1. School of Software Engineering, Chongqing University, Chongqing 401331, China
2. School of Chemistry and Chemical Engineering, Chongqing University, Chongqing 401331, China
3. National Key Laboratory of Fundamental Science of Micro/Nano-Device and System Technology, Chongqing University, Chongqing 400044, China
Abstract：The identification of multiple species blood is particularly important for entry-exit inspection and quarantine, forensic investigation and wildlife protection. The traditional methods often destroy blood samples and make further analysis of samples impossible. Raman Spectroscopy is a vibrational spectrum, which can obtain the information of molecular vibration and rotation so as to analyze the chemical composition of the material. It provides the possibility of non-destructive blood identification. Currently, there are several methods of blood identification based on Raman spectroscopy, but these methods use the linear classification model, ignoring nonlinear relationship between the spectrum and sample, and lead to the bad performance of the model. Moreover, the small sample number of each species usually results in the under-fitting the model. Therefore, this paper set up a classification model for the nonlinear relationship using the support vector machine to identify Raman spectra of blood, overcame the shortcoming of the linear classification model which emphasizes the linear characteristic of the spectrum in the training, and absorbed the nonlinear relationship in the Raman spectrum effectively, realizing the three classification of human, dog and rabbit blood. There are a total of 326 samples which were measured by Ocean Raman spectrometer with excitation wavelength of 785 nm, including 110 humans, 116 dogs and 100 rabbits. Savitzky-Golay smoothing filter, weighted least squares baseline correction, and vector normalization were used to preprocess them. The 2/3 of these samples were used as calibration set for training and the remaining samples were used as test set for blind testing. Experimental results showed that the classification accuracy of proposed model for the calibration set and the blind test were 100% and 93.52%, and outperformed the existing linear classification models. This indicates that proposed classification model has good application prospects and research value.
Key words：Blood; Raman spectrum; Classification model; Support vector machine
[1] Mclaughlin G, Doty K C, Lednev I K. Forensic Science International, 2014, 238(5): 91.
[2] WANG Xiao-bin, WU Rui-mei, LIU Mu-hua, et al(王晓彬，吴瑞梅，刘木华，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014，34(6): 1566.
[3] LU Ming-zi, GUO Yan-jun, ZHAO Lian, et al(卢明子，郭延军，赵 莲，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014，34(2): 439.
[4] Virkler K, Lednev I K. Analytical Chemistry, 2009, 81(18): 7773.
[5] Mclaughlin G, Doty K C, Lednev I K, et al. Anal. Chem.，2014, 86：11628.
[6] Mclaughlin G, Doty K C, Lednev I K. Forensic Science International, 2014, 238(5): 91.
[7] Fujihara J, Fujita Y, Yamamoto T, et al. International Journal of Legal Medicine, 2016. 1.
[8] CHEN Da, YAN Meng-yu, LI Qi-feng, et al(陈 达，闫孟雨，李奇峰，等). Nanotechnology and Precision Engineering(纳米技术与精密工程), 2015, 13(3): 226.
[9] Li J, Deng H, Li P, et al. Applied Physics B, 2015, 120(2): 207.
[10] Huang G, Ruan X, Chen X, et al. Analytical Methods, 2014, 6(9): 2900.
[11] Premasiri W R, Lee J C, Ziegler L D. Journal of Physical Chemistry B, 2012, 116(31): 9376.
[12] WANG Gui-wen, PENG Li-xin, SHEN Wei-dong, et al(王桂文，彭立新，申卫东，等). Acta Optica Sinica(光学学报), 2011(6): 276.
[13] Skrobot V L, Castro E V R, Pereira R C C, et al. Energy & Fuels, 2016, 21(6): 5.
[14] Wong T T. Pattern Recognition, 2015, 48(9): 2839.
[15] Guerbai Y, Chibani Y, Hadjadji B. Pattern Recognition, 2015, 48(1): 103.
