WCSE

Support Vector Machine OVA-RFE Approach for Finding the Significant Plants of Jamu

Abstract— Jamu medicines are popular traditional medicines from Indonesia. Jamu made from a mixture of several plants. Jamu formula are based on empirical data and personal experiences, so it needs to systemize the formulation of Jamu and develop basic scientific principles of Jamu for Indonesian Healthcare System. The purpose of this research is to find the Jamu plants that have the most significant effect on the diseases. We proposed a feature selection approach using SVM OVA-RFE. We also added the previous Jamu feature selection research using K-Means and PLS-DA for comparison. The SVM OVA-RFE method successfully reduced the data dimension into 3085 of Jamu samples and 238 species of plants. The result from SVM classification using OVA-RFE outperform the previous researches.

Index Terms— Jamu, feature selection, machine learning, recursive feature elimination, SVM OVA-RFE.

Aries Fitriawan, Ito Wasito
Faculty of Computer Science, Universitas Indonesia, INDONESIA
Aries Fitriawan, Wisnu Ananta Kusuma
Department of Computer Science, Faculty of Mathematics and Natural Sciences, Bogor Agricultural University, INDONESIA
Rudi Heryanto
Department of Chemistry, Faculty of Mathematics and Natural Sciences, Bogor Agricultural University, INDONESIA
Rudi Heryanto
Biopharmaca Research Center, Bogor Agricultural University, INDONESIA

[Download]

Cite: Aries Fitriawan, Ito Wasito, Wisnu Ananta Kusuma, Rudi Heryanto, "Support Vector Machine OVA-RFE Approach for Finding the Significant Plants of Jamu," Proceedings of 2016 6th International Workshop on Computer Science and Engineering, pp. 650-654, Tokyo, 17-19 June, 2016.