Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Bulletin of Electrical Engineering and Informatics

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.