Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.

Original languageEnglish
Pages (from-to)1312-1329
Number of pages18
JournalInternational Journal of Systems Science
Volume47
Issue number6
DOIs
Publication statusPublished - 25 Apr 2016

Fingerprint

Harmony Search
Feature Selection
Search Algorithm
Feature extraction
Genes
Gene
Uncertainty
Microarrays
Wrapper
Microarray Data
Cancer
Filter
Gene Selection
Microarray
Isolation
Bioelectric potentials
Tumor
Bioinformatics
Diagnostics
Decision Making

Keywords

  • feature selection
  • filter
  • harmony search
  • microarray
  • wrapper

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications

Cite this

Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm. / Shreem, Salam Salameh; Abdullah, Salwani; Ahmad Nazri, Mohd Zakree.

In: International Journal of Systems Science, Vol. 47, No. 6, 25.04.2016, p. 1312-1329.

Research output: Contribution to journalArticle

@article{791a6914a1114739a1986bc8092843a5,
title = "Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm",
abstract = "Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.",
keywords = "feature selection, filter, harmony search, microarray, wrapper",
author = "Shreem, {Salam Salameh} and Salwani Abdullah and {Ahmad Nazri}, {Mohd Zakree}",
year = "2016",
month = "4",
day = "25",
doi = "10.1080/00207721.2014.924600",
language = "English",
volume = "47",
pages = "1312--1329",
journal = "International Journal of Systems Science",
issn = "0020-7721",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm

AU - Shreem, Salam Salameh

AU - Abdullah, Salwani

AU - Ahmad Nazri, Mohd Zakree

PY - 2016/4/25

Y1 - 2016/4/25

N2 - Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.

AB - Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.

KW - feature selection

KW - filter

KW - harmony search

KW - microarray

KW - wrapper

UR - http://www.scopus.com/inward/record.url?scp=84995360048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995360048&partnerID=8YFLogxK

U2 - 10.1080/00207721.2014.924600

DO - 10.1080/00207721.2014.924600

M3 - Article

AN - SCOPUS:84995360048

VL - 47

SP - 1312

EP - 1329

JO - International Journal of Systems Science

JF - International Journal of Systems Science

SN - 0020-7721

IS - 6

ER -