Deteksi Rasa Buah Jeruk Siam Kintamani Menggunakan SVM dengan Optimasi Algoritma Genetika

Abstract

Kintamani Siam oranges are one of the important commodities in Indonesian agriculture, especially in Bangli Regency, Bali. However, assessing the quality of orange taste still often relies on subjective manual identification. In an effort to enhance objectivity and consistency in assessing orange quality, this study proposes the use of Support Vector Machine (SVM) algorithm optimized with genetic algorithm. The aim of this research is to detect the quality of Kintamani Siam orange taste based on texture characteristics in orange images. Test results show that SVM optimized with genetic algorithm has better accuracy than SVM without optimization. For instance, SVM without optimization yields an accuracy of 0.78, while after optimization with genetic algorithm, the accuracy increases to 0.80. These results indicate the significant potential of genetic algorithm in improving the performance of SVM in detecting the quality of Kintamani Siam orange taste, which can help enhance efficiency and consistency in the orange industry.