Jump to main content
Jump to site search
PLANNED MAINTENANCE Close the message box

Scheduled maintenance work on Wednesday 22nd May 2019 from 11:00 AM to 1:00 PM (GMT).

During this time our website performance may be temporarily affected. We apologise for any inconvenience this might cause and thank you for your patience.



Molecular spectroscopic wavelength selection using combined interval partial least squares and correlation coefficient optimization

Abstract

Wavelength selection plays a vital role in employing near-infrared spectroscopy for analyzing samples. Existing wavelength selection algorithms present certain drawbacks that can be mitigated by combining algorithms. In this study, we employed a combination of algorithms to quantitatively analyze corn oil components using near-infrared spectroscopy data. We combined Savitzky-Golay (SG) preprocessing, correlation coefficient (CC) method, and synergy interval partial least squares (siPLS) algorithms to propose CC-SiPLS and CC-SG-SiPLS methods. The results of applying full-spectrum partial least squares (PLS), correlation coefficient partial least squares (CC-PLS), synergy interval partial least squares (SiPLS), CC-SiPLS, and CC-SG-SiPLS method to the near-infrared spectral wavelength selection were compared. The results showed that the mathematical models established from the spectral data after wavelength selection using CC, SiPLS, CC-SiPLS, and CC-SG-SiPLS were simplified, and the numbers of wavelengths were 33.6% (CC) and 14.3% (SiPLS), 11.1% (CC-SiPLS), and 6.3% (CC-SG-SiPLS) of that using the full spectrum. The prediction accuracy for predicting the oil content of corn was improved compared to PLS. CC-SG-SIPLS,wavelength selection algorithm combined with preprocessing method, reduced the number of wavelengths from 700 to 44. And, the model complexity was most simplified. The root mean square error in prediction (RMSEP) and relative percent deviation (RPD) were 0.0552 and 2.5706, respectively, demonstrating adequate prediction accuracy. This result indicates that a combination strategy provides a effective way for multiple waveband selection, and that CC-SG-SiPLS can provide high analysis accuracy using molecular absorption bands composed of several wavelength intervals, and is an effective and robust wavelength selection strategy.

Back to tab navigation

Publication details

The article was accepted on 15 May 2019 and first published on 16 May 2019


Article type: Paper
DOI: 10.1039/C9AY00898E
Anal. Methods, 2019, Accepted Manuscript

  •   Request permissions

    Molecular spectroscopic wavelength selection using combined interval partial least squares and correlation coefficient optimization

    W. JIANG, C. Lu, Y. Zhang, W. Ju, J. Wang and M. Xiao, Anal. Methods, 2019, Accepted Manuscript , DOI: 10.1039/C9AY00898E

Search articles by author

Spotlight

Advertisements