PRINCIPAL COMPONENT DAN K-MEANS CLUSTER ANALYSIS UNTUK DATA SPEKTRUM BLACK TEA GRADES GUNA PENILAIAN KUALITAS ALTERNATIF

Aditya Toraismaya (Program Studi Matematika, Universitas Kristen Satya Wacana)
Leopoldus Ricky Sasongko (Program Studi Matematika, Universitas Kristen Satya Wacana)
Ferdy Semuel Rondonuwu (Program Studi Matematika, Universitas Kristen Satya Wacana)

Journal of Fundamental Mathematics and Applications (JFMA)
Vol 3, No 2 (2020)

The aim of this article is to apply the method to measure or evaluate the sampling quality of black tea in determining its category or class based on the spectrum of the sampled data. The number of the spectrum of the variable of data reduced by the Principal Components Analysis (PCA) method becomes a new variable that will be classified later by using K-Means Clustering method. This research use 120 sample of tea from Fanning II (F-II), Pekoe Fanning (PFANN), and Broken Orange Pekoe Fannings (BOPF) with 90 sample used for training and 30 sample used for validation. The method and the analysis used in this research gave effective and efficient performance in measuring/evaluating the quality of the black tea sample to determine its class as it showed that the accuracy of K-Means Clustering results is larger than 50%.