Predicting the sweetness level of avomango (Gadung Klonal 21) using multi-predictor local polynomial regression

Abstract

One of the mango’s maturity aspects is the sweetness of the fruits. Mature Avomango has a high degree of sweetness, characterized by a high total soluble solids (TSS) content. Currently, many non-destructive tests are 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 the level of Avomangos sweetness by using a multi-predictor local polynomial regression approach and compare it with multiple polynomial regression. In this study, we use 120 samples of Avomango divided into two parts, 100 as training data and 20 as testing data. The multi-predictor local polynomial regression has better performance with the value mean absolute percentage error (MAPE) is 8.554% that categorized as a highly accurate prediction for predicting Avomangos sweetness level.

Mango quality prediction based on near-infrared spectroscopy using multi-predictor local polynomial regression modeling

“…All treatment spectra revealed that the best predictive model used MLPR, with the highest R 2 value and the lowest RMSE, MSE, and MAPE values compared with the other regression methods. This is consistent with the results of the previous studies by Ulya et al 16,26 The order of prediction performance based on the regression method from the best is MLPR, SVMR and KPLSR. MLPR is a novel method for predicting the internal quality of fruits developed by Ulya et al 16,26 This study confirms that the MLPR method can produce a robust predictive model for determining the internal quality of mangoes; MLPR (nonparametric regression) has predictive performance with a lower MAPE value than that of the MPR (parametric regression).…”

“…This is consistent with the results of the previous studies by Ulya et al 16,26 The order of prediction performance based on the regression method from the best is MLPR, SVMR and KPLSR. MLPR is a novel method for predicting the internal quality of fruits developed by Ulya et al 16,26 This study confirms that the MLPR method can produce a robust predictive model for determining the internal quality of mangoes; MLPR (nonparametric regression) has predictive performance with a lower MAPE value than that of the MPR (parametric regression). Table 2 proves that SVMR outperforms KPLSR with higher R 2 values, lower MSE, RMSE and MAPE.…”

“…MLPR for predicting the internal quality of fruits was proposed by Ulya et al 16 The prediction was obtained using a nonparametric regression approach based on a local polynomial estimator with one response variable and multiple predictors. The MLPR model has a response variable y that depends on the sum of some functions of the predictor variable x and can be written as follows.…”

“…22,23 The prediction of the sweetness level of mangoes has been reported by Ulya, Chamidah, and Saifudin. 16 These studies report that nonparametric regression based on local polynomial estimators, particularly, multiple polynomial regression (MPR), results in a better predictive model than the parametric regression approach.…”