Parameter Selection Based on Support Vector Machines for Tongue Spectral Identification Model

Abstract:

Support Vector Machine (SVM) method is suitable for machine learning. In order to detect pathological information from tongue diagnosis rapidly, noninvasively and objectively, a near infrared spectral identification model is proposed based on SVM. The tongue spectral data of healthy people and hepatitis patients were collected. Twenty two samples were obtained for individual groups, and for each group, fifteen samples were randomly selected and used as the training sets, while the other seven were taken as the prediction sets. For the data sets, The effects of the principal component number, kernel parameters, and kernel functions on the identification model were investigated respectively. The results showed that the penalty parameter c was always 0.25, not related to the values of the principal component number and kernel parameter g. The kernel parameter g decreased along with the increased number of principal components, and ultimately reached a relatively stable value. When the Radial Basis Function (RBF) was applied, the established model was the best, indicating that the SVM approach is feasible to classify and recognize tongue near infrared spectroscopy, as along as right parameters are selected. This can provide a novel tongue spectral analysis method to distinguish healthy individuals from hepatitis patients.

• Periodical: Applied Mechanics and Materials (Volume 678)
• Pages: 242-251
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.678.242
• Online since: October 2014
• Authors: Wen Juan Yan*, Guo Quan He, Shi Jian Huang, Lin Qin
• Keywords: Principal Component Analysis (PCA), Spectral, Support Vector Machine (SVM), Tongue Diagnosis

References

[1] Linlin Yuan, Wenshu Li, Jianfu Yao, Hong Song, Xiaowei Zheng. Acta Universitatis Traditionis Medicalis Sinensis Pharmacologiaeque Shanghai(in Chinese), vol. 25, (2), pp.80-86, (2011).

[2] Qun Chen, Zhiwei Xu , Mei Liu. Modern research on recognition technology of Tongue Inspection of TCM(in Chinese), vol. 22, (7) , pp.1215-1216, (2004).

[3] D. T. Ubbink, B. Koopman. Eur. J. Vasc. Endovasc. Surg., vol. 31, pp.394-400, (2006).

[4] Xiliang Wu, and Xiaozuo Lu. Tianjin Journal of Traditional China Medicine(in Chinese), vol. 22, (5), pp.388-390, (2005).

[5] Meng Zhang, Xianwei Hu, Yuanbin Wang. Journal of Chinese Computer Systems(in Chinese), vol. 29, (6), pp.1149-1153, (2008).

[6] LI Xiaoyu, ZHANG Xinfeng, SHEN Lansun. Beijing Biomedical Engineering(in Chinese), vol. 25, (1), pp.43-46, (2006).

[7] Min Zhang, Zhifeng Zhang, Jiatuo Xu, Liping Tu.  Acta Universitatis Traditionis Medicalis Sinensis Pharmacologiaeque Shanghai(in Chinese), vol. 26, (2), pp.93-95, (2012).

[8] Wenjuan Yan, Gang Li, Ling Lin. Infrared Technology(in Chinese), vol. 32, (8), pp.487-494, (2010).

[9] Gang LI, Jing Zhao, Jiaxing Li, Hui Xiong, Ling Lin, Ying Tong, Biaoju Zhang. Spectroscopy and Spectral Analysis(in Chinese), vol. 31, (5) pp.1328-1331, (2011).

[10] Ling Lin, Zhe Li, Xiaoxia Li, Yongcheng Li, Gang Li, Baoju Zhang, Wei Song. Spectroscopy and Spectral Analysis(in Chinese), vol. 32, (8), pp.2110-2116, (2012).

[11] Jinhui Zhang, Zhengjun He, Xi Tian. Manuf Acturing Informatization(in Chinese), vol. 8, pp.31-32, (2012).

[12] V. Vapnik. The nature of statistical learning theory (1995). New York: Springer Verlag.

[13] Chen Xu, Hui Cao, Xiao Zhao. Computer Engineering(in Chinese), vol. 38, (21), pp.175-177, (2012).

[14] Yu Yang, Dejie Yu, Junsheng Cheng. Measurement(in Chinese), vol. 40, p.943–950, (2007).

[15] Lingfei Xu, Wusen Li, Meng Zhang, Shixue Xu, Jia Li. Optik(in Chinese), vol. 122, pp.594-598, (2011).