Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1830002(2022)
Spectral Pattern Recognition and Traceability Analysis of Human Fingernail Based on Machine Learning
Figures & Tables(10)
Fig. 1. Infrared spectra of fingernail samples. (a) Infrared spectra of different sampling sites for the same fingernail sample; (b) infrared spectra of ten fingernails from the same person; (c) infrared spectra of fingernail samples from different people
Fig. 2. Variance contribution rate depending on number of principal components and factor components. (a) Principal components; (b) factor components
Fig. 3. Classification accuracy of MLP and RBF models based on PCA and FA dimensionality reduction. (a) PCA-MLP; (b) FA-MLP; (c) PCA-RBF; (d) FA-RBF
Fig. 5. Classification accuracy of SVM model based on different principal components
Fig. 6. Spatial classification details of fingernail samples from five provinces of north China
Table 1. Spectral peaks and their modes of vibration
View tableTable 1. Spectral peaks and their modes of vibration
Wavenumber /cm-1 Mode of vibration 3292 O-H stretching，carboxyl acid and derivatives 3068 Amide A and B and NH stretching 2925 C-H symmetric stretching（CH2 and CH3 anti symmetric and symmetric stretching modes） 2858 1618 C=C stretching 1532 Amide II，C-N stretch and N-H in plane bend 1461 C-H deformation in CH2 1241 Amide III band，C-N stretching vibrations 1062 C-C trans conformation 756 Cis-R，CH≡CHR
Table 2. Classification accuracy of decision tree model based on different algorithms
View tableTable 2. Classification accuracy of decision tree model based on different algorithms
Region Classification accuracy /% CHAID Exhaustive CHAID CRT QUEST Training set Test set Training set Test set Training set Test set Training set Test set R1 92.9 94.4 82.6 92.9 97.6 84.2 87.2 81.0 R2 62.5 50.0 57.1 66.7 71.4 66.7 100.0 100.0 R3 97.2 92.9 96.4 86.4 86.1 85.7 94.3 93.3 R4 100.0 83.3 80.0 100.0 66.7 100.0 85.7 33.3 R5 84.2 100.0 91.7 62.5 85.7 83.3 94.7 100.0 R6 88.9 100.0 100.0 80.0 84.6 57.1 73.3 100.0 R7 94.4 100.0 100.0 100.0 95.0 100.0 46.7 20.0 Total 91.0 92.0 89.2 86.2 89.1 82.8 84.8 73.7
Table 3. Classification accuracy of support vector machine model based on different kernel functions
View tableTable 3. Classification accuracy of support vector machine model based on different kernel functions
Type Classification accuracy /% RBF kernel Polynomial kernel Sigmoid kernel Linear kernel Training set 90.8 100.0 47.3 88.6 Test set 92.2 100.0 50.0 82.8
Table 4. Classification results of unknown samples by MLP and SVM models
View tableTable 4. Classification results of unknown samples by MLP and SVM models
Project Total number of samples Number of unknown samples Number of correctly classified samples Classification accuracy /% MLP SVM MLP SVM 1 195 57 54 57 94.7 100.0 2 60 15 15 15 100.0 100.0
Tools
Get Citation
Copy Citation Text
Wei Hou, Jifen Wang, Yiran Liu. Spectral Pattern Recognition and Traceability Analysis of Human Fingernail Based on Machine Learning[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1830002
Paper Information
Category: Spectroscopy
Received: May. 15, 2021
Accepted: Jul. 27, 2021
Published Online: Sep. 5, 2022
The Author Email: Wang Jifen (wangjifen58@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20