Classification of the green tea varieties based on Support Vector Machines using Terahertz spectroscopy

Author

Xi-Ai, Chen ; Guang-Xin, Zhang ; Ping-Jie, Huang ; Di-Bo, Hou ; Xu-Sheng, Kang ; Ze-Kui, Zhou

Author_Institution

Dept. of Control Sci. & Eng., Zhejiang Univ., Hangzhou, China

fYear

2011

fDate

10-12 May 2011

Firstpage

1

Lastpage

5

Abstract

Terahertz time-domain spectroscopy have been applied in research of four different varieties of Chinese green tea, the absorption and refractive Terahertz Spectrum of these tea were got in the range of 0.2 to 1.5 THz. Least Squares Support Vector Machines, Naive Bayes and Back Propagation Artificial Neural Network were applied to achieve Multi-class classification of these four kinds of tea, and the classification results of three algorithms were analyzed in detail. The results shows that support vector machine have better classification results in the experiment. This study demonstrated the feasibility of time-domain Terahertz Spectroscopy for the classification of difference kinds of tea.

Keywords

backpropagation; computerised instrumentation; least squares approximations; pattern classification; support vector machines; terahertz wave spectra; backpropagation artificial neural network; frequency 0.2 THz to 1.5 THz; green tea variety classification; least square support vector machines; terahertz time-domain spectroscopy; Absorption; Artificial neural networks; Classification algorithms; Kernel; Neurons; Spectroscopy; Support vector machines; BP Artificial Neural Network; Green tea; LS-SVM; Naive Bayes classification; Terahertz spectroscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference (I2MTC), 2011 IEEE

Conference_Location

Binjiang

ISSN

1091-5281

Print_ISBN

978-1-4244-7933-7

Type

conf

DOI

10.1109/IMTC.2011.5944018

Filename

5944018