Detection of XinyangMaojian Green Tea Quality and Age by Electronic Nose

Abstract:

In this work, the capacity of an electronic nose (E-nose, PEN2) to classify tea quality grades is investigated. Three tea groups with different quality grades were harvested at different times. Principal component analysis (PCA) and artificial neural network (ANN) were applied to identify the different tea samples. PCA provided perfect classification of tea quality grades. In the analysis of age, six groups of XinyangMaojian green tea were distinguished completely by PCA. The results of ANN analysis gave a high percentage of correct discrimination of green tea samples. The correct identification rates of the training and testing data were 98.6% and 83%, respectively, for three grades of green tea samples harvested in 2009. The correct identification rates of the training and testing data were 100% and 87.8%, respectively, for three grades of green tea samples harvested in 2010. In the analysis of age, the correct discrimination percentages for six groups of XinyangMaojian green tea were 99.4% and 88.9% for training and testing data, respectively. These results indicate that the electronic nose could be successfully used for the detection of teas of different quality grades and ages.

• Periodical: Advanced Materials Research (Volumes 239-242)
• Pages: 2096-2100
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.239-242.2096
• Online since: May 2011
• Authors: Hong Mei Zhang, Ming Xun Chang, Yong Chang Yu, Hui Tian, Yu Qing He, Xin Chang Chen
• Keywords: Artificial Neural Network (ANN), Electronic Nose, Green Tea, Principal Component Analysis (PCA), Sensor Array

References

[1] H.C. Yu, J.Wang, H.M. Zhang, Y.Yu, C.Yao: Sensors and Actuators B vol.128(2008), p.455–461.

[2] A.P. Bhondekar, M. Dhiman, A.Sharma, A. Bhakta, A. Ganguli, S.S. Bari, R.Vig, P. Kapur, M.L. Singla: Sensors and Actuators B, vol.148(2010), pp.601-609.

DOI: 10.1016/j.snb.2010.05.053

[3] Z.Y. Yang, F. Dong, K. Shimizu, T. Kinoshita, M. Kanamori, A. Morita, N.Watanabe: Journal of Food Engineering, vol.92(2009), p.312–316.

[4] S. Buratti, S.Benedetti, M.Scampicchio, E.C. Pangerod: Analytica Chimica Acta, vol.525(2004), p.133–139

DOI: 10.1016/j.aca.2004.07.062

[5] P.M. Marti, O. Busto, J. Guasch: Journal of Chromatography A, vol.1057(2004),p.211–217.

[6] A.H. Gomez, G.X. Hu, J. Wang, A.G. Pereira: Computers and Electronics in Agriculture vol.54(2006), p.44–52.

[7] A.H. Gomez, J. Wang, G.X. Hu, A.G. Pereira: Sensors and Actuators B, vol.113(2006), p.347–353.

[8] Z. Hai, J.Wang: Sensors and Actuators B, vol.119(2006), pp.449-455.

[9] M.A. Markom, A.Y. Md. Shakaff, A.H. Adom, M.N. Ahmad, W. hidayat, A.H. Abdullah, N.A. Fikri: Computers and Electronics in Agriculture, vol. 66(2009), p.140–146.

DOI: 10.1016/j.compag.2009.01.006

[10] R.E. Ren, H.W. Wang: Multivariate Statistical Data Analysis –Theory, Method, Example. National Defence Industry Press, Beijing, p.34–119. (1997) (In Chinese)

[11] H.K. Ekenel, B. Sankur: Pattern Recognition Letters, vol.25(2004), p.1377–1388.

[12] J. Lozano, J.P. Santos, M.C. Horrillo: Talanta, vol.67(2005), p.610–616.