Application of visible and near-infrared spectroscopy to classification of Miscanthus species

Xiaoli Jin, Xiaoling Chen, Liang Xiao, Chunhai Shi, Liang Chen, Bin Yu, Zili Yi, Ji Hye Yoo, Kweon Heo, Chang Yeon Yu, Toshihiko Yamada, Erik J. Sacks, Junhua Peng

Research output: Contribution to journalArticle

Abstract

The feasibility of visible and near infrared (NIR) spectroscopy as tool to classify Miscanthus samples was explored in this study. Three types of Miscanthus plants, namely, M. sinensis, M. sacchariflorus and M. fIoridulus, were analyzed using a NIR spectrophotometer. Several classification models based on the NIR spectra data were developed using line discriminated analysis (LDA), partial least squares (PLS), least squares support vector machine regression (LSSVR), radial basis function (RBF) and neural network (NN). The principal component analysis (PCA) presented rough classification with overlapping samples, while the models of LineLSSVR, RBFLSSVR and RBFNN presented almost same calibration and validation results. Due to the higher speed of LineLSSVR than RBFLSSVR and RBFNN, we selected the lineLSSVR model as a representative. In our study, the model based on lineLSSVR showed higher accuracy than LDA and PLS models. The total correct classification rates of 87.79 and 96.51%were observed based on LDA and PLS model in the testing set, respectively, while the lineLSSVR showed 99.42%of total correct classification rate. Meanwhile, the linLSSVR model in the testing set showed correct classification rate of 100, 100 and 96.77%for M. sinensis, M. sacchariflorus and M. fIoridulus, respectively. The linLSSVR model assigned 99.42%of samples to the right groups, except one M. fIoridulus sample. The results demonstrated that NIR spectra combined with a preliminary morphological classification could be an effective and reliable procedure for the classification of Miscanthus species.

Original languageEnglish (US)
Article numbere0171360
JournalPloS one
Volume12
Issue number4
DOIs
StatePublished - Mar 2017

Fingerprint

Miscanthus
Near infrared spectroscopy
Near-Infrared Spectroscopy
near-infrared spectroscopy
Least-Squares Analysis
least squares
Miscanthus sacchariflorus
Infrared spectrophotometers
Miscanthus sinensis
Infrared radiation
sampling
Radial basis function networks
Principal Component Analysis
spectrophotometers
Testing
Calibration
Principal component analysis
neural networks
Support vector machines
principal component analysis

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

Jin, X., Chen, X., Xiao, L., Shi, C., Chen, L., Yu, B., ... Peng, J. (2017). Application of visible and near-infrared spectroscopy to classification of Miscanthus species. PloS one, 12(4), [e0171360]. https://doi.org/10.1371/journal.pone.0171360

Application of visible and near-infrared spectroscopy to classification of Miscanthus species. / Jin, Xiaoli; Chen, Xiaoling; Xiao, Liang; Shi, Chunhai; Chen, Liang; Yu, Bin; Yi, Zili; Yoo, Ji Hye; Heo, Kweon; Yu, Chang Yeon; Yamada, Toshihiko; Sacks, Erik J.; Peng, Junhua.

In: PloS one, Vol. 12, No. 4, e0171360, 03.2017.

Research output: Contribution to journalArticle

Jin, X, Chen, X, Xiao, L, Shi, C, Chen, L, Yu, B, Yi, Z, Yoo, JH, Heo, K, Yu, CY, Yamada, T, Sacks, EJ & Peng, J 2017, 'Application of visible and near-infrared spectroscopy to classification of Miscanthus species', PloS one, vol. 12, no. 4, e0171360. https://doi.org/10.1371/journal.pone.0171360
Jin, Xiaoli ; Chen, Xiaoling ; Xiao, Liang ; Shi, Chunhai ; Chen, Liang ; Yu, Bin ; Yi, Zili ; Yoo, Ji Hye ; Heo, Kweon ; Yu, Chang Yeon ; Yamada, Toshihiko ; Sacks, Erik J. ; Peng, Junhua. / Application of visible and near-infrared spectroscopy to classification of Miscanthus species. In: PloS one. 2017 ; Vol. 12, No. 4.
@article{c0f0fa3baade40a6ba64c6d4bc8a2464,
title = "Application of visible and near-infrared spectroscopy to classification of Miscanthus species",
abstract = "The feasibility of visible and near infrared (NIR) spectroscopy as tool to classify Miscanthus samples was explored in this study. Three types of Miscanthus plants, namely, M. sinensis, M. sacchariflorus and M. fIoridulus, were analyzed using a NIR spectrophotometer. Several classification models based on the NIR spectra data were developed using line discriminated analysis (LDA), partial least squares (PLS), least squares support vector machine regression (LSSVR), radial basis function (RBF) and neural network (NN). The principal component analysis (PCA) presented rough classification with overlapping samples, while the models of LineLSSVR, RBFLSSVR and RBFNN presented almost same calibration and validation results. Due to the higher speed of LineLSSVR than RBFLSSVR and RBFNN, we selected the lineLSSVR model as a representative. In our study, the model based on lineLSSVR showed higher accuracy than LDA and PLS models. The total correct classification rates of 87.79 and 96.51{\%}were observed based on LDA and PLS model in the testing set, respectively, while the lineLSSVR showed 99.42{\%}of total correct classification rate. Meanwhile, the linLSSVR model in the testing set showed correct classification rate of 100, 100 and 96.77{\%}for M. sinensis, M. sacchariflorus and M. fIoridulus, respectively. The linLSSVR model assigned 99.42{\%}of samples to the right groups, except one M. fIoridulus sample. The results demonstrated that NIR spectra combined with a preliminary morphological classification could be an effective and reliable procedure for the classification of Miscanthus species.",
author = "Xiaoli Jin and Xiaoling Chen and Liang Xiao and Chunhai Shi and Liang Chen and Bin Yu and Zili Yi and Yoo, {Ji Hye} and Kweon Heo and Yu, {Chang Yeon} and Toshihiko Yamada and Sacks, {Erik J.} and Junhua Peng",
year = "2017",
month = "3",
doi = "10.1371/journal.pone.0171360",
language = "English (US)",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Application of visible and near-infrared spectroscopy to classification of Miscanthus species

AU - Jin, Xiaoli

AU - Chen, Xiaoling

AU - Xiao, Liang

AU - Shi, Chunhai

AU - Chen, Liang

AU - Yu, Bin

AU - Yi, Zili

AU - Yoo, Ji Hye

AU - Heo, Kweon

AU - Yu, Chang Yeon

AU - Yamada, Toshihiko

AU - Sacks, Erik J.

AU - Peng, Junhua

PY - 2017/3

Y1 - 2017/3

N2 - The feasibility of visible and near infrared (NIR) spectroscopy as tool to classify Miscanthus samples was explored in this study. Three types of Miscanthus plants, namely, M. sinensis, M. sacchariflorus and M. fIoridulus, were analyzed using a NIR spectrophotometer. Several classification models based on the NIR spectra data were developed using line discriminated analysis (LDA), partial least squares (PLS), least squares support vector machine regression (LSSVR), radial basis function (RBF) and neural network (NN). The principal component analysis (PCA) presented rough classification with overlapping samples, while the models of LineLSSVR, RBFLSSVR and RBFNN presented almost same calibration and validation results. Due to the higher speed of LineLSSVR than RBFLSSVR and RBFNN, we selected the lineLSSVR model as a representative. In our study, the model based on lineLSSVR showed higher accuracy than LDA and PLS models. The total correct classification rates of 87.79 and 96.51%were observed based on LDA and PLS model in the testing set, respectively, while the lineLSSVR showed 99.42%of total correct classification rate. Meanwhile, the linLSSVR model in the testing set showed correct classification rate of 100, 100 and 96.77%for M. sinensis, M. sacchariflorus and M. fIoridulus, respectively. The linLSSVR model assigned 99.42%of samples to the right groups, except one M. fIoridulus sample. The results demonstrated that NIR spectra combined with a preliminary morphological classification could be an effective and reliable procedure for the classification of Miscanthus species.

AB - The feasibility of visible and near infrared (NIR) spectroscopy as tool to classify Miscanthus samples was explored in this study. Three types of Miscanthus plants, namely, M. sinensis, M. sacchariflorus and M. fIoridulus, were analyzed using a NIR spectrophotometer. Several classification models based on the NIR spectra data were developed using line discriminated analysis (LDA), partial least squares (PLS), least squares support vector machine regression (LSSVR), radial basis function (RBF) and neural network (NN). The principal component analysis (PCA) presented rough classification with overlapping samples, while the models of LineLSSVR, RBFLSSVR and RBFNN presented almost same calibration and validation results. Due to the higher speed of LineLSSVR than RBFLSSVR and RBFNN, we selected the lineLSSVR model as a representative. In our study, the model based on lineLSSVR showed higher accuracy than LDA and PLS models. The total correct classification rates of 87.79 and 96.51%were observed based on LDA and PLS model in the testing set, respectively, while the lineLSSVR showed 99.42%of total correct classification rate. Meanwhile, the linLSSVR model in the testing set showed correct classification rate of 100, 100 and 96.77%for M. sinensis, M. sacchariflorus and M. fIoridulus, respectively. The linLSSVR model assigned 99.42%of samples to the right groups, except one M. fIoridulus sample. The results demonstrated that NIR spectra combined with a preliminary morphological classification could be an effective and reliable procedure for the classification of Miscanthus species.

UR - http://www.scopus.com/inward/record.url?scp=85016830253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016830253&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0171360

DO - 10.1371/journal.pone.0171360

M3 - Article

C2 - 28369059

AN - SCOPUS:85016830253

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0171360

ER -