Detection of hollow heart disorder in watermelons using vibrational test and machine learning

Abstract

The presence of internal voids in watermelons has an impact on the costs of producers and on consumer confidence. Various studies have shown that the vibrational parameters of the fruit are related to maturity, quality and the existence of internal defects. A method for the detection of internal voids in seedless watermelons based on vibrational parameters obtained in impact hammer tests and machine learning is presented. After a statistical study of the test results, the frequency of the first peak of the vibrational response and the density of the watermelon are selected as predictors to be used in the classification algorithms. The accuracy of detecting hollow watermelons increases if firmness estimator is introduced as a predictor. Probabilities of success above 89% in the detection of internal voids have been achieved using different classification algorithm.