Evaluate the performance of SVM kernel functions for multiclass cancer classification

Mohd Hatta, Noramalina and Ali Shah, Zuraini and Kasim, Shahreen (2020) Evaluate the performance of SVM kernel functions for multiclass cancer classification. International Journal of Data Science, 1 (1). pp. 37-41. ISSN 2722-2039

Text AJ 2020 (249).pdf Restricted to Registered users only Download (80kB) | Request a copy

Abstract

Multiclass cancer classification is basically one of the challenging fields in machine learning which a fast growing technology that use human behaviour as examples. Supervised classification such Support Vector Machine (SVM) has been used to classify the dataset on classification by its own function and merely known as kernel function. Kernel function has stated to have a problem especially in selecting their best kernels based on a specific datasets and tasks. Besides, there is an issue stated that the kernels function have a high impossibility to distribute the data in straight line. Here, three basic kernel functions was used and tested with selected dataset and they are linear kernel, polynomial kernel and Radial Basis Function (RBF) kernel function. The three kernels were tested by different dataset to gain the accuracy. For a comparison, this study conducting a test by with and without feature selection in SVM classification kernel function since both tests will give different result and thus give a big meaning to the study.

Item Type:	Article
Uncontrolled Keywords:	multiclass cancer classification; support vector machine; kernel functions; machine learning; SVM classification
Subjects:	R Medicine > R Medicine (General) > R855-855.5 Medical technology
Divisions:	Faculty of Computer Science and Information Technology > Department of Web Technology
Depositing User:	Miss Afiqah Faiqah Mohd Hafiz
Date Deposited:	27 Jan 2022 06:24
Last Modified:	27 Jan 2022 06:24
URI:	http://eprints.uthm.edu.my/id/eprint/6239

Actions (login required)

View Item