Considering the deficiency of the traditional liquor classification method, a novel method for liquor classification based on support vector machine is discussed in this paper. Liquor chromatographic data is used as basis and the LIBSVM toolbox is used as classification tool in this method. Two different grades of 490 base liquor samples (containing 242 samples of ordinary base liquor, 248 samples of high-quality base liquor) were used to test the method. In the experiment, 180 samples of ordinary base liquor and 184 samples of high-quality base liquor were selected as the training set to build the model and the remaining base liquor were used as the testing set to test the accuracy of the model. The model accuracy could reach 98 % without the correlation parameter optimization. The results show that the method can achieve a higher accuracy, and prove the correctness and effectiveness of the method.
[1]
Yin Jing-yuan.
Applications of Modern Equipment Analytical Techniques in Sensory Evaluation of Liquor
,
2007
.
[2]
Chih-Jen Lin,et al.
LIBSVM: A library for support vector machines
,
2011,
TIST.
[3]
Nello Cristianini,et al.
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
,
2000
.
[4]
Vladimir N. Vapnik,et al.
The Nature of Statistical Learning Theory
,
2000,
Statistics for Engineering and Information Science.
[5]
Vladimir Vapnik,et al.
Statistical learning theory
,
1998
.