In this work, a deep belief neural network model (DBN) was developed to classify doves, chickens, mice and sheep blood samples, which have many similarities in composition causing their spectra to look almost identical by visual comparison alone. The DBN model was formulated for the feature extraction from the pretreated fluorescence spectroscopy. Then, cross-validation results showed that the application of deep learning method made it possible to classify the blood fluorescence spectroscopy in a more precise way than previous methods. Especially, the classification accuracy of whole blood with 1% of concentration was up to 97.5%.
References
[1]
Frank, C.J., Mccreery, R.L. and Redd, D.C.B. (1995) Raman Spectroscopy of Normal and Diseased Human Breast Tissues. Analytical Chemistry, 67, 777-783. https://doi.org/10.1021/ac00101a001
[2]
Sun, Y., Liu, R., Elson, D.S., et al. (2008) Simultaneous Time- and Wavelength-Resolved Fluorescence Spectroscopy for Near Real-Time Tissue Diagnosis. Optics Letters, 33, 630-632. https://doi.org/10.1364/OL.33.000630
[3]
Sikirzhytski, V., Virkler, K. and Lednev, I.K. (2010) Discriminant Analysis of Raman Spectra for Body Fluid Identification for Forensic Purposes. Sensors, 10, 2869-2884. https://doi.org/10.3390/s100402869
[4]
Sikirzhytskaya, A., Sikirzhytski, V. and Lednev, I.K. (2017) Determining Gender by Raman Spectroscopy of a Bloodstain. Analytical Chemistry, 89, 1486-1492. https://doi.org/10.1021/acs.analchem.6b02986
[5]
Mclaughlin, G., Doty, K.C. and Lednev, I.K. (2014) Raman Spectroscopy of Blood for Species Identification. Analytical Chemistry, 86, 11628-11633. https://doi.org/10.1021/ac5026368
[6]
Zhang, L., Zhou, M., Li, X., Li, G. and Lin, L. (2014) Discrimination of Human and Nonhuman Blood Using Visible Diffuse Reflectance Spectroscopy. Analytical Methods, 6, 9419-9423. https://doi.org/10.1039/C4AY01673D
[7]
Andrasko, J. and Rosã, N.B. (1994) Sensitive Identification of Hemoglobin in Bloodstains from Different Species by High Performance Liquid Chromatography with Combined UV and Fluorescence Detection. Journal of Forensic Sciences, 39, 1018-1025. https://doi.org/10.1520/JFS13680J
[8]
Van Steendam, K., De Ceuleneer, M., Dhaenens, M., Van Hoofstat, D. and Deforce, D. (2013) Mass Spectrometry-Based Proteomics as a Tool to Identify Biological Matrices in Forensic Science. International Journal of Legal Medicine, 127, 287-298. https://doi.org/10.1007/s00414-012-0747-x
[9]
De, W.K., Lepot, L., Gason, F. and Gilbert, B. (2008) In Search of Blood-Detection of Minute Particles Using Spectroscopic Methods. Forensic Science International, 180, 37-42. https://doi.org/10.1016/j.forsciint.2008.06.013
[10]
Virkler, K. and Lednev, I.K. (2009) Blood Species Identification for Forensic Purposes Using Raman Spectroscopy Combined with Advanced Statistical Analysis. Analytical Chemistry, 81, 7773-7777. https://doi.org/10.1021/ac901350a
[11]
Deng, L. and Yu, D. (2014) Deep Learning: Methods and Applications. Foundations and Trends in Signal Processing, 7, 197-387. https://doi.org/10.1561/2000000039
[12]
Gong, M., Yang, H. and Zhang, P. (2017) Feature Learning and Change Feature Classification Based on Deep Learning for Ternary Change Detection in SAR Images. ISPRS Journal of Photogrammetry and Remote Sensing, 129, 212-225. https://doi.org/10.1016/j.isprsjprs.2017.05.001
[13]
Lu, P., Fan, Y., Zhou, L., et al. (2017) Feature Extraction and Classification of Animal Blood Spectra with Support Vector Machine. Spectroscopy and Spectral Analysis, 37, 3828-3832.
[14]
Dong, J., Hong, M., Zheng, X., et al. (2018) Discrimination of Human, Dog and Rabbit Blood Using Raman Spectroscopy. Spectroscopy and Spectral Analysis, 38, 459-466.
[15]
Zhang, Y. (2016) Research of Deep Learning Method Based on Restricted Boltzmann Machine. Beijing University of Chemical Technology, Beijing.
[16]
Ma, S., Shen, T., Wang, R., et al. (2015) Terahertz Spectroscopic Identification with Deep Belief Network. Spectroscopy and Spectral Analysis, 35, 3325-3329.
[17]
Lu, W., Guo, Y., Dai, J., et al. (2018) Rice Germination Rate Detection Based on Fluorescent Spectrometry and Deep Belief Network. Spectroscopy and Spectral Analysis, 38, 1303-1312.
[18]
Wang, S., Xu, X., Liu, Q., et al. (2001) The Application of Fluorescence Spectroscopy in the Study on Protein Conformation. Progress in Chemistry, 13, 28-31.
