan Ahmed, Israa S. Zaki, Nashwan Dheyaa Hoomod, Haider K. Informatic Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Information Technology and Communications Baghdad Iraq Computer Science Department College of Education Mustanisiryah University Baghdad Iraq

This paper presents the 512-bit encryption algorithm based on modified SALSA20 using an 11-dimensional chaotic system used for generating the keys for the proposed encryption algorithm. Chaotic keys are derived from a combination of two systems, one with six dimensions and the other with five. These keys are used in different operations like shifting, Xoring, and encryption steps in the new proposed algorithm. The proposed algorithm consists of a combination of two parallel parts: Salsa20 and S boxes with chaos keys. The proposed system takes 512 bits of the plaintext, which will be split into two 256-bit parts, the left part encrypted with modified salas20 and the chaos keys, and the right 256-bit part encrypted using eight 8x8 s-boxes and the chaos keys. The results are swapped and combined, and this operation is repeated for 16 rounds to get the cipher text. The testing of EAMSA 512bit using various tests demonstrates the algorithm's strength and security, as well as its ability to avoid many attacks with lightweight processing. © 2023 International Journal of Chemical and Biochemical Sciences. All rights reserved.

关键词： Chaotic systems

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：