Limits...
Characterization of wheat varieties using terahertz time-domain spectroscopy.

Ge H, Jiang Y, Lian F, Zhang Y, Xia S - Sensors (Basel) (2015)

Bottom Line: Using partial least squares (PLS), a regression model for discriminating wheat varieties was developed.The coefficient of correlation in cross validation (R) and root-mean-square error of cross validation (RMSECV) were 0.985 and 1.162, respectively.In addition, interval PLS was applied to optimize the models by selecting the most appropriate regions in the spectra, improving the prediction accuracy (R = 0.992 and RMSECV = 0.967).

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Transducer Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing 100080, China. gehongyi2004@163.com.

ABSTRACT
Terahertz (THz) spectroscopy and multivariate data analysis were explored to discriminate eight wheat varieties. The absorption spectra were measured using THz time-domain spectroscopy from 0.2 to 2.0 THz. Using partial least squares (PLS), a regression model for discriminating wheat varieties was developed. The coefficient of correlation in cross validation (R) and root-mean-square error of cross validation (RMSECV) were 0.985 and 1.162, respectively. In addition, interval PLS was applied to optimize the models by selecting the most appropriate regions in the spectra, improving the prediction accuracy (R = 0.992 and RMSECV = 0.967). Results demonstrate that THz spectroscopy combined with multivariate analysis can provide rapid, nondestructive discrimination of wheat varieties.

Show MeSH

Related in: MedlinePlus

The iPLS results for the THz spectra data. The columns indicate the RMSECV in each subinterval, and the mean absorption spectrum of the wheat samples is overlaid on the plot.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4507591&req=5

sensors-15-12560-f005: The iPLS results for the THz spectra data. The columns indicate the RMSECV in each subinterval, and the mean absorption spectrum of the wheat samples is overlaid on the plot.

Mentions: For comparison, iPLS analysis was also performed using the same absorption spectral data sets to improve the model performance. First, the full spectrum was divided into 16 equal subintervals with eight variables. Calibration models were developed for each of the 16 intervals. Then, cross-validation was performed for each of the 16 models. Figure 5 presents the iPLS variable selection results for the discrimination of wheat varieties.


Characterization of wheat varieties using terahertz time-domain spectroscopy.

Ge H, Jiang Y, Lian F, Zhang Y, Xia S - Sensors (Basel) (2015)

The iPLS results for the THz spectra data. The columns indicate the RMSECV in each subinterval, and the mean absorption spectrum of the wheat samples is overlaid on the plot.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4507591&req=5

sensors-15-12560-f005: The iPLS results for the THz spectra data. The columns indicate the RMSECV in each subinterval, and the mean absorption spectrum of the wheat samples is overlaid on the plot.
Mentions: For comparison, iPLS analysis was also performed using the same absorption spectral data sets to improve the model performance. First, the full spectrum was divided into 16 equal subintervals with eight variables. Calibration models were developed for each of the 16 intervals. Then, cross-validation was performed for each of the 16 models. Figure 5 presents the iPLS variable selection results for the discrimination of wheat varieties.

Bottom Line: Using partial least squares (PLS), a regression model for discriminating wheat varieties was developed.The coefficient of correlation in cross validation (R) and root-mean-square error of cross validation (RMSECV) were 0.985 and 1.162, respectively.In addition, interval PLS was applied to optimize the models by selecting the most appropriate regions in the spectra, improving the prediction accuracy (R = 0.992 and RMSECV = 0.967).

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Transducer Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing 100080, China. gehongyi2004@163.com.

ABSTRACT
Terahertz (THz) spectroscopy and multivariate data analysis were explored to discriminate eight wheat varieties. The absorption spectra were measured using THz time-domain spectroscopy from 0.2 to 2.0 THz. Using partial least squares (PLS), a regression model for discriminating wheat varieties was developed. The coefficient of correlation in cross validation (R) and root-mean-square error of cross validation (RMSECV) were 0.985 and 1.162, respectively. In addition, interval PLS was applied to optimize the models by selecting the most appropriate regions in the spectra, improving the prediction accuracy (R = 0.992 and RMSECV = 0.967). Results demonstrate that THz spectroscopy combined with multivariate analysis can provide rapid, nondestructive discrimination of wheat varieties.

Show MeSH
Related in: MedlinePlus