Nondestructive Detection of Pesticide Residue on Longan Surface Based on Near Infrared Spectroscopy

摘要

In this research, nondestructive detection of a slathered pesticides trichlorfon on longan surface based on near infrared spectroscopy was studied. Firstly, principal component analysis (PCA) was applied to analyze the spectra data within the wavelength range from 500nm to 1000nm. Satisfied results were achieved from clustering based on the scores of PC1 and PC2. Then a BP artificial neural network (ANN) was built to detect the pesticide residue with the scores of PC1 and PC2 as inputs. The results indicated that the ratio of correct detection was 93%. This study may provide a novel way for fast and nondestructive fruit surface pesticide residue detection.