Hyperspectral Technique Coupled With Chemometrics Methods for Predicting Alkali Spreading Value of Millet Flour

Guo-liang WANG; Ke-qiang YU; Kai CHENG; Xin LIU; Wen-jun WANG; Hong LI; Er-hu GUO; Zhi-wei LI

doi:10.3964/j.issn.1000-0593(2021)10-3189-05

Spectroscopy and Spectral Analysis, Volume. 41, Issue 10, 3189(2021)

Hyperspectral Technique Coupled With Chemometrics Methods for Predicting Alkali Spreading Value of Millet Flour

Guo-liang WANG^1、*, Ke-qiang YU^3、3;, Kai CHENG^2、2;, Xin LIU^2、2;, Wen-jun WANG^1、1;, Hong LI^2、2;, Er-hu GUO^2、2;, and Zhi-wei LI^{1、1; *;}

Author Affiliations

¹1. College of Agricultural Engineering, Shanxi Agricultural University, Taigu 030801, China

²2. Millet Research Institute, Shanxi Agricultural University, Changzhi 046000, China

³3. College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Average spectral curves of millet flour

Download full size

View in Article

Fig. 2. Selection of key variables using CARS algorithm
(a): Changing trend of the number of sampled variables; (b): Variation of root-mean-square error of cross-validation values;(c): Regression coefficients of each variable with the increasing of sampling runs

Download full size

View in Article

Fig. 3. Selection probabilities of each wavelength using RF algorithm

Download full size

View in Article

Fig. 4. The fit of training set and prediction set pretreated by MSC

Download full size

View in Article

Table 1. Statistic results of alkali spreadingvalues in millet flour
View table
View in Article
Table 1. Statistic results of alkali spreadingvalues in millet flour
Sample
Number Minimum
/℃ Maximum
/℃ Mean
/℃ Standard
deviation
358 75.25 84.25 79.65 1.98

Table 2. PLSR modeling results of different methods based on key wavelengths extraction
View table
View in Article
Table 2. PLSR modeling results of different methods based on key wavelengths extraction
Pretreatment Number of
variables R_c RMSEC R_p RMSEP
RAW 148 0.73 0.99 0.77 0.83
CARS 16 0.74 0.96 0.72 0.93
RF 10 0.7 1.03 0.7 0.90

Table 3. Analysis results of PLSR models by different pretreatments
View table
View in Article
Table 3. Analysis results of PLSR models by different pretreatments
Pretreatment R_c RMSEC R_p RMSEP
S-G 0.71 1.00 0.74 0.91
MSC 0.78 0.85 0.83 0.83
S-G+MSC 0.73 0.94 0.71 1.06

Table 4. PLSR predictive modeling results of different key wavelengths extractions pretreated by MSC
View table
View in Article
Table 4. PLSR predictive modeling results of different key wavelengths extractions pretreated by MSC
Pretreatment Number of
variables R_c RMSEC R_p RMSEP
CARS 10 0.74 0.99 0.7 0.83
RF 10 0.71 1.03 0.66 0.87

Tools

Get Citation

Copy Citation Text

Guo-liang WANG, Ke-qiang YU, Kai CHENG, Xin LIU, Wen-jun WANG, Hong LI, Er-hu GUO, Zhi-wei LI. Hyperspectral Technique Coupled With Chemometrics Methods for Predicting Alkali Spreading Value of Millet Flour[J]. Spectroscopy and Spectral Analysis, 2021, 41(10): 3189

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Research Articles

Received: Sep. 25, 2020

Accepted: --

Published Online: Oct. 29, 2021

The Author Email: WANG Guo-liang (wangguoliangwz@126.com)

DOI:10.3964/j.issn.1000-0593(2021)10-3189-05

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Statistic results of alkali spreadingvalues in millet flour

Table 1. Statistic results of alkali spreadingvalues in millet flour

Table 2. PLSR modeling results of different methods based on key wavelengths extraction

Table 2. PLSR modeling results of different methods based on key wavelengths extraction

Table 3. Analysis results of PLSR models by different pretreatments

Table 3. Analysis results of PLSR models by different pretreatments

Table 4. PLSR predictive modeling results of different key wavelengths extractions pretreated by MSC

Table 4. PLSR predictive modeling results of different key wavelengths extractions pretreated by MSC