Friday 29th of March 2024
 

Bagging Support Vector Machines for Leukemia Classification


Gokmen Zararsiz, Ferhan Elmali and Ahmet Ozturk

Leukemia is one of the most common cancer type, and its diagnosis and classification is becoming increasingly complex and important. Here, we used a gene expression dataset and adapted bagging support vector machines (bSVM) for leukemia classification. bSVM trains each SVM seperately using bootstrap technique, then aggregates the performances of each SVM by majority voting. bSVM showed accuracy between 87.5% - 92.5%, area under ROC curve between 98.0% - 99.2%, F-measure between 90.5% - 92.7% and outperformed single SVM and other classification methods. We also compared our results with other study results which used the same dataset for leukemia classification. Experimental results revealed that bSVM showed the best performance and can be used as a biomarker for the diagnose of leukemia disease.

Keywords: Bagging, Leukemia diagnosis, Microarray, Support vector machines

Download Full-Text


ABOUT THE AUTHORS

Gokmen Zararsiz
Gokmen Zararsiz was born in 1986 at Bursa, Turkey. He has acquired his MSc Degree in Department of Biostatistics and Medical Informatics in Erciyes University. He has 5 published international/national articles and over 10 articles under review in international/national journals. He has participated to many congress and symposiums and have about 40 conference proceedings. Also, he got 2 oral and 2 poster presentation awards in these congress. He is a member of many associations including International Society for Computational Biology (ISCB) and Statistics Without Borders (SWB). He is now writing a book chapter about statistical analysis of miRNA datasets, which will be published by Springer, in “Methods in Molecular Biology”. His area of interest is biostatistics, data mining, machine learning, bioinformatics and gamlss modelling.

Ferhan Elmali
Ferhan Elmali was born in 1979 at Kiel, Germany. He has acquired his MSc and PhD degrees in Department of Biostatistics in Eskisehir Osmangazi University. He has many published international/national articles. He has participated to many congress and symposiums and have many conference proceedings. His working areas are survival analysis, ROC analysis, regression analysis and exact tests.

Ahmet Ozturk
Ahmet Ozturk was born in 1967 at Kayseri, Tukey. He has acquired his MSc degree in Department of Biostatistics and Medical Informatics in Erciyes University and his PhD degree in same department in Eskisehir Osmangazi University. He has many published international/national articles. His working areas are constructing children growth curves, gamlss modelling and multivariate statistics.


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »