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

Author

Fen, Dai ; Tiansheng, Hong ; Kun, Zhang ; Ya, Hong

Author_Institution

Key Lab. of Key Technol. on Agric. Machine & Equip., South China Agric. Univ., Guangzhou, China

Volume

2

fYear

2010

fDate

11-12 May 2010

Firstpage

781

Lastpage

783

Abstract

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 500 nm to 1000 nm. 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.

Keywords

agricultural products; backpropagation; chemical engineering computing; chemical products; food products; infrared spectroscopy; neural nets; nondestructive testing; principal component analysis; BP artificial neural network; clustering; longan surface; near infrared spectroscopy; nondestructive fruit surface pesticide residue detection; principal component analysis; slathered pesticides trichlorfon; spectra data; wavelength 500 nm to 1000 nm; wavelength range; Artificial neural networks; Chemical industry; Data analysis; Educational technology; Infrared detectors; Infrared spectra; Principal component analysis; Spectroscopy; Spraying; Variable speed drives; artificial neural network (ANN); longan; near infrared spectroscopy; pesticide residue; principal component analysis (PCA);

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on

Conference_Location

Changsha

Print_ISBN

978-1-4244-7279-6

Electronic_ISBN

978-1-4244-7280-2

Type

conf

DOI

10.1109/ICICTA.2010.477

Filename

5522639