Qualitative and Quantitative Analysis Algorithms Based on Terahertz Spectroscopy for Biomedical Detection

Yan Peng; Chenjun Shi; Yiming Zhu; Songlin Zhuang

doi:10.3788/CJL201946.0614002

Chinese Journal of Lasers, Volume. 46, Issue 6, 0614002(2019)

Qualitative and Quantitative Analysis Algorithms Based on Terahertz Spectroscopy for Biomedical Detection

Yan Peng, Chenjun Shi, Yiming Zhu^**, and Songlin Zhuang^*

Terahertz Technology Innovation Research Institute, Terahertz Spectrum and Imaging Technology Cooperative Innovation Center, Shanghai Key Lab of Modern Optical System, University of Shanghai for Science and Technology, Shanghai 200093, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(11)

Fig. 1. Spectra of four pure samples of L-Glu, D-MI, CMH, and GABA

Download full size

Fig. 2. Measured spectra and calculated spectra. (a) Mixture sample of L-Glu, D-MI, and CMH; (b) mixture sample of all four components

Download full size

Fig. 3. Spectra of 10 mixture samples. (a) Before wavelet transform; (b) after wavelet transform

Download full size

Fig. 4. RMSE of three SVR parameters based on leave-one-out cross validation. (a) Parameter c when g=0.01and e=0.01; (b) parameter g when c=0.25 and e=0.01; (c) parameter e when c=0.25 and g=0.01

Download full size

Fig. 5. Actual and predicted concentrations of 10 mixture samples. (a) NAA; (b) NE

Download full size

Table 1. Concentration results of mixture sample of L-Glu, D-MI and CMH
View table
Table 1. Concentration results of mixture sample of L-Glu, D-MI and CMH
Component Actual concentrationn_a1 /% Calculated concentrationn_c1 /% Root mean squarederror E_RMS1 Average root meansquared error $\begin{matrix} {\bar{E}}_{RMS 1} \end{matrix}$ /%
L-Glu 4.65 4.65 0
D-MI 4.65 4.55 0.0215 4.65
CMH 4.65 4.10 0.1180

Table 2. Concentration results of mixture sample of all four components

View table

Table 2. Concentration results of mixture sample of all four components

Component	Actual concentrationn_a2 /%	Calculated concentrationn_c2 /%	Root mean squarederror E_RMS2	Average root meansquared error $\begin{matrix} {\bar{E}}_{RMS 2} \end{matrix}$ /%
L-Glu	4.90	4.50	0.0816
D-MI	4.90	4.90	0	5.44
CMH	4.90	4.60	0.0612
GABA	4.90	4.80	0.0204

Table 3. Parameters of mixture samples including NAA and NE
View table
Table 3. Parameters of mixture samples including NAA and NE
Samplenumber NAA massm₁ /mg NE massm₂ /mg Mass of otherfive componentsm₃ /mg
1 3.02 1.13 -
2 9.85 7.02 -
3 11.99 15.08 -
4 9.20 3.82 -
5 1.20 9.98 -
6 4.13 8.91 -
7 15.20 12.03 -
8 12.87 3.19 -
9 4.86 4.80 -
10 7.02 13.03 -

Table 4. RMSE and correlation coefficient between predicted and actual concentrations of NAA and NE in mixture
View table
Table 4. RMSE and correlation coefficient between predicted and actual concentrations of NAA and NE in mixture
Component RMSE E_RMS Average RMSE $\begin{matrix} {\bar{E}}_{RMS} \end{matrix}$ Correlationcoefficient R Average correlationcoefficient $\begin{matrix} \bar{R} \end{matrix}$
NAA 0.0040 0.9913
NE 0.0040 0.0040 0.9914 0.99135

Table 5. Accuracy of algorithm models under different sample numbers
View table
Table 5. Accuracy of algorithm models under different sample numbers
Number ofsamples RMSE E_RMSn Correlationcoefficient R_n
6 0.0125 0.9026
8 0.0055 0.9853
10 0.0040 0.9914

Table 6. Prediction accuracy of different algorithms
View table
Table 6. Prediction accuracy of different algorithms
Algorithm RMSE E_RMSa Correlationcoefficient R_a
Partial least squares 0.0231 0.8052
BP nerve network 0.0175 0.8353
Support vector regression 0.0040 0.9914

Tools

Get Citation

Copy Citation Text

Yan Peng, Chenjun Shi, Yiming Zhu, Songlin Zhuang. Qualitative and Quantitative Analysis Algorithms Based on Terahertz Spectroscopy for Biomedical Detection[J]. Chinese Journal of Lasers, 2019, 46(6): 0614002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites