Next Article in Journal
Machine Learning Models for Error Detection in Metagenomics and Polyploid Sequencing Data
Next Article in Special Issue
eHealth and Artificial Intelligence
Previous Article in Journal
A Review on Energy Consumption Optimization Techniques in IoT Based Smart Building Environments
Previous Article in Special Issue
Glomerular Filtration Rate Estimation by a Novel Numerical Binning-Less Isotonic Statistical Bivariate Numerical Modeling Method
Article Menu

Export Article

Open AccessArticle
Information 2019, 10(3), 109; https://doi.org/10.3390/info10030109

An Experimental Comparison of Feature-Selection and Classification Methods for Microarray Datasets

Department of Electrical and Information Engineering “Maurizio Scarano”, University of Cassino and Southern Lazio, 03043 Cassino (FR), Italy
*
Author to whom correspondence should be addressed.
Received: 29 January 2019 / Revised: 3 March 2019 / Accepted: 5 March 2019 / Published: 10 March 2019
(This article belongs to the Special Issue eHealth and Artificial Intelligence)
Full-Text   |   PDF [253 KB, uploaded 10 March 2019]

Abstract

In the last decade, there has been a growing scientific interest in the analysis of DNA microarray datasets, which have been widely used in basic and translational cancer research. The application fields include both the identification of oncological subjects, separating them from the healthy ones, and the classification of different types of cancer. Since DNA microarray experiments typically generate a very large number of features for a limited number of patients, the classification task is very complex and typically requires the application of a feature-selection process to reduce the complexity of the feature space and to identify a subset of distinctive features. In this framework, there are no standard state-of-the-art results generally accepted by the scientific community and, therefore, it is difficult to decide which approach to use for obtaining satisfactory results in the general case. Based on these considerations, the aim of the present work is to provide a large experimental comparison for evaluating the effect of the feature-selection process applied to different classification schemes. For comparison purposes, we considered both ranking-based feature-selection techniques and state-of-the-art feature-selection methods. The experiments provide a broad overview of the results obtainable on standard microarray datasets with different characteristics in terms of both the number of features and the number of patients. View Full-Text
Keywords: feature-selection; feature ranking; classification methods; DNA microarrays feature-selection; feature ranking; classification methods; DNA microarrays
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Cilia, N.D.; De Stefano, C.; Fontanella, F.; Raimondo, S.; Scotto di Freca, A. An Experimental Comparison of Feature-Selection and Classification Methods for Microarray Datasets. Information 2019, 10, 109.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Information EISSN 2078-2489 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top