Menoufia Journal of Electronic Engineering Research最新文献_第3页

Diabetic Retinopathy Detection and Grading using Deep learning 糖尿病视网膜病变的深度学习检测和分级

Menoufia Journal of Electronic Engineering Research Pub Date : 2022-06-17 DOI: 10.21608/mjeer.2022.138003.1057

M. Berbar

{"title":"Diabetic Retinopathy Detection and Grading using Deep learning","authors":"M. Berbar","doi":"10.21608/mjeer.2022.138003.1057","DOIUrl":"https://doi.org/10.21608/mjeer.2022.138003.1057","url":null,"abstract":"One of the complications of diabetes disease is diabetic retinopathy (DR). Diabetic patients may suffer from total loss of sight. That's if it is not detected and medicated early enough. The early detection of DR is very important during funds screening on a regular basis. Detection and grading of DR are difficult because most fundus images suffer from undersaturation and noise. This paper proposes a new enhancement process as a solution to the poor quality of fundus images. It also proposes two architectures for convolutional neural network (CNN) models. The first one is the binary classifier of DR images into normal and abnormal. The second CNN architecture to classify the severity grades of DR. In this study, we also utilized different pre-trained convolutional neural network models to show the impact on the performance of the use of transfer learning from pre-trained CNN models vs newly defined architectures. The pre-trained CNN models and the two new proposed CNN models are tested using Messidor1, Messidor2, and Kaggle EyePACS datasets. The proposed binary classifier model results in F1-scores of 0.9387, 0.9629, and 0.9430 on the Messidor-1, Messidor-2, and EyePACS datasets, respectively. The proposed second model classifies the five grades with an F1-score of 0.9133, 0.9226, and 0.9393 on the Messidor1, Messidor2, and Kaggle EyePACS datasets, respectively. The new proposed CNN model proved its reliability and efficiency in detecting DR and classifying severity grades of DR in fundus images. Preprocessing techniques enhanced the performance by 10.83% of accuracy and 0.13037 in AUC using the binary model. Keywords— Diabetic Retinopathy; Convolutional Neural Network; Fundus images; Deep learning.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125781529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Faces Recognition and Facial Gender Classification using Convolutional Neural Network 基于卷积神经网络的人脸识别与性别分类

Menoufia Journal of Electronic Engineering Research Pub Date : 2022-06-17 DOI: 10.21608/mjeer.2022.137937.1056

M. Berbar

{"title":"Faces Recognition and Facial Gender Classification using Convolutional Neural Network","authors":"M. Berbar","doi":"10.21608/mjeer.2022.137937.1056","DOIUrl":"https://doi.org/10.21608/mjeer.2022.137937.1056","url":null,"abstract":"Computational power in deep convolutional neural networks has made it possible to have robust classifiers for faces and facial gender for many security issues and computer vision problems. This paper proposes two convolutional neural network (CNN) models for face recognition and facial gender classification. The models consist of an image input layer, followed by three blocks of convolutional, normalization, activation, and max-pooling layers, and three fully connected layers. The performance of the proposed CNN solutions is evaluated using five publicly available face datasets. Two greyscale face datasets: Sheffield and AT & T. Three color face datasets, Faces94, Ferret, and Celebrity Face Images from Kaggle. The achieved classification accuracy ranged between 99.0% and 100% on the Faces94, Ferret, Sheffield, and AT&T datasets, and classification accuracy of 93.6% to 95.0% on the Kaggle dataset. The proposed CNN can process and classify a smallsize face image 32 × 32-pixel from the Faces94, Sheffield, and AT&T datasets and 100 × 100 pixels from the Ferret and Kaggle datasets. The obtained results prove that the proposed CNN models are an effective solution for face image recognition and facial gender image classification. The proposed model produces competitive accuracy compared to several state-of-the-art methods. Keywords— Face recognition; facial gender classification; convolutional neural network; max pooling layer, fully","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126179209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Logistic Regression Hyperparameter Optimization for Cancer Classification 肿瘤分类的逻辑回归超参数优化

Menoufia Journal of Electronic Engineering Research Pub Date : 2022-01-11 DOI: 10.21608/mjeer.2021.70512.1034

Ahmed Ahmed Arafa, M. Radad, M. Badawy, Nawal A. El-Fishawy

{"title":"Logistic Regression Hyperparameter Optimization for Cancer Classification","authors":"Ahmed Ahmed Arafa, M. Radad, M. Badawy, Nawal A. El-Fishawy","doi":"10.21608/mjeer.2021.70512.1034","DOIUrl":"https://doi.org/10.21608/mjeer.2021.70512.1034","url":null,"abstract":"In machine learning, optimization of hyperparameters aims to find the best values of model hyperparameters yielding an optimal model with minimum prediction error. It is the most important step that directly affects the performance of learned model. Many techniques have been proposed to optimize hyperparameters for different predictive models. In this paper, the performance of grid search, random search, Bayesian Tree Parzen Estimator (TPE) and Simulated Annealing (SA) optimization techniques is evaluated to determine the best hyperparameters for a logistic regression model when used in cancer classification. Wisconsin Breast Cancer Dataset (WBCD) has been used to evaluate the previously mentioned optimization techniques. The results show that Bayesian TPE outperformed other techniques in terms of number of iterations and running time. The number of iterations to get optimal parameters in TPE is less than SA by 75.75 %, and random search by 77.1%. While the time taken by TPE is better than SA, random search and grid search by 79.9%, 86.1% and 99.9% respectively. The resulted optimal hyperparameter values have been utilized to learn a logistic regression model to classify cancer using WBCD dataset. The optimized model succeeded in classifying cancer with 98.2% for test accuracy, 0.962 for kappa statistic and 0.963 for MCC metrics when evaluated using 10-fold cross validation. Keywords— Hyperparameter Optimization, Random Search Grid Search, Tree Parzen Estimator, Simulated Annealing","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130301384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Applying Recurrent Networks For Arabic Sentiment Analysis 递归网络在阿拉伯语情感分析中的应用

Menoufia Journal of Electronic Engineering Research Pub Date : 2022-01-01 DOI: 10.21608/mjeer.2022.218776

Eslam Omara, Mervat Mosa, Nabil A. Ismail

{"title":"Applying Recurrent Networks For Arabic Sentiment Analysis","authors":"Eslam Omara, Mervat Mosa, Nabil A. Ismail","doi":"10.21608/mjeer.2022.218776","DOIUrl":"https://doi.org/10.21608/mjeer.2022.218776","url":null,"abstract":"The main characteristic of deep learning approaches is the ability to learn differentiating and discriminating features. These techniques can discover complex relations and structures within high-dimensional data. For feature extraction, deep learning models employ several layers of nonlinear processing units. One of the fields that have applied deep architectures with a noticeable breakthrough in performance measures is Natural Language Processing (NLP). Recurrent neural networks (RNNs) and their variants Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are commonly used for NLP applications as they are efficient at processing sequential data. Unlike RNNs, LSTMs and GRUs can combat vanishing and exploding gradients. In Addition, Convolutional Neural Network (CNN) is another deep architecture that has been widely used in language processing. On the other side, sentiment analysis (SA) is an NLP task concerned with opinions, attitudes, emotions, and feelings. Sentiment analysis deduces the author's attitude regarding a topic and classifies the attitude polarity according to a set of predefined classes. Application of SA in business analytics helps to gain insight into consumer behaviour and needs. In the proposed work deep LSTM, GRU, and CNN are applied for Arabic sentiment analysis. The models are implemented and tested employing character-level representation. Also, deep hybrid models that combine multiple layers of CNN with LSTM or GRU are studied. The application aims at investigating the capability of deep LSTM, GRU, and hybrid architectures to learn and extract features from characterlevel representation. Results show that combining different architectures can boost performance in SA tasks. The CNNLSTM/GRU combinations registered higher accuracy compared to deep LSTM and GRU. Keywords— Deep learning; Sentiment analysis; LSTM; GRU; CNN-LSTM; CNN-GRU.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124171354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Efficient Implementation of An Elliptic Curve Cryptosystem for Cancelable Biometrics 可取消生物特征的椭圆曲线密码系统的有效实现

Menoufia Journal of Electronic Engineering Research Pub Date : 2022-01-01 DOI: 10.21608/mjeer.2022.109707.1043

Ahmed A. Asaker, Zeinab F. Elsharkawy, Sabry S. Nassar, N. Ayad, O. Zahran, F. El-Sayed

{"title":"Efficient Implementation of An Elliptic Curve Cryptosystem for Cancelable Biometrics","authors":"Ahmed A. Asaker, Zeinab F. Elsharkawy, Sabry S. Nassar, N. Ayad, O. Zahran, F. El-Sayed","doi":"10.21608/mjeer.2022.109707.1043","DOIUrl":"https://doi.org/10.21608/mjeer.2022.109707.1043","url":null,"abstract":"With the increasing demands for biometric systems in our daily life for automatic identification of individuals, recently iris recognition system has gained a lot of attention attributed to its reliability, uniqueness, difficulty to be imitated and high accuracy in comparison with other available biometric recognition systems. Unfortunately, templates in traditional iris recognition system are unprotected and vulnerable to various threats, such as attacks at the iris reader level or at the database level. Hence, there is a need for developing a system for securing the existing iris recognition system for keeping the original biometrics safe and secure. In this paper, we introduce a hybrid model for protecting iris recognition system through combining an elliptic curve cryptosystem with a new salting-based cancelable iris recognition scheme. The obtained experimental results on CASIA-IrisV3 database proved that the proposed system guarantees a high degree of security and privacy protection without affecting the accuracy. Keywords—Iris Recognition System, Cancelable Biometrics, Elliptic Curve Cryptography, Hamming Distance, Normalized Cross Correlation, Receiver Operating Characteristics.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"363 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114500475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

COVID-19 Ad-hoc Remote Learning – Quality Assessment, “Seven Stars” Analysis and Lessons Learned 2019冠状病毒病临时远程学习——质量评估、“七星”分析和经验教训

Menoufia Journal of Electronic Engineering Research Pub Date : 2021-09-06 DOI: 10.21608/mjeer.2021.193088

Wael Badawy

引用次数: 0

EEG Signal Analysis Based Brain-Computer 基于脑机的脑电信号分析

Menoufia Journal of Electronic Engineering Research Pub Date : 2021-07-01 DOI: 10.21608/mjeer.2021.193083

Hend Nooreldeen, S. Badawy, M. El-Brawany

引用次数: 0

Fuzzy Controller based TCP-Vegas Enhancement for Congestion Control 基于模糊控制器的TCP-Vegas增强拥塞控制

Menoufia Journal of Electronic Engineering Research Pub Date : 2021-07-01 DOI: 10.21608/mjeer.2021.193084

Doaa Elnady, Gamal mahrouce, Gaber Allam

引用次数: 2

Performance enhancement of cooperative networks utilizing MAP decoder and Alamouti code 利用MAP解码器和Alamouti码增强合作网络的性能

Menoufia Journal of Electronic Engineering Research Pub Date : 2020-09-13 DOI: 10.21608/MJEER.2021.146087

S. Ramzy

引用次数: 0

Dynamic Modeling of Reactor Protection System in Nuclear Power Plant for Reliability Evaluation Based on State Transition Diagram 基于状态转换图的核电厂反应堆保护系统可靠性评估动态建模

Menoufia Journal of Electronic Engineering Research Pub Date : 2020-08-30 DOI: 10.21608/MJEER.2021.146073

M. Shouman, Amany S. Saber, M. Shaat, A. El-Sayed, Hanaa Torkey

引用次数: 1