Classification and Identification of Pesticide Residues in Cucumber Based on Near Infrared Spectroscopy

Abstract

To explore the feasibility of Near Infrared spectroscopy (NIR) for rapid and nondestructive qualitative identification of pesticide residues in vegetables, this paper presents a qualitative classification and discrimination method based on Support Vector Machine (SVM) with Gaussian Radial Basis Function (RBF). The cucumber with three kinds of pesticide residue levels (no pesticide, standard pesticide residue, severe excess) was used as the research object. The total reflectance NIR spectra of two groups of cucumber were collected after spraying 24 hours and 48 hours of pesticide respectively. First, Principal Component Analysis (PCA) was applied to dimensionality reduction of spectral data. Then normalize the spectrum. Next, the SVM training model based on RBF was established, and then SVM prediction was carried out. The correct recognition rate of the training set was 100%, and the correct prediction rate of the test set was 94.4444% and 95.5556%, respectively. Experiments show that this method is accurate and fast for qualitative classification and identification of pesticide residues in cucumbers with different concentrations, and provides a new idea for rapid non-destructive detection of vegetable pesticide residues.