Article Per Year (5 Year)
p-Index From 2021 - 2026
1.152
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Bulletin of Electrical Engineering and Informatics
Abeer S. Desuky
Al-Azhar University
Computer Science & IT Electrical & Electronics Engineering

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
AutoKeras and particle swarm optimization to predict the price trend of stock exchange Doaa A. Fattah; Amany A. Naim; Abeer S. Desuky; Mervat S. Zaki
Bulletin of Electrical Engineering and Informatics Vol 11, No 2: April 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v11i2.3373

Abstract

The stock price varies depending on time, so stock market data is time-series data. The prediction of the trend of a stock price is a more interesting topic for investors to take an investment decision in a specific stock. Prediction of stock price always depends on machine learning algorithms. In this work, optimizing deep neural network (DNN) is used for predicting if the close price is reached to the profit which is determined by the investor or not and improve the prediction accuracy. Particle swarm optimization (PSO) and auto machine learning (AutoML) are used as optimizers with DNNs. The methods are applied to data of nine companies in Indonesia and National Stock Exchange (NSE) of India. The data is got from yahoo finance. Based on the experimental results, AutoML of deep learning proved to have the best accuracy rate, which is varying from 81 percent to 92 percent across all companies, and the accuracy after optimizing DNNs using PSO is varying from 73 percent to 82 percent across all companies.
Simulated annealing for SVM parameters optimization in student’s performance prediction Esraa Alaa Mahareek; Abeer S. Desuky; Habiba Abdullah El-Zhni
Bulletin of Electrical Engineering and Informatics Vol 10, No 3: June 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i3.2855

Abstract

High education is an important and critical part of education all over the world. In last year, the world has been turned increasingly to online education due to the outbreak of the Covid-19 pandemic; therefore, improving this education system became an urgent matter. Online learning systems are a primal environment for acquiring educational data which can be from different sources, especially academic institutions. These data can be mainly used to analyze and extract utilizable information to help in understanding university students’ performance and identifying factors that affect it. To extract some meaningful information from these large volumes of data, academic organizations must mine the data with high accuracy. In this work, three different real datasets were selected, pre-processed, cleaned, and filtered for applying support vector machine (SVM) with multilayer perceptron kernel (MLP kernel) and optimize its parameters using simulated annealing (SA) algorithm to improve the objective function value. While examining the search space, SA has the advantage of escaping from local minima since it offers the chance for accepting the worse neighbor as a solution in a controlled manner. The results show that the designed system can determine the best SVM parameters using SA and therefore presents better model evaluation.
Boosting with crossover for improving imbalanced medical datasets classification Abeer S. Desuky; Asmaa Hekal Omar; Naglaa M. Mostafa
Bulletin of Electrical Engineering and Informatics Vol 10, No 5: October 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i5.3121

Abstract

Due to the common use of electronic health databases in many healthcare services, healthcare data are available for researchers in the classification field to make diseases’ diagnosis more efficient. However, healthcare-medical data classification is most challenging because it is often imbalanced data. Most proposed algorithms are susceptible to classify the samples into the majority class, resulting in the insufficient prediction of the minority class. In this paper, a novel preprocessing method is proposed, using boosting and crossover to optimize the ratio of the two classes by progressively rebuilding the training dataset. This approach is shown to give better performance than other state-of-the-art ensemble methods, which is demonstrated by experiments on seven real-world medical datasets with different imbalance ratios and various distributions.
Even-odd crossover: a new crossover operator for improving the accuracy of students’ performance prediction Somia A. Shams; Asmaa Hekal Omar; Abeer S. Desuky; Mohammad T. Abou-Kreisha; Gaber A. Elsharawy
Bulletin of Electrical Engineering and Informatics Vol 11, No 4: August 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v11i4.3841

Abstract

Prediction using machine learning has evolved due to its impact on providing valuable and intuitive feedback. It has covered a wide range of areas for predicting student’ performance. Instructors can track student’s dropout in a particular course at an early stage and try to improve students’ performance. The problem of students’ future performance prediction using advanced statistics and machine learning is a hard problem due to the imbalanced nature of the student data where the number of students who passed the exam is generally much higher than the number of students who failed the exam. This paper proposes a new type of crossover operator called Even-Odd crossover to generate new instances into the minority class to handle the imbalanced data problem. The experiments are implemented using three machine learning (ML) algorithms: random forest (RF), support vector machines (SVM), and K-Nearest-Neighbor (KNN) to ensure the efficiency of the proposed technique. The performance of the classifiers is evaluated using several performance measures. The efficient ability of the proposed method on solving the imbalance problem is proved by performing the experiments on 22 real-world datasets from different fields and four students’ datasets. The proposed Even-Odd crossover shows superior performance compared to state-of-the-art resampling techniques.
Node classification with graph neural network based centrality measures and feature selection Asmaa M. Mahmoud; Abeer S. Desuky; Heba F. Eid; Hoda A. Ali
International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 2: April 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v13i2.pp2114-2122

Abstract

Graph neural networks (GNNs) are a new topic of research in data science where data structure graphs are used as important components for developing and training neural networks. GNN always learns the weight importance of the neighbor for perform message aggregation in which the feature vectors of all neighbors are aggregated without considering whether the features are useful or not. Using such more informative features positively affect the performance of the GNN model. So, in this paper i) after selecting a subset of features to define important node features, we present new graph features’ explanation methods based on graph centrality measures to capture rich information and determine the most important node in a network. Through our experiments, we find that selecting certain subsets of these features and adding other features based on centrality measure can lead to better performance across a variety of datasets and ii) we introduce a major design strategy for graph neural networks. Specifically, we suggest using batch renormalization as normalization over GNN layers. Combining these techniques, representing features based on centrality measures that passed to multilayer perceptron (MLP) layer which is then passed to adjusted GNN layer, the proposed model achieves greater accuracy than modern GNN models.
Rhizostoma optimization algorithm and its application in different real-world optimization problems Esraa A. Mahareek; Mehmet Akif Cifci; Habiba A. El-Zohni; Abeer S. Desuky
International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 4: August 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v13i4.pp4317-4338

Abstract

In last decade, numerous meta-heuristic algorithms have been proposed for dealing the complexity and difficulty of numerical optimization problems in the realworld which is growing continuously recently, but only a few algorithms have caught researchers’ attention. In this study, a new swarm-based meta-heuristic algorithm called Rhizostoma optimization algorithm (ROA) is proposed for solving the optimization problems based on simulating the social movement of Rhizostoma octopus (barrel jellyfish) in the ocean. ROA is intended to mitigate the two optimization problems of trapping in local optima and slow convergence. ROA is proposed with three different movement strategies (simulated annealing (SA), fast simulated annealing (FSA), and Levy walk (LW)) and tested with 23 standard mathematical benchmark functions, two classical engineering problems, and various real-world datasets including three widely used datasets to predict the students’ performance. Comparing the ROA algorithm with the latest meta-heuristic optimization algorithms and a recent published research proves that ROA is a very competitive algorithm with a high ability in optimization performance with respect to local optima avoidance, the speed of convergence and the exploration/exploitation balance rate, as it is effectively applicable for performing optimization tasks.
Co-Authors Amany A. Naim Asmaa Hekal Omar Asmaa M. Mahmoud Doaa A. Fattah Esraa A. Mahareek Esraa Alaa Mahareek Gaber A. Elsharawy Habiba A. El-Zohni Habiba Abdullah El-Zhni Heba F. Eid Hoda A. Ali Mehmet Akif Cifci Mervat S. Zaki Mohammad T. Abou-Kreisha Naglaa M. Mostafa Somia A. Shams