Comparison of apple firmness prediction models based on non‐destructive acoustic signal.

This paper aimed to explore the non‐destructive detection of apple firmness based on portable acoustic signals for consumers. The acoustic eigenvalues processed by Time‐domain, Fourier Transform (FT), and Hilbert Huang Transform (HHT) are used to analyse the correlations with apple firmness. The apple firmness prediction models are established through Multiple Linear Regression (MLR) and Artificial Neural Network (ANN). The results proved that the acoustic eigenvalues of wave index form and total energy of 8–9 kHz correlated with apple firmness (P < 0.05), the significant acoustic eigenvalues of sound intensity, amplitude difference, max frame energy, maximum power spectral density, power spectral density characteristics and total energy of 0–1 kHz significantly correlated with apple firmness (P < 0.01). The average relative error of ANN model was significantly lower than that of MLR model (P < 0.05). Compared with Time‐FT, the acoustic eigenvalues processed by a combination of Time‐FT‐HHT possessed a superior effect on the prediction model established by ANN of apple firmness. [ABSTRACT FROM AUTHOR]