Feature Selection Techniques for Cancer Classification applied to Microarray Data: A survey
In multidimensional microarrays, data that collect gene expression profiles that fulfill the state of the cell at the molecular level. Feature selection and extraction have become an obvious need for the analysis of this microarray. There are many different methods for selecting and extracting attri...
Saved in:
Published in | 2019 International Conference on Intelligent Systems and Advanced Computing Sciences (ISACS) pp. 1 - 8 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.12.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | In multidimensional microarrays, data that collect gene expression profiles that fulfill the state of the cell at the molecular level. Feature selection and extraction have become an obvious need for the analysis of this microarray. There are many different methods for selecting and extracting attributes, and they are widely used. One of the serious tasks is to learn how to extract useful information from huge microarrays datasets with complex relationships between different genes. These methods are aimed at removing excess and irrelevant traits and extruding marker genes that effectively maintain classification accuracy. This report gives an overview of the various ways of performing dimensional reduction methods that were used in these microarrays to select important features and presents a comparison between them. The advantages and disadvantages of several methods are described in order to show an obvious idea of when to use each of them to save computational time and resources. |
---|---|
DOI: | 10.1109/ISACS48493.2019.9068865 |