@inproceedings{d0bcb41a47de490c990fcdf8c04c2050,
title = "Multi-predictor Local Polynomial Regression for Predicting the Acidity Level of Avomango (Gadung Klonal 21)",
abstract = "There are many studies on nondestructive evaluation using Near Infra-Red (NIR) Spectroscopy to determine the quality parameters of mangoes. The predictor variables used for predicting the mango quality parameters in the form of spectra values are generated from NIR spectroscopy. One parameter of the qualities of fruits is the fruit acidity. In general, the lower acidity of mangoes is the riper of the mangoes. Prediction of the acidity level of avomango by using one predictor still produces a high MAPE value of more than 40 percent, so that multi-predictor variables are needed to improve the prediction performance. This study aims to predict the acidity of Avomango (Gadung Klonal 21) by using the multi-predictor local polynomial regression approach and compare it with multiple polynomial regression. This study uses 100 divided samples into two parts, 80 in-sample data, and 20 out-sample data. The results showed that the multi-predictor local polynomial regression model gave highly prediction results for predicting acidity level of Avomango (Gadung Klonal 21) with MAPE value of 6.23 percent that is better than the MAPE value of MPR parametric approach of 10.79 percent.",
author = "Millatul Ulya and Nur Chamidah",
note = "Funding Information: The author would like to thank the Directorate General of Indonesian Higher Education for funding this research through a BPPDN scholarship and also thanks to the owner of the avomango garden, Mr. Sugik, as an expert who has supported this research and provided knowledge about the sensory determination of avomango maturity. Publisher Copyright: {\textcopyright} 2021 American Institute of Physics Inc.. All rights reserved.; International Conference on Mathematics, Computational Sciences and Statistics 2020, ICoMCoS 2020 ; Conference date: 29-09-2020",
year = "2021",
month = feb,
day = "26",
doi = "10.1063/5.0042290",
language = "English",
series = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",
editor = "Cicik Alfiniyah and Fatmawati and Windarto",
booktitle = "International Conference on Mathematics, Computational Sciences and Statistics 2020",
}