High dimensional microarray data classification using correlation based feature selection

Abid Hassan; Md Akhtaruzzaman Adnan

doi:10.1109/ICoBE.2012.6179029

High dimensional microarray data classification using correlation based feature selection

Abid Hassan, Md Akhtaruzzaman Adnan

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

7 Citations (Scopus)

Abstract

Analyzing DNA microarray data pose a serious challenge because of their large number of features (genes) and relatively small number of samples. Extracting features, those have predictive capability for classifying these huge datasets
demands appropriate approaches like feature reduction and identifying optimal set of genes. In this paper along with conventional statistical methods like filtering the dataset to reduce the number of features, one additional approach of evaluating correlation between the classes for each feature is performed. Proposed approach yields higher classification accuracy for both Acute Lymphoblastic (ALL) and High Grade Glioma cancer dataset than using only traditional statistical filtering methods.

Original language	English
Title of host publication	2012 International Conference on Biomedical Engineering (ICoBE)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	319-321
Number of pages	3
ISBN (Electronic)	9781457719912
ISBN (Print)	9781457719905
DOIs	https://doi.org/10.1109/ICoBE.2012.6179029
Publication status	Published - 27 Feb 2012
Externally published	Yes
Event	2012 International Conference on Biomedical Engineering (ICoBE) - Penang, Malaysia Duration: 27 Feb 2012 → 28 Feb 2012

Conference

Conference	2012 International Conference on Biomedical Engineering (ICoBE)
Country/Territory	Malaysia
City	Penang
Period	27/02/12 → 28/02/12

Keywords

DNA microarray data
correlation
feature selection
classification

Access to Document

10.1109/ICoBE.2012.6179029

Cite this

@inproceedings{3216b31c451d44a4828a59f39e076ac4,

title = "High dimensional microarray data classification using correlation based feature selection",

abstract = "Analyzing DNA microarray data pose a serious challenge because of their large number of features (genes) and relatively small number of samples. Extracting features, those have predictive capability for classifying these huge datasetsdemands appropriate approaches like feature reduction and identifying optimal set of genes. In this paper along with conventional statistical methods like filtering the dataset to reduce the number of features, one additional approach of evaluating correlation between the classes for each feature is performed. Proposed approach yields higher classification accuracy for both Acute Lymphoblastic (ALL) and High Grade Glioma cancer dataset than using only traditional statistical filtering methods. ",

keywords = "DNA microarray data, correlation, feature selection, classification",

author = "Abid Hassan and Adnan, {Md Akhtaruzzaman}",

year = "2012",

month = feb,

day = "27",

doi = "10.1109/ICoBE.2012.6179029",

language = "English",

isbn = "9781457719905",

pages = "319--321",

booktitle = "2012 International Conference on Biomedical Engineering (ICoBE)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2012 International Conference on Biomedical Engineering (ICoBE) ; Conference date: 27-02-2012 Through 28-02-2012",

}

Hassan, A & Adnan, MA 2012, High dimensional microarray data classification using correlation based feature selection. in 2012 International Conference on Biomedical Engineering (ICoBE). Institute of Electrical and Electronics Engineers (IEEE), pp. 319-321, 2012 International Conference on Biomedical Engineering (ICoBE) , Penang, Malaysia, 27/02/12. https://doi.org/10.1109/ICoBE.2012.6179029

High dimensional microarray data classification using correlation based feature selection. / Hassan, Abid; Adnan, Md Akhtaruzzaman.
2012 International Conference on Biomedical Engineering (ICoBE). Institute of Electrical and Electronics Engineers (IEEE), 2012. p. 319-321.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - High dimensional microarray data classification using correlation based feature selection

AU - Hassan, Abid

AU - Adnan, Md Akhtaruzzaman

PY - 2012/2/27

Y1 - 2012/2/27

N2 - Analyzing DNA microarray data pose a serious challenge because of their large number of features (genes) and relatively small number of samples. Extracting features, those have predictive capability for classifying these huge datasetsdemands appropriate approaches like feature reduction and identifying optimal set of genes. In this paper along with conventional statistical methods like filtering the dataset to reduce the number of features, one additional approach of evaluating correlation between the classes for each feature is performed. Proposed approach yields higher classification accuracy for both Acute Lymphoblastic (ALL) and High Grade Glioma cancer dataset than using only traditional statistical filtering methods.

AB - Analyzing DNA microarray data pose a serious challenge because of their large number of features (genes) and relatively small number of samples. Extracting features, those have predictive capability for classifying these huge datasetsdemands appropriate approaches like feature reduction and identifying optimal set of genes. In this paper along with conventional statistical methods like filtering the dataset to reduce the number of features, one additional approach of evaluating correlation between the classes for each feature is performed. Proposed approach yields higher classification accuracy for both Acute Lymphoblastic (ALL) and High Grade Glioma cancer dataset than using only traditional statistical filtering methods.

KW - DNA microarray data

KW - correlation

KW - feature selection

KW - classification

U2 - 10.1109/ICoBE.2012.6179029

DO - 10.1109/ICoBE.2012.6179029

M3 - Conference proceeding contribution

SN - 9781457719905

SP - 319

EP - 321

BT - 2012 International Conference on Biomedical Engineering (ICoBE)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2012 International Conference on Biomedical Engineering (ICoBE)

Y2 - 27 February 2012 through 28 February 2012

ER -

High dimensional microarray data classification using correlation based feature selection

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this