Dong-xu SHEN, Ming-jian HONG, Jia-lin DONG. Raman Spectrum Wavelength Selection Method Based on Neural Network[J]. Spectroscopy and Spectral Analysis, 2020, 40(11): 3457
- Spectroscopy and Spectral Analysis
- Vol. 40, Issue 11, 3457 (2020)
Fig. 1. WSNet structure chart
Fig. 2. Raman spectra of human, beagle and New Zealand rabbit were measured
Fig. 3. Raman spectra of human serum, dog serum and rabbit serum after normalization
Fig. 4. Loss value and accuracy during model training
Fig. 5. Classification accuracy of different dimensionality reductions on test sets and calibration sets
Fig. 6. Raman spectrum wavelength selection before and after comparison chart
Fig. 6. Spectral wavelength point weight
Fig. 7. ROC curve of PLS-DA and NN classification
Fig. 8. (a) the spectrum after Raman-WSNet wavelength selection and (b) the spectrum after UVE wavelength selection
The red part is reserved wavelength point
The red part is reserved wavelength point
Fig. 9. Comparison of Raman-WSNet-PLS-DA and UVE-PLS-DA ROC curves
|
Table 1. Serum sample list
|
Table 2. Comparison of classification results
|
Table 3. Comparison of Raman-WSNet-PLS-DA and UVE-PLS-DA classification results
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20