Raman Spectral Blood Stain Identification Based on Band Selection
YANG Zhi-chao1, 2, SHI Lu1, CAI Jing1, ZHANG Hui1
1. Zhejiang Police College, Hangzhou 310053, China
2. Key Laboratory of Drug Prevention and Control Technology of Zhejiang Province, Hangzhou 310053, China
Abstract:The species identification of blood stains has important practical significance in criminal technology and inspection and quarantine. Raman spectroscopy provides an idea for the identification of bloodstain species. In this paper, human blood samples and blood samples of pig, chicken, duck, cow and mouse were collected and their Raman spectra were obtained. Savitzky-Golay method was used to smooth noise reduction, airPLS method was used for baseline correction, and 100~1 700 cm-1 bands were selected for the experiment. The training set contained 600 sets of data, and the test set contained 300 sets of Raman spectral data. The first part of the experiment compared plS-DA, LDA, PCA+LDA, SVM and PCA+SVM. The accuracy of the test set was 84.0%, 49.3%, 78%, 83.0% and 85.7% respectively, which verified the effectiveness of the combination of the dimension-reduction algorithm and the SVM classifier. In the second part, three band selection algorithms of mutual information algorithm, genetic algorithm and equispaced combination were adopted. A comparative experiment was conducted in combination with the SVM classifier. The results showed that the combination of mutual information and the SVM algorithm had the best classification accuracy. When the number of band selection is 300, the accuracy of the three band selection algorithms combined with the SVM classifier is about 93%, which is much higher than the traditional classification method. The experimental results show that the spectral dimension reduction using a band selection algorithm can effectively improve the accuracy and robustness of the algorithm, and at the same time, make the identification of Raman spectral species more interpretable. The band selection algorithm determines the key band location of blood stain identification, which is also important for the design of a portable Raman system for law enforcement.
Key words:Blood stain; Raman spectrum; Classification model; Band selection
杨志超,石 璐,蔡 竞,张 辉. 基于波段选择的拉曼光谱血痕鉴别[J]. 光谱学与光谱分析, 2021, 41(10): 3137-3141.
YANG Zhi-chao, SHI Lu, CAI Jing, ZHANG Hui. Raman Spectral Blood Stain Identification Based on Band Selection. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3137-3141.
[1] Toishi Y, Tsunoda N, Nagata S, et al. Journal of Reproduction & Development, 2018, 64: 41.
[2] Li Y, Pan X, Roberts M L, et al. Epigenomics, 2018, 10: 797.
[3] Kotnik P, Krajnc M K, Pahor A, et al. Journal of Pharmaceutical & Biomedical Analysis, 2018, 150: 137.
[4] ZHU Zhi-hui, MENG Fan-hao, XIA Jia-bin, et al(朱智慧, 孟凡皓, 夏嘉斌, 等). Acta Academiae Medicinae Sinicae(中国医学科学院学报), 2020, 42(3): 399.
[5] Ding Qianqian, Wang Jing, Chen Xueyan, et al. Nano Letters,2020,20(10):7304.
[6] Ceballos M, Arizmendi-Morquecho A, Sanchez-Dominguez M, et al. Materials Chemistry and Physics, 2020, 240: 122225.
[7] Sarychev A K, Bykov I V, Boginskaya I A, et al. Optical and Quantum Electronics, 2020, 52(1): 26.
[8] LIN Ling, ZHU Zhan-yuan, WANG Lan(林 玲,朱占元,王 兰). Guangdong Chemical Industry(广东化工), 2019,(2):92.
[9] Wang Z, Yang H, Wang M, et al. Colloids & Surfaces A Physicochemical & Engineering Aspects, 2018, 546: 48.
[10] Lee M, Kim H, Kim E, et al. ACS Applied Materials & Interfaces, 2018, 10: 37829.
[11] BAI Peng-li, WANG Jun, YIN Huan-cai, et al(白鹏利, 王 钧, 尹焕才, 等). The Journal of Light Scattering(光散射学报), 2016, 28(2): 163.
[12] ZHENG Xiang-quan, LIAO Xin, XU Yi, et al(郑祥权, 廖 鑫, 徐 溢, 等). Chemical Journal in Chinese Universities(高等学校化学学报), 2017, 38(4): 575.
[13] DONG Jia-lin, HONG Ming-jian, ZHENG Xiang-quan, et al(董家林, 洪明坚, 郑祥权, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(2): 459.
[14] DU Pei-jun, XIA Jun-shi, XUE Chao-hui, et al(杜培军, 夏俊士, 薛朝辉, 等). Journal of Remote Sensing(遥感学报), 2016, 20(2): 236.
[15] Feng Pengmian, Feng Lijing. International Journal of Biological Macromolecules, 2020, 162: 931.