Abstract：Blood identification is crucial for the field of inspection and quarantine, criminal investigation and animal protection. Traditional blood identification methods have shortcomings such as long analysis period and damaging to blood samples during the identification process. Raman spectroscopy can obtain molecular vibration and rotation information by analyzing the scattering spectrum different from the incident light frequency, and obtain the composition of the material. Moreover, it has the characteristics of zero pollution and non-contact, which provides the possibility of non-destructive identification of blood. However, there is serious multicollinearity between each wavelength point in Raman spectrum, and directing the use of full-spectrum for modeling will increase the complexity of the model and reduce the stability of the model. According to the characteristics of Raman spectroscopy, this paper proposes a wavelength selection based on neural network. The method uses the neural network to learn the contribution weight of each wavelength point to the correction model, and uses the mean value of the weight as the threshold value to remove the wavelength point whose weight is lower than the threshold value, so as to achieve the purpose of wavelength selection. In order to make it easier to determine the threshold of the screening, sparse constraints are added to the weight learning process, which greatly reduces the wavelength points used for screening. The proposed method was validated by Raman spectroscopy datasets of animal and human serum. The experimental results show that the model established by the wavelength selection using this method has a certain improvement in classification accuracy compared and AUC value with the full spectrum, the accuracy of artificial neural network (NN) reached 94.495% and AUC value reached 0.985 0. The accuracy of PLS-DA reached 92.661%, and AUC value reached 0.976 0. Compared with the traditional wavelength selection method UVE, the method selects fewer wavelength points, and only 42 wavelength points have been selected for modeling, the classification accuracy of the calibration model and AUC value is high, and accuracy reached 92.661%, and AUC value reached 0.976 0. It is proved that the wavelength selection method can effectively screen out the wavelength points contributing to the modeling, which provide a possibility for non-destructive identification of blood, which has certain practical value.
[1] Doty K C, Lednev I K. Forensic Science International, 2018, 282: 204.
[2] Bian H, Wang P, Wang N, et al. Biomedical Optics Express, 2018, 9(8): 3512.
[3] Martens H, Naes T, Naes T. Multivariate Calibration. John Wiley & Sons, 1992.
[4] LI Pao, ZHOU Jun, JIANG Li-wen, et al(李 跑, 周 骏, 蒋立文, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(5): 1428.
[5] Duarte L M, Paschoal D, Izumi C M S, et al. Food Research International, 2017, 99: 106.
[6] Wang S H, Zhao Y, Hu, R, et al. Chinese Journal of Analytical Chemistry, 2019, 47(4): e19034.
[7] Chen J, Yang C, Zhu H, et al. Chemometrics and Intelligent Laboratory Systems, 2018, 182: 188.
[8] Centner V, Massart D L, de Noord O E, et al. Analytical Chemistry, 1996, 68(21): 3851.
[9] Bin J, Ai F, Fan W, et al. Chemometrics and Intelligent Laboratory Systems, 2016, 158: 1.
[10] Choi H, Cho K, Bengio Y. Neurocomputing, 2018, 284: 171.
[11] Premasiri W R, Lee J C, Ziegler L D. The Journal of Physical Chemistry B, 2012, 116(31): 9376.
[12] Araújo M C U, Saldanha T C B, Galvao R K H, et al. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65.
