Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score

Z. Rustam; Indira Primasari; D. Widya

doi:10.1063/1.5064231

Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score

Z. Rustam, Indira Primasari, D. Widya

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

8 Citations (Scopus)

Abstract

Cancer is one of the most deadly diseases for humans. According to the WHO (2015), cancer is the causes of the death number two in the world by 13 % after cardiovascular disease. Cancer often causes death if treatment is too late. Therefore, early detection of cancer is necessary to avoid the spread of cancer. High-dimensional medical data is one of the obstacles to the application of machine learning techniques due to a negative effect on the process of analysis. Therefore, the selection features required to increase performance in the detection of cancer. This paper focuses on the comparison of feature selection on cancer data. We use Genetic Algorithm and Laplacian Score for cancer gene selection of features, coupled with the Support Vectors Machines for cancer classification. The results will show that Genetic Algorithm gives the best accuracy with the percentage of 98.69 % only using 40 features.

Original language	English
Title of host publication	Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017
Editors	Ratna Yuniati, Terry Mart, Ivandini T. Anggraningrum, Djoko Triyono, Kiki A. Sugeng
Publisher	American Institute of Physics Inc.
ISBN (Electronic)	9780735417410
DOIs	https://doi.org/10.1063/1.5064231
Publication status	Published - 22 Oct 2018
Event	3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017 - Bali, Indonesia Duration: 26 Jul 2017 → 27 Jul 2017

Publication series

Name	AIP Conference Proceedings
Volume	2023
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017
Country/Territory	Indonesia
City	Bali
Period	26/07/17 → 27/07/17

Keywords

cancer
classification
genetic algorithm
laplacian score
support vectors machines

Access to Document

10.1063/1.5064231

Cite this

Rustam, Z., Primasari, I., & Widya, D. (2018). Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score. In R. Yuniati, T. Mart, I. T. Anggraningrum, D. Triyono, & K. A. Sugeng (Eds.), Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017 [020234] (AIP Conference Proceedings; Vol. 2023). American Institute of Physics Inc.. https://doi.org/10.1063/1.5064231

Rustam, Z. ; Primasari, Indira ; Widya, D. / Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score. Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017. editor / Ratna Yuniati ; Terry Mart ; Ivandini T. Anggraningrum ; Djoko Triyono ; Kiki A. Sugeng. American Institute of Physics Inc., 2018. (AIP Conference Proceedings).

@inproceedings{e048c71472f44db4a9d1d76dbdd36aa2,

title = "Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score",

abstract = "Cancer is one of the most deadly diseases for humans. According to the WHO (2015), cancer is the causes of the death number two in the world by 13 % after cardiovascular disease. Cancer often causes death if treatment is too late. Therefore, early detection of cancer is necessary to avoid the spread of cancer. High-dimensional medical data is one of the obstacles to the application of machine learning techniques due to a negative effect on the process of analysis. Therefore, the selection features required to increase performance in the detection of cancer. This paper focuses on the comparison of feature selection on cancer data. We use Genetic Algorithm and Laplacian Score for cancer gene selection of features, coupled with the Support Vectors Machines for cancer classification. The results will show that Genetic Algorithm gives the best accuracy with the percentage of 98.69 % only using 40 features.",

keywords = "cancer, classification, genetic algorithm, laplacian score, support vectors machines",

author = "Z. Rustam and Indira Primasari and D. Widya",

note = "Funding Information: This research is supported by PITTA 2017 Universitas Indonesia research grant with contract number 706/UN2.R3.1/HKP.05.00/2017. Publisher Copyright: {\textcopyright} 2018 Author(s).; 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017 ; Conference date: 26-07-2017 Through 27-07-2017",

year = "2018",

month = oct,

day = "22",

doi = "10.1063/1.5064231",

language = "English",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics Inc.",

editor = "Ratna Yuniati and Terry Mart and Anggraningrum, {Ivandini T.} and Djoko Triyono and Sugeng, {Kiki A.}",

booktitle = "Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017",

}

Rustam, Z, Primasari, I & Widya, D 2018, Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score. in R Yuniati, T Mart, IT Anggraningrum, D Triyono & KA Sugeng (eds), Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017., 020234, AIP Conference Proceedings, vol. 2023, American Institute of Physics Inc., 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017, Bali, Indonesia, 26/07/17. https://doi.org/10.1063/1.5064231

Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score. / Rustam, Z.; Primasari, Indira ; Widya, D.
Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017. ed. / Ratna Yuniati; Terry Mart; Ivandini T. Anggraningrum; Djoko Triyono; Kiki A. Sugeng. American Institute of Physics Inc., 2018. 020234 (AIP Conference Proceedings; Vol. 2023).

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

TY - GEN

T1 - Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score

AU - Rustam, Z.

AU - Primasari, Indira

AU - Widya, D.

PY - 2018/10/22

Y1 - 2018/10/22

N2 - Cancer is one of the most deadly diseases for humans. According to the WHO (2015), cancer is the causes of the death number two in the world by 13 % after cardiovascular disease. Cancer often causes death if treatment is too late. Therefore, early detection of cancer is necessary to avoid the spread of cancer. High-dimensional medical data is one of the obstacles to the application of machine learning techniques due to a negative effect on the process of analysis. Therefore, the selection features required to increase performance in the detection of cancer. This paper focuses on the comparison of feature selection on cancer data. We use Genetic Algorithm and Laplacian Score for cancer gene selection of features, coupled with the Support Vectors Machines for cancer classification. The results will show that Genetic Algorithm gives the best accuracy with the percentage of 98.69 % only using 40 features.

AB - Cancer is one of the most deadly diseases for humans. According to the WHO (2015), cancer is the causes of the death number two in the world by 13 % after cardiovascular disease. Cancer often causes death if treatment is too late. Therefore, early detection of cancer is necessary to avoid the spread of cancer. High-dimensional medical data is one of the obstacles to the application of machine learning techniques due to a negative effect on the process of analysis. Therefore, the selection features required to increase performance in the detection of cancer. This paper focuses on the comparison of feature selection on cancer data. We use Genetic Algorithm and Laplacian Score for cancer gene selection of features, coupled with the Support Vectors Machines for cancer classification. The results will show that Genetic Algorithm gives the best accuracy with the percentage of 98.69 % only using 40 features.

KW - cancer

KW - classification

KW - genetic algorithm

KW - laplacian score

KW - support vectors machines

UR - http://www.scopus.com/inward/record.url?scp=85056116055&partnerID=8YFLogxK

U2 - 10.1063/1.5064231

DO - 10.1063/1.5064231

M3 - Conference contribution

AN - SCOPUS:85056116055

T3 - AIP Conference Proceedings

BT - Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017

A2 - Yuniati, Ratna

A2 - Mart, Terry

A2 - Anggraningrum, Ivandini T.

A2 - Triyono, Djoko

A2 - Sugeng, Kiki A.

PB - American Institute of Physics Inc.

T2 - 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017

Y2 - 26 July 2017 through 27 July 2017

ER -

Rustam Z, Primasari I , Widya D. Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score. In Yuniati R, Mart T, Anggraningrum IT, Triyono D, Sugeng KA, editors, Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017, ISCPMS 2017. American Institute of Physics Inc. 2018. 020234. (AIP Conference Proceedings). doi: 10.1063/1.5064231

Classification of cancer data based on support vectors machines with feature selection using genetic algorithm and Laplacian score

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this