Research Article Open Access

Dimensionality Reduction using Principal Component Analysis for Cancer Detection based on Microarray Data Classification

Adiwijaya1, Untari N. Wisesty1, E. Lisnawati1, A. Aditsania1 and Dana S. Kusumo1
  • 1 Telkom University, Indonesia

Abstract

Cancer is one of the most deadly diseases in the world. The International Agency for Research on Cancer (IARC) noted 14.1 million new cancer cases and 8.2 million deaths from cancer in 2012. In the last few years, DNA microarray technology has increasingly been used to analyze and diagnose cancer. Analysis of gene expression data in the form of microarray allows medical experts to ascertain whether or not a person suffers from cancer. DNA microarray data has a large dimension that can affect the process and accuracy of cancer classification. Therefore, a classification scheme that includes dimension reduction is needed. In this research, a Principal Component Analysis (PCA) dimension reduction method that includes the calculation of variance proportion for eigenvector selection was used. For the classification method, a Support Vector Machine (SVM) and Levenberg-Marquardt Backpropagation (LMBP) algorithm were selected. Based on the tests performed, the classification method using LMBP was more stable than SVM. The LMBP method achieved an average 96.07% accuracy, while the SVM achieved 94.98% accuracy.

Journal of Computer Science
Volume 14 No. 11, 2018, 1521-1530

DOI: https://doi.org/10.3844/jcssp.2018.1521.1530

Submitted On: 12 May 2018 Published On: 15 November 2018

How to Cite: Adiwijaya, Wisesty, U. N., Lisnawati, E., Aditsania, A. & Kusumo, D. S. (2018). Dimensionality Reduction using Principal Component Analysis for Cancer Detection based on Microarray Data Classification. Journal of Computer Science, 14(11), 1521-1530. https://doi.org/10.3844/jcssp.2018.1521.1530

  • 3,028 Views
  • 1,107 Downloads
  • 56 Citations

Download

Keywords

  • Cancer Detection
  • Classification
  • Dimensional Reduction
  • PCA
  • SVM
  • LMBP