Research Article | OPEN ACCESS
A Comparison of Methods for Classification of Flue-cured Tobacco Aroma Types
Fenghua Ma and Wei Wu
College of Computer and Information Science, Southwest University, Chongqing 400716, China
Advance Journal of Food Science and Technology 2016 2:82-87
Received: September 9, 2015 | Accepted: September 25, 2015 | Published: September 15, 2016
Abstract
It is well acknowledged that flue-tobacco aroma types were divided into light, medium and heavy in China. For the sake of singling out an optimal scheme to discriminate the spatial distribution of flue-cured tobacco aroma type, in the current study, different amounts of chemical indices data with various methods including Back-Propagation Neural Networks (BP NN), Support Vector Machine (SVM) and Discriminant Analysis (DA) were presented and compared. All the experimental results indicated that, by and large, the number of chemical indices have nothing to do with the accuracy. Additionally, the classification effects of BP NN are superior to the others. On a whole, the best scheme with accuracy reaching to 81.18% and kappa value up to 0.72 was drawn only when the BP model combined with 9 kinds of chemical indices. In the end, the optimal spatial distribution was established in ArcGIS9.3.
Keywords:
BP NN, DA, flue-cured tobacco aroma, spatial classification, SVM,
References
-
Bi, S.F., X.L. Zhu and C.Z. Ma, 2006. Application of stepwise discriminatory analysis in distinguishing aromas of flue-cured Tobacco in China. Chinese J. Trop. Crop., 27(4): 104-107.
Direct Link -
Du, Y.M., C.F. Guo, H.B. Zhang, Y. Shang, X.L. Wang, J. Qiu and H.L. Ai, 2000. Study on relationship between content of water soluble sugar, alkaloid, total nitrogen and taste quality of flue cured tobacco. Chinese Tobacco Sci., 1: 7-10.
-
Fleiss, J.L., 1971. Measuring nominal scale agreement among many raters. Psychol. Bull., 76(5): 378-382. http://psycnet.apa.org/psycinfo/1972-05083-001.
CrossRef Direct Link -
Hecht-Nielsen, R., 1989. Theory of the backpropagation neural network [C]. Proceeding of the IEEE International Joint Conference on Neural Networks (IJCNN, 1989), 1: 593-605.
-
Hsu, C.W. and C.J. Lin, 2002. A comparison of methods for multiclass support vector machines. IEEE T. Neural Networ., 13(2): 415-425.
-
Hu, J.J., M. Ma, Y.G. Li and C.Y. Yu, 2010. Grey incidence analysis on the correlation between main chemical components and sensory quality of flue-cured Tobacco. Tobacco Sci. Technol., Vol. 1, 2010.
-
Johnson, R.A. and D.W. Wichern, 1992. Applied Multivariate Statistical Analysis. 3rd Edn., Prentice-Hall, Englewood Cliffs, NJ, pp: 644.
-
Kavdir, I., 2004. Discrimination of sunflower, weed and soil by artificial neural networks. Comput. Electron. Agr., 44(2): 153-160.
-
Kolios, S. and C.D. Stylios, 2013. Identification of land cover/land use changes in the greater area of the Preveza peninsula in Greece using Landsat satellite data. Appl. Geogr., 40: 150-160.
CrossRef Direct Link -
Landis, J.R. and G.G. Koch, 1977. The measurement of observer agreement for categorical data. Biometrics, 33(1): 159-174.
CrossRef PMid:843571 Direct Link -
Li, Z.H., N.R. Wang, D.S. Wang, X.L. Zhu and H.L. Zhou, 2009. Preliminary study of aroma type styles of flue-cured tobacco in different ecological scale regions. Chinese Tobacco Sci., 30(5): 67-70, 76.
-
Marey-Pérez, M.F. and V. Rodríguez-Vicente, 2011. Factors determining forest management by farmers in northwest Spain: Application of discriminant analysis. Forest Policy Econ., 13(5): 318-327.
CrossRef Direct Link -
Nieuwenhuizen, A.T., J.W. Hofstee, J.C. van de Zande, J. Meuleman and E.J. van Henten, 2010. Classification of sugar beet and volunteer potato reflection spectra with a neural network and statistical discriminant analysis to select discriminative wavelengths. Comput. Electron. Agr., 73(2): 146-153.
-
Riveiro-Vali-o, J.A., C.J. Álvarez-López and M.F. Marey-Pérez, 2009. The use of discriminant analysis to validate a methodology for classifying farms based on a combinatorial algorithm. Comput. Electron. Agr., 66(2): 113-120.
-
Wang, Y.B., B.H. Wang, C.F. Guo, F.L. Wang and J. Zhou, 1998. Study on the main chemical components related to smoking quality in flue-curred tobacco. Sci. Agr. Sinica, 31(1): 89-91.
-
Widrow, B., 1988. DARPA Neural Network Study. AFCEA Int. Press, Fairfax, VA.
-
Zhang, J., F.F. Zhou, G.B. Deng, C.T. Mao, C.Y. Bao, J.C. Rao and X.L. Zhang, 2013. Discriminant analysis of aroma types of upper leaf in flue-cured tobacco based on chemical constituents and aroma components. J. Hunan Agric. Univ. Nat. Sci., 39(3): 232-241. http://en.cnki.com.cn/Article_en/CJFDTOTAL-HNND201303005.htm.
Direct Link -
Zheng, B.J., S.W. Myint, P.S. Thenkabail and R.M. Aggarwal, 2015. A support vector machine to identify irrigated crop types using time-series Landsat NDVI data. Int. J. Appl. Earth Obs., 34: 103-112.
Competing interests
The authors have no competing interests.
Open Access Policy
This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Copyright
The authors have no competing interests.
|
|
![](http://www.maxwellsci.com/images/AJFST-maxw.jpg) |
ISSN (Online): 2042-4876
ISSN (Print): 2042-4868 |
![Submit Manuscript](../images/sub.jpg) |
Information |
|
|
|
Sales & Services |
|
|
|