Skip to main content

Classification of Acute Luekemia Using HMLP Network Trained by Genetic Algorithm

Buy Article:

$105.00 + tax (Refund Policy)

Leukemia is a type of cancer that can lead to death. The main problem with the leukemia diagnosis lies in the human error in reading the data analysis and the shortage of hematologists available, to perform the data analysis. Creating a computer-aided diagnosis system is one of the solutions where it can automatically interpret the data so that fast and accurate diagnosis of the disease can be conducted. Recently, most of the researches in the leukemia applied artificial neural network (ANN) for their system seek to classify the blood cells data into normal and abnormal. This study focuses on the automated detection of acute leukemia and it also attempts to classify the disease into Acute Myelogenous Leukemia (AML) and Acute Lymphoblastic Leukemia (ALL). This research utilises a type of neural network (NN) namely Hybrid Multi-layered Perceptron (HMLP) and trained by Genetic Algorithm (GA) to diagnose the data. The data are obtained from blood cells and 31 features are extracted such as size, radius, perimeter, standard deviation (red, green and blue), the mean of the pixels of colour (red, blue, green), second order moments, third order moments and affine moments. These features are inserted into the algorithm to calculate and determine the neural network performance. For the analysis, the data is evaluated using the 5-fold cross validation technique. This research shows that HMLP trained with GA provides a better classification performance with 92.67%, 88.67% and 96.67% of the overall, AML and ALL accuracy respectively.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: Genetic Algorithm; HMLP Network; Leukemia Classification

Document Type: Research Article

Affiliations: 1: School of Computing, College of Art and Scinces, Universiti Utara Malaysia (UUM), Sintok, Malaysia 2: Faculty of Electrical Engineering, Universiti Teknologi MARA Pulau Pinang, 13500 Permatang Pauh, P. Pinang, Malaysia 3: School of Mechatronics Engineering, Universiti Malaysia Perlis, 02600 Pauh, Perlis, Malaysia 4: Department of Hematology, Universiti Sains Malaysia, Kubang Kerian, Kelantan, Malaysia

Publication date: 01 April 2017

More about this publication?
  • ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more