Predicting Sweetness Level of Avomango (Gadung Klonal 21) Using Local Polynomial Regression Approach
Millatul Ulya(a), Nur Chamidah(b*)

a) Ph.D. Student of Mathematics and Natural Sciences Study Program, Faculty of Science and Technology, Airlangga University
Jl. Mulyorejo, Surabaya, Indonesia
a) Study Program of Agroindustrial Technology, Faculty of Agriculture, University of Trunojoyo Madura
Jl. Raya Telang, Kamal, Bangkalan, Indonesia
b) Department of Mathematics, Faculty of Science and Technology, Airlangga University
Jl. Mulyorejo, Surabaya, Indonesia

Abstract

One aspect of the mangos maturity is the fruits sweetness. Mature Avomango has a high degree of sweetness, characterized by a high total soluble solid (TSS) content. Currently, there are many non - destructive tests using Near Infra-Red (NIR) spectroscopy to find out the TSS content. NIR spectroscopy generates spectra data which can be used as predictors to predict Avomangos sweetness level. This study aims to predict Avomangos level of sweetness by using multipredictor local polynomial nonparametric regression approach. In this study, we use 100 samples of Avomango divided into two parts, 80 as in-samples and 20 as out-samples. Based on multipredictor local polynomial regression estimation result, we obtain mean square error (MSE) and mean absolute percentage error (MAPE) are 0.239 and 3.911%, respectively. It means that the multipredictor local polynomial estimator has been suitable to use for predicting Avomangos sweetness level.

Keywords: predicting, sweetness level of Avomango, Gadung Klonal 21, multi-predictors local polynomial.

Topic: AGRICULTURAL ENGINEERING