Next Article in Journal
Field Demonstration of Real-Time Wind Turbine Foundation Strain Monitoring
Next Article in Special Issue
Exploring the Efficacy of Platinum and Palladium Nanostructures for Organic Molecule Detection via Raman Spectroscopy
Previous Article in Journal
A Novel Approach to Monitoring the Curing of Epoxy in Closed Tools by Use of Ultrasonic Spectroscopy
Previous Article in Special Issue
Remotely Exploring Deeper-Into-Matter by Non-Contact Detection of Audible Transients Excited by Laser Radiation
Article Menu
Issue 1 (January) cover image

Export Article

Open AccessArticle
Sensors 2018, 18(1), 95;

Identification of Coffee Varieties Using Laser-Induced Breakdown Spectroscopy and Chemometrics

1,2,* and 1,2
College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China
Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture, Hangzhou 310058, China
Author to whom correspondence should be addressed.
Received: 7 November 2017 / Revised: 13 December 2017 / Accepted: 27 December 2017 / Published: 31 December 2017
(This article belongs to the Special Issue Spectroscopy Based Sensors)
Full-Text   |   PDF [2438 KB, uploaded 31 December 2017]   |  


We linked coffee quality to its different varieties. This is of interest because the identification of coffee varieties should help coffee trading and consumption. Laser-induced breakdown spectroscopy (LIBS) combined with chemometric methods was used to identify coffee varieties. Wavelet transform (WT) was used to reduce LIBS spectra noise. Partial least squares-discriminant analysis (PLS-DA), radial basis function neural network (RBFNN), and support vector machine (SVM) were used to build classification models. Loadings of principal component analysis (PCA) were used to select the spectral variables contributing most to the identification of coffee varieties. Twenty wavelength variables corresponding to C I, Mg I, Mg II, Al II, CN, H, Ca II, Fe I, K I, Na I, N I, and O I were selected. PLS-DA, RBFNN, and SVM models on selected wavelength variables showed acceptable results. SVM and RBFNN models performed better with a classification accuracy of over 80% in the prediction set, for both full spectra and the selected variables. The overall results indicated that it was feasible to use LIBS and chemometric methods to identify coffee varieties. For further studies, more samples are needed to produce robust classification models, research should be conducted on which methods to use to select spectral peaks that correspond to the elements contributing most to identification, and the methods for acquiring stable spectra should also be studied. View Full-Text
Keywords: coffee varieties; laser-induced breakdown spectroscopy; discrimination; chemometrics; wavelength selection coffee varieties; laser-induced breakdown spectroscopy; discrimination; chemometrics; wavelength selection

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Zhang, C.; Shen, T.; Liu, F.; He, Y. Identification of Coffee Varieties Using Laser-Induced Breakdown Spectroscopy and Chemometrics. Sensors 2018, 18, 95.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top