检索结果-内蒙古大学图书馆

2020 International Conference on computer Science and Software Engineering, CSASE 2020

作者： Ridha, Jwad Ali Saud, Jamila Harbi Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq College of Science Mustansiriyah University Baghdad Iraq

ISBN: (纸本)9781728152493

Researchers have proposed several approaches to provide processing methodologies for iris images captured in unconstrained mediums to leverage the level of accuracy for iris recognition systems. Segmentation is the most critical stage which considered a challenging area to researchers. In this paper, we propose an iris segmentation approach to handle the problem of low contrast iris images, in which the iris boundary is undetected. It uses the pupil boundary to define a search space for automatically finding an appropriate threshold value to extract the iris region, and then uses the thresholded image to create binary edge map with strong iris edge. Circular Hough Transform (CHT) is adopted to localize pupil/iris boundaries, and Rubber Sheet Model (RSM) of lower half of iris is used in normalization stage to eliminate upper eyelashes and eyelid. Contrast-Limited Adaptive Histogram Equalization (CLAHE) technique is adopted to overcome the low contrast problem of iris image. Finally, a region of interest without the impact of lower eyelashes and eyelid is selected to obtain noise free iris template. The proposed approach is tested on CASIA Iris Image Dataset Version 2.0. © 2020 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Criteria Decision Making for Machine Learning Algorithms Using AHP-VIKOR techniques: Case Study Adult Autism Diagnosis 5

Multi-Criteria Decision Making for Machine Learning Algorith...

引用

5th International Conference on Engineering Technology and its Applications, IICETA 2022

作者： Jassim, Mustafa Mohammed Ali, Manar Hassan Elamer, Amer S. Jaber, Mustafa Musa Mohammed, Mohammed Q. Alkhayyat, Ahmed Al-Farahidi University Department of Medical Instruments Engineering Techniques Baghdad10021 Iraq Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Informatics Baghdad10011 Iraq Dijlah University Collage Department of Computer Science Baghdad10021 Iraq Al-Esraa University College Department of Information Technology Baghdad10021 Iraq The Islamic University College of Technical Engineering Najaf Iraq

ISBN: (纸本)9781665472159

autism spectrum disorder is known as a neurodevelopmental disorder with sensory problems. Many infected adults die frequently due to the psychological conditions they live in. Machine learning helps doctors detect cases of autism spectrum disorders in adults. It has proven very successful in this field. In this study, after pre-processing and solving the data class imbalance problem the data we proposed to use MCDM methods to know prioritization and the best method to diagnose autism between four algorithms (SVM, Random Forest, Neural Network, and KNN), after obtaining the classification results we utilized AHP method to assign weights to each classification performance metrics based on expert assessment then he used both the obtained weights and the classification results to enter them into the VIKOR method to make a decision based on the weighted table where we would get the ranking of the algorithms. The random Forest method scores the best in this classification for diagnosing autism, with an accuracy rate of 0.9957 and sensitivity 0.9841. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Arabic Document Clustering: A Survey

Arabic Document Clustering: A Survey

引用

Current Research in Engineering and Science Applications (ICCRESA), International Conference on

作者： Khitam A. Salman Hussien K. Khafaji Iraqi Commission for Computers and Informatics / Informatics Institute for Postgraduate Studies-Baghdad-Iraq Baghdad Iraq Communication Engineering Department Al-Rafidain University College Baghdad Iraq

Arabic language significance is continuously growing due to economic advancements and the textual content of the Internet nowadays. As Arabic documents become more widely available on the Internet, Arabic document clustering becomes an essential topic in information retrieval and mining. Electronic Arabic documents are growing daily, making a clustering procedure based on humans impractical. Effective and efficient electronic search algorithms are necessary to make clustering easier and more accurate information retrieval possible. The purpose of this work is to provide a thorough examination of the algorithms and strategies utilized for clustering digitized Arabic texts. The paper presents a critical and constructive analysis of existing published literature in Arabic document clustering through summary, classification, analysis, and comparison. It collects the aims of surveys, such as literature organization and evaluation, identifying patterns and trends in the literature, synthesizing literature, identifying research gaps, and recommending new research areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construct an Efficient DDoS Attack Detection System Based on RF-C4.5-GridSearchCV

Construct an Efficient DDoS Attack Detection System Based on...

引用

Communication and Information Technologies (IICCIT), iraqi International Conference on

作者： Dhurgham Kareem Ghurkan Amer A. Abdulrahman dept of Computer Informatics Institute for Post Graduate Studies Iraqi Commission for Computers and Informatics Technical Institute-Suwaira Middle Technical University Baghdad Iraq dept. of Computer Informatics Institute for Post Graduate Studies (IIPS) Baghdad Iraq

ISBN: (纸本)9781665472210

Distributed Denial of Service (DDoS) attacks are intended to drain network resources and increase malicious traffic. This paper describes the mechanism and methods of DDoS attacks. By studying and analyzing a data set of this type, more than one parameter is collected, preprocessed, and expanded. In this work, experiments were carried out by building RF and C4.5 classification models and using the GridSearchCV class for the purpose of optimizing the parameters of these techniques are used. Then, an Extra tree classifier is used to identify the feature and reduce the dimensions according to the importance of each feature, eliminating the noise value that occurs in the feature data. Use the accuracy of the confusion matrix to illustrate the evaluation of the model, and finally check that the evaluation model is effective and can be trusted.

关键词： Buildings Denial-of-service attack Feature extraction Classification algorithms Information and communication technology computer crime Random forests

来源：评论

学校读者我要写书评

暂无评论

Unequal clustering and scheduling in Wireless Sensor Network using Advance Genetic Algorithm

Unequal clustering and scheduling in Wireless Sensor Network...

引用

2019 Imam Al-Kadhum International Conference for Modern Applications of Information and Communication Technology, MAICT 2019

作者： Yas, Ruwaida M. Hashem, Soukaena H. Information Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Iraq Computer Science Department University of Technology Iraq

Duo to limited energy of the sensor nodes which forming the wireless sensor network (WSN), and almost deployed in harsh environment, therefore it is very important to minimize the consumption of the sensor node's energy. For this reasons designing an energy efficient clustering and scheduling of sensor nodes considered the most efficient methods for extending the WSN's lifetime. In this paper, we have proposed Genetic algorithm based methods for clustering and scheduling. The proposed methods have two stages;in the first stage GA is used for cluster formation where the chromosome is represented by using the sensor node's position. While in the second stage GA is used for selecting a minimum number of nodes while maintaining the full coverage and the connectivity of the selected nodes. The simulation result shows that the proposed algorithm (AGA) is more efficient than the existent algorithms in terms of number of first node die per round, number of a live nodes, and energy consumption. © Published under licence by IOP Publishing Ltd.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

iraqi e-learning adoption trials for building sustained developed society 3

Iraqi e-learning adoption trials for building sustained deve...

引用

3rd International Conference on Engineering Technology and its Applications, IICETA 2020

作者： El-Ameer, Amer S. Hammed, Ahmed G. Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Baghdad Baghdad Iraq

ISBN: (纸本)9781728182315

Everything in the world become digitally nowadays. International world organization's reports showed a very dark view and bad visions about the educational system in Iraq. Two big ministries for education and higher education with good numbers of workers in this sector. Because of the lack of the experience and good planners and other factors, our education system still focuses on the traditional teaching and learning methods like face to face old method. The digital facts about Iraq show us that the society are ready to transform towards new electronic learning methods. If we keep our traditional methods, we rob the future of our students. The research shows the iraqi higher education roadmap towards raising the learning efficiency by adoption of e-learning approaches and applications. A trial start very slowly in 2015 without any kind of supporting and have achieved a lot of its goals and enter new zones in the education world like MOOCs, Higher Education Atlas, Academic Monitoring system and complete learning platforms and adopt new pedagogical and ICT concepts to the iraqi higher education systems. Start with raising the e-learning culture between iraqi academics (30 activity, distributed between conferences, meetings, workshops in different iraqi universities) (public and private), 10 iraqi e-learning design solutions, executing and testing its software's, with a lot of trials show us the correct way at the end which are the merging between our iraqi e-learning solutions and the web applications in an iraqi mosaicked blended e-learning platforms. As a result with taken into consideration the iraqi universities independencies, we have write a road map for re building our iraqi society and make it knowledge society with adoption of e-learning and lifelong learning. © 2020 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Implementing a Novel Low Complexity CNN Model for Brain Tumor Detection

Implementing a Novel Low Complexity CNN Model for Brain Tumo...

引用

Contemporary Information Technology and Mathematics (ICCITM), International Conference on

作者： Nawras Al-Ani Omran Al-Shamma Iraqi Commission for Computers and Informatics Information Institute for Postgraduate Studies Baghdad Iraq Scientific Affairs Department University of Information Technology and Communications Baghdad Iraq

All over the world, thousands of people die yearly from brain tumor disease. It is considered a life-threatening, prominent, and serious disease. Thus, saving people-life requires automated detection and well-timed analysis of brain tumors. Accurate detection is the first and most important stage in diagnosing and treating brain tumors. Recently, the deep learning approach has been widely used in the medical sector, especially in diagnosing brain tumors. This paper introduces a novel low-complexity CNN model for detecting brain tumors using MRI images. A freely available dataset from Kaggle is employed. Initially, to select the baseline model, four famous CNN models, involving AlexNet, VGG-16, GoogLeNet, and ResNet-50, are examined and trained from scratch. The AlexNet model showed the best performance and got the highest accuracy of 98.8%. After improving it by inserting different layers, the proposed model reached an accuracy of 99.4%. To attain a low-complexity model, the final model has twenty-two layers, including nine convolutional blocks and four dropout layers. Other performance metrics include 99.67% precision, 99.02% recall, and 99.35% F1 score.

关键词： Shape Computational modeling Magnetic resonance imaging Brain modeling Mathematical models Complexity theory Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DuaNet: A Novel Lightweight CNN Model for Classifying Five-class Lung Diseases

DuaNet: A Novel Lightweight CNN Model for Classifying Five-c...

引用

Data Science and Intelligent Computing (ICDSIC), International Conference on

作者： Duaa Al-Naqeeb Omran Al-Shamma Information Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq Scientific Affairs Department University of Information Technology and Communications Baghdad Iraq

Lung diseases rank among the world's top killers and disablers. Therefore, early identification is crucial for improving long-term survival rates and boosting the chances of recovery. Unlike the traditional method, machine learning (ML) showed great success in the medical field, mainly detecting and diagnosing different diseases. Most recently, the deep learning approach enhanced classification accuracy and eliminated the difficulty of manual feature extraction. As a literature conclusion, the model performance accuracy is inversely proportional to the number of lung diseases under consideration. In addition, no more than four classes (including normal) were considered previously. This work developed a lightweight CNN model, identified as DuaNet, with higher accuracy than the up-to-the-date models. The dataset has 930 x-ray images, categorized into five-class lung diseases: normal, tuberculosis, pneumonia COVID-19, pneumonia viral, and pneumonia bacterial. DuaNet comprises fifteen layers involving input, seven convolutional blocks, three max-pooling, three fully connected, and one output (Softmax) layer. Each convolutional block consists of a convolutional layer, Batch normalization, and ReLU activation function. The final model (DuaNet) obtained a performance accuracy of 99.87%, with 100% for other metrics.

关键词： COVID-19 Microorganisms Tuberculosis Pulmonary diseases Computational modeling Data models Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Facial deepfake performance evaluation based on three detection tools: MTCNN, Dlib, and MediaPipe

引用

AIP Conference Proceedings 2024年第1期3097卷

作者： Mohammed Thajeel Abdullah Nada Hussein M. Ali Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq Department of Computer Science College of Science University of Baghdad Baghdad Iraq

DeepFake, DeepFake detection, and face detection technologies have a strong relationship. DeepFake techniques have become a serious threat to celebrities, the general public, and the judiciary, which relies on visual media as evidence in criminal cases. DeepFake detection methods are responsible for detecting DeepFake through a series of procedures, the first and most significant of which is face detection. Note that face detection approaches are used in several methods to detect faces in photos, including those in DeepFake generating and DeepFake detection. Hence, the first part of this paper describes the concept of face detection and three of its tools, two of which are frequently utilized in DeepFake detection (Multi-Task Cascaded Convolutional Networks (MTCNN) and Dlib). MediaPipe has not yet been employed in this field to study and evaluate the performance of these tools through a practical comparison. Consequently, a group of modern DeepFake detection methods proposes a new taxonomy based on extracting the features utilized in each. Lastly, datasets of photos from DeepFake detection experiments were used to determine which one posed a genuine challenge to the three tools. The results presented that the MediaPipe tool is the best in accuracy, 99.3%, and the dataset Open Forensic (OF) is the most challenging due to the many mistakes generated when its works on it.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image compression techniques using multiwavelet transform algorithm

引用

AIP Conference Proceedings 2024年第1期3079卷

作者： Shaymaa Abdulelah Shaban Waleed A. M. Al-Jawher Information Institute for Postgraduate Studies Iraqi Commission for Computer & Informatics Baghdad-Iraq Uruk University Baghdad-Iraq

Multiwavelets, a relatively new area, have the potential to overcome some of the drawbacks of wavelets. Multiwavelets can combine multiple desired transform properties and provide more design options. This study examines the effectiveness of multiwavelet transforms for compressing medical images. A two-dimensional (2-D) multiwavelet decomposition is performed on the original image. Multiwavelet image transformation is implemented in the Geronimo-Hardin-Massopust (GHM) stage. Metrics utilized in the research include Mean Square Error (MSE) and Peak Signal Noise Ratio (PSNR). MRI brain imaging was employed for this proposed study, and Matlab2021 software was used to implement it.

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：