• Register
  • Login
  • العربیة

Alkut university college journal

  1. Home
  2. A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach

Current Issue

By Issue

By Author

By Subject

Author Index

Keyword Index

About Journal

News

Aims and Scope

A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach

    Authors

    • Maryam Jawad Kadhim
    • Jamal Kh-Madhloom
    • Khanapi Abd Ghan

    Al-Kut University College Journal

,

Document Type : Research Paper

  • Article Information
  • Download
  • Export Citation
  • Statistics
  • Share

Abstract

Machine learning algorithms have been a hallmark of data mining in image and signal processing. Several studies have proposed various methods for improving classification accuracy. Artificial Neural network (ANN) is one of the most important data mining classification method among predictive algorithms. The performance of ANN is affected by several parameters such as a number of hidden layers neurons, learning function, stop conditions and network architecture. Parameter regulation is a point of critical challenge in this algorithm. The main purpose of this study is to provide a novel approach by using multi-objective genetic algorithm and ensemble classifier to obtain optimal parameters of ANN. To this end, first, a set of neural networks were trained by setting their parameters through the multi-objective genetic algorithm. Next, the best combination of neural networks was selected to make an ensemble classifier. This method was evaluated with five popular and available datasets. Three measurements; accuracy, time and ROC curve were considered to assess the efficiency. The experimental results show that the proposed approach can achieve a trade-off between time and accuracy by the multi-objective genetic algorithm. Moreover, using ensemble-classifiers approach, we increased the reliability of the model. Consequently, the proposed method promotes the detection accuracy in three of selected datasets in comparison of four recent suitable methods.

Keywords

  • Artificial Neural Network
  • Multi-Objective Genetic Algorithm
  • Ensemble-Classifier
  • Optimal Parameters Regulation
  • XML
  • PDF 648.73 K
  • RIS
  • EndNote
  • Mendeley
  • BibTeX
  • APA
  • MLA
  • HARVARD
  • CHICAGO
  • VANCOUVER
    • Article View: 786
    • PDF Download: 59
Alkut university college journal
Volume 6, Issue 1
volume 6 issue 1
June 2021
Page 66-82
Files
  • XML
  • PDF 648.73 K
Share
Export Citation
  • RIS
  • EndNote
  • Mendeley
  • BibTeX
  • APA
  • MLA
  • HARVARD
  • CHICAGO
  • VANCOUVER
Statistics
  • Article View: 786
  • PDF Download: 59

APA

Kadhim, M. J. , Kh-Madhloom, J. and Abd Ghan, K. (2022). A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach. Alkut university college journal, 6(1), 66-82.

MLA

Kadhim, M. J. , , Kh-Madhloom, J. , and Abd Ghan, K. . "A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach", Alkut university college journal, 6, 1, 2022, 66-82.

HARVARD

Kadhim, M. J., Kh-Madhloom, J., Abd Ghan, K. (2022). 'A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach', Alkut university college journal, 6(1), pp. 66-82.

CHICAGO

M. J. Kadhim , J. Kh-Madhloom and K. Abd Ghan, "A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach," Alkut university college journal, 6 1 (2022): 66-82,

VANCOUVER

Kadhim, M. J., Kh-Madhloom, J., Abd Ghan, K. A Novel Optimal Configuration of Neural Networks by Multi-Objective Genetic Algorithm and Ensemble-classifier approach. Alkut university college journal, 2022; 6(1): 66-82.

  • Home
  • About Journal
  • Editorial Board
  • Submit Manuscript
  • Contact Us
  • Sitemap

News

Newsletter Subscription

Subscribe to the journal newsletter and receive the latest news and updates

©