Annals of Mathematical Modeling
Vol. 3 No. 1 (2023)

Lung cancer classification based on support vector machine-recursive feature elimination and artificial bee colony

Alhadi Bustamam (Universitas Indonesia)
Zuherman Rustam (Universitas Indonesia)
Selly A. A. K (Universitas Indonesia)
Nyoman A. Wibawa (Universitas Indonesia)
Devvi Sarwinda (Universitas Indonesia)
Nadya Asanul Husna (Universitas Indonesia)

Article Info

Publish Date
01 Jul 2023


Early detection of cancerous cells can increase survival rates for patients by more than 97%. Microarray data, used for cancer classification, are comp osed of many thousands of features and from tens to hundreds of instances. Handling these huge datasets is the most imp ortant challenge in data classification. Feature selection or reduction is therefore an essential task in data classification. We prop ose a cancer diagnostic to ol using a supp ort vector machine for classifier and feature selection. First, we use supp ort vector machine-recursive feature elimination to prefilter the genes. This was enhanced with the artificial b ee colony algorithm. We ran four simulations using Ontario and Michigan lung cancer datasets. This approach provides higher classification accuracy than those without feature selection, supp ort vector machine-recursive feature elimination, or the artificial b ee colony algorithm. The accuracy of a supp ort vector machine using a feature selection-based recursive feature elimination metho d combined with the artificial b ee colony algorithm reached 98% with 100 b est features for the Michigan lung cancer dataset and 97% with 70 b est features for the Ontario lung cancer dataset. SVM with RFE-ABC as the feature selection metho d gives us an accurate result to diagnose Lung cancer using microarray data.

Copyrights © 2023

Journal Info





Computer Science & IT Mathematics


Annals of Mathematical Modeling is a peer-reviewed open-access journal that publishes educational research articles in mathematics education. Every submitted manuscript will be reviewed by at least two peer-reviewers using the double-blind review method. This journal is published ...