文章基本信息

标题：An Experimental Comparison of Feature-Selection and Classification Methods for Microarray Datasets
本地全文：下载
作者：Nicole Dalia Cilia ; Nicole Dalia Cilia ; Claudio De Stefano 等
期刊名称：Information
电子版ISSN：2078-2489
出版年度：2019
卷号：10
期号：3
页码：109
DOI：10.3390/info10030109
出版社：MDPI Publishing
摘要：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.
关键词：feature-selection; feature ranking; classification methods; DNA microarrays feature-selection ; feature ranking ; classification methods ; DNA microarrays