Spectrometric Classification of Bamboo Shoot Species by Comparison of Different Machine Learning Methods

The nutrition and quality of bamboo shoots from different species have a large variation, and traditional methods used for the classification of different bamboo shoot species are expensive and time-consuming. Here, the capability of near-infrared reflectance (NIR) spectroscopy to identify bamboo shoot species in a time- and cost-effective manner was examined. The NIR spectra of four bamboo shoot species were collected. Three classification models, a support vector machine (SVM), partial least squares-discriminant analysis (PLSDA), and random forest (RF), were calibrated. Several spectra pre-processing methods and their combination were trained before model calibration for the best classification model collection; each model was run 200 times for the calculation of the prediction error and model stability checking. The SVM model combined with the Det+2nd derivative had the best performance with an overall accuracy of 0.95. The use of less than 16% of the full-length NIR spectra produced a similar high accuracy of 0.91. Eight important regions, 1015, 1135, 1175, 1338, 1380, 1620, 1690, and 1750 nm, were found to be highly related to the classification of bamboo shoots. This study found that NIR spectra combined with SVM methods produced a rapid and non-destructive approach for the classification of bamboo shoot species.