Rapid Determination of Content of Total Volatile Basic Nitrogen in Pork Based on Multispectral Detection System with Optimal Wavelength

Wensong Wei; Yankun Peng; Xiaochun Zheng; Wenxiu Wang; Fang Tian

doi:10.3788/AOS201737.1130003

Acta Optica Sinica, Volume. 37, Issue 11, 1130003(2017)

Rapid Determination of Content of Total Volatile Basic Nitrogen in Pork Based on Multispectral Detection System with Optimal Wavelength

Wensong Wei, Yankun Peng^*, Xiaochun Zheng, Wenxiu Wang, and Fang Tian

Author Affiliations

National Research & Development Center for Agro-Processing Equipment, College of Engineering, China Agricultural University, Beijing 100083, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(17)

Fig. 1. (a) Hyperspectral image at wavelength of 280 nm of ROI and (b) reflectance curve after calibration of a certain sample

Download full size

Fig. 2. Raw reflectance spectra of 52 pork samples

Download full size

Fig. 3. Spectrograms of raw spectra after preprocessing with FD-SNV algorithm

Download full size

Fig. 4. (a) Number of characteristic wavelength screened by SWA algorithm; (b) wavelength distribution of screening variable

Download full size

Fig. 5. Regression coefficient distribution of band screened by SWA algorithm

Download full size

Fig. 6. (a) Number of optimal characteristic wavelength screened by SPA algorithm; (b) detailed position of characteristic wavelength

Download full size

Fig. 7. (a) Frequency of characteristic wavelength screened by GA algorithm; (b) modeling contribution rate of characteristic wavelength number

Download full size

Fig. 8. Distribution of characteristic wavelength screened by GA algorithm

Download full size

Fig. 9. Distribution of optimal characteristic wavelength screened by three algorithms of SWA, SPA, and GA

Download full size

Fig. 10. Diagram of multispectral detection system

Download full size

Fig. 11. Reflectance of 44 pork samples collected by multispectral method

Download full size

Fig. 12. Predicted content of TVB-N with PLSR model and MLR model. (a) PLSR model, calibration set; (b) PLSR model, prediction set; (c) MLR model, calibration set; (d) MLR model, prediction set

Download full size

Table 1. Measured mass fraction of TVB-N in calibration set and prediction set of the first group pork samples
View table
Table 1. Measured mass fraction of TVB-N in calibration set and prediction set of the first group pork samples
Set Sample number Maximum /10^-5 Minimum /10^-5 Average /10^-5
Calibration 39 31.71 5.55 15.45
Prediction 13 35.56 6.56 16.85

Table 2. Measured mass fraction of TVB-N in calibration set and prediction set of the second group pork samples
View table
Table 2. Measured mass fraction of TVB-N in calibration set and prediction set of the second group pork samples
Set Sample number Maximum /10^-5 Minimum /10^-5 Average /10^-5
Calibration 33 38.01 6.96 17.69
Prediction 11 34.86 6.29 16.09

Table 3. PLSR model results of raw spectra after preprocessing with different methods

View table

Table 3. PLSR model results of raw spectra after preprocessing with different methods

Preprocessing method	R_c	$\begin{matrix} {x_{SEC}}_{} \end{matrix}$ /10^-5	R_p	$\begin{matrix} {x_{SEP}}_{} \end{matrix}$ /10^-5
Raw spectrum	0.8762	3.4443	0.8601	3.9485
FD	0.9466	2.3026	0.9372	2.7969
SD	0.9041	3.2120	0.8820	3.7442
SNV	0.8686	4.4983	0.6788	7.8631
FD-SNV	0.9454	2.3288	0.9395	2.6838
AS	0.8039	4.3647	0.7630	5.1728
AS-FD	0.8955	4.0074	0.8251	5.5752
AS-SD	0.6952	4.7815	0.6578	7.5999
SD-SNV	0.9113	3.0918	0.8949	3.8736

Table 4. Modeling results of characteristic wavelength obtained by different screening variable algorithms

View table

Table 4. Modeling results of characteristic wavelength obtained by different screening variable algorithms

Screening algorithm	Variable number	Modeling method	R_c	$\begin{matrix} {x_{SEC}}_{} \end{matrix}$ /10^-5	R_p	$\begin{matrix} {x_{SEP}}_{} \end{matrix}$ /10^-5	Screening wavelength /nm	t
SWA	5	PLSR	0.81	4.18	0.79	4.47	472,595,765,811,830	5/455
SWA	5	MLR	0.83	4.04	0.78		472,595,765,811,830	4.62
SPA	13	PLSR	0.92	2.88	0.892	3.40	452,455,474,532,544,579,586,596,610,635,778,860,865	13/455
SPA	13	MLR	0.94	2.47	0.893		452,455,474,532,544,579,586,596,610,635,778,860,865	3.14
GA	28	PLSR	0.95	2.24	0.91	3.78	471,481,483,485,489,491,506,525,542,543,544,546,547,548,564,576,593,597,601,605,607,610,612,615,620,807,858,865	28/455
GA	28	MLR	0.96	2.16	0.85			4.24

Table 5. Predicted results of PLSR model and MLR model established by multispectral method
View table
Table 5. Predicted results of PLSR model and MLR model established by multispectral method
Model R_c $\begin{matrix} {x_{SEC}}_{} \end{matrix}$ /10^-5 R_p $\begin{matrix} {x_{SEP}}_{} \end{matrix}$ /10^-5
PLSR 0.9014 4.18 0.8976 4.19
MLR 0.9050 3.63 0.9040 3.81

Tools

Get Citation

Copy Citation Text

Wensong Wei, Yankun Peng, Xiaochun Zheng, Wenxiu Wang, Fang Tian. Rapid Determination of Content of Total Volatile Basic Nitrogen in Pork Based on Multispectral Detection System with Optimal Wavelength[J]. Acta Optica Sinica, 2017, 37(11): 1130003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Spectroscopy

Received: Jul. 3, 2017

Accepted: --

Published Online: Sep. 7, 2018

The Author Email: Yankun Peng (ypeng@cau.edu.cn)

DOI:10.3788/AOS201737.1130003

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Measured mass fraction of TVB-N in calibration set and prediction set of the first group pork samples

Table 1. Measured mass fraction of TVB-N in calibration set and prediction set of the first group pork samples

Table 2. Measured mass fraction of TVB-N in calibration set and prediction set of the second group pork samples

Table 2. Measured mass fraction of TVB-N in calibration set and prediction set of the second group pork samples

Table 3. PLSR model results of raw spectra after preprocessing with different methods

Table 3. PLSR model results of raw spectra after preprocessing with different methods

Table 4. Modeling results of characteristic wavelength obtained by different screening variable algorithms

Table 4. Modeling results of characteristic wavelength obtained by different screening variable algorithms

Table 5. Predicted results of PLSR model and MLR model established by multispectral method

Table 5. Predicted results of PLSR model and MLR model established by multispectral method