Xplore (2021), Vol. 10, No. 02, 129-139 Xplore: Journal of Statistics DOI: 10.29244/xplore.v10i2. 783 Available at https://journal.stats.id/index.php/xplore e-ISSN: 2655-2744 129 Metode SVM untuk Klasifikasi Enam Tumbuhan Zingiberaceae Menggunakan Variabel Terpilih Hasil Algoritma Genetika * Triyani Oktaria 1 , Utami Dyah Syafitri 2‡ , Mohamad Rafi 3 , Farit M Afendi 4 1 Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi, Indonesia 234 Department of Statistics, IPB University, Indonesia ‡ corresponding author: utamids@apps.ipb.ac.id Copyright © 2021 Triyani Oktaria, Utami Dyah Syafitri, Mohamad Rafi, and Farit M afendi. This is an open-access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Abstract Ginger, red ginger, emprit ginger, elephant ginger, red galangal and white galangal are known to have similar shapes and uses, especially those that are packaged in powder form. In this study, UV-Vis spectrum 200nm-700nm were used as a source of data from chemical compound contain in those plants for classification of the six plants. In this research, the support vector machine (SVM) classification method was used to classify the six plants. Another goal of this study was to identify the wavelengths which give more information about the chemical compound of the plants. The preprocessing procedure was implemented by construction of a genetic algorithm. There were four parameters in the genetic algorithm were set namely population size, crossover probability, mutation, and generation probability. The mutation and the population size influenced significantly the results of SVM. The best result was given by probability of mutation was 10 and population size was 30. The SVM model was better than the SVM model without preprocessing procedure. Keywords: UV-Vis, genetic algorithm, support vector machine, preprocessing. 1. Pendahuluan Beberapa jenis tanaman rimpang seperti jahe emprit (Zingiber officinale var amarum), jahe merah (Z. officinale var rubrum), lempuyang emprit (Z. americans), lempuyang gajah (Z. zerumbet), lengkuas merah (Alpinia purpurata), dan lengkuas putih (A. galanga) memiliki bentuk dan kegunaan yang mirip. Adanya kemiripan bentuk dan kegunaan yang ada pada tanaman rimpang ini dimungkinkan terjadinya substitusi bahan baku antara satu dengan lainnya sehingga sulit dibedakan, misalnya dalam produk obat herbal, terutama jika dikemas dalam bentuk serbuk. Pusat Studi * Received: May 2021; Reviewed: May 2021; Published: May 2021