Rapid determination of acidity index of peanuts by near-infrared spectroscopy technology: Comparing the performance of different near-infrared spectral models

• This study compares the potential of using different NIR spectra to detect acidity index of peanut. • Selecting spectral intervals of FT-NIR and P-NIR spectra by the SiPLS algorithm. • Optimizing characteristic wavelength variables using the BOSS algorithm. • Developing SVM models using the features optimized to determine acidity index of peanuts. This study compared the potential of detection models based on different near-infrared (NIR) spectral characteristics in detecting acidity index of peanut during storage. Fourier transform near-infrared (FT-NIR) spectrometer and portable near-infrared (P-NIR) spectrometer were used to obtain the NIR spectra of peanut samples in different storage periods. The characteristic wavelength intervals of the preprocessed NIR spectra were roughly optimized by synergy interval partial least squares (SiPLS). The bootstrapping soft shrinkage (BOSS) was introduced to further fine select the characteristic wavelength variables, and the support vector machine (SVM) models based on the optimized characteristic wavelength variables were established. The results obtained showed that the SVM model based on the fusion of different NIR spectra wavelength variables obtained the best predictive performance. Root mean square error of prediction set (RMSEP) of the model was 0.73 g·kg −1 , the determination coefficient of prediction set ( R P 2 ) was 0.93, and the residual prediction deviation (RPD) was 3.83. The overall results indicate that although the commercial NIR spectrometer and portable near-infrared spectroscopy system overlap in band, the wavelength variables obtained can play a complementary effect to a certain extent. Therefore, the combination of two instrument data can effectively improve the generalization performance of the detection model.