A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm

Madan Kumar Lakshmanan; Birte Boelt; René Gislum

doi:10.1177/09670335221138955

A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm

Madan Kumar Lakshmanan^*, Birte Boelt, René Gislum

^*Corresponding author af dette arbejde

Institut for Agroøkologi - Afgrødesundhed

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Abstract

This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds’ viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.

Originalsprog	Engelsk
Tidsskrift	Journal of Near Infrared Spectroscopy
Vol/bind	31
Nummer	1
Sider (fra-til)	24-32
Antal sider	9
ISSN	0967-0335
DOI	https://doi.org/10.1177/09670335221138955
Status	Udgivet - feb. 2023

Adgang til dokumentet

10.1177/09670335221138955

Citationsformater

@article{4a47792249f242f99088192bf9502d38,

title = "A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm",

abstract = "This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds{\textquoteright} viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.",

keywords = "seed quality assessment, near infrared spectroscopy, chemometrics, variable selection for data classification, successive projections algorithm",

author = "Lakshmanan, {Madan Kumar} and Birte Boelt and Ren{\'e} Gislum",

year = "2023",

month = feb,

doi = "10.1177/09670335221138955",

language = "English",

volume = "31",

pages = "24--32",

journal = "Journal of Near Infrared Spectroscopy",

issn = "0967-0335",

publisher = "N I R Publications",

number = "1",

}

A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm. / Lakshmanan, Madan Kumar; Boelt, Birte ; Gislum, René.
I: Journal of Near Infrared Spectroscopy, Bind 31, Nr. 1, 02.2023, s. 24-32.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

TY - JOUR

T1 - A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm

AU - Lakshmanan, Madan Kumar

AU - Boelt, Birte

AU - Gislum, René

PY - 2023/2

Y1 - 2023/2

N2 - This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds’ viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.

AB - This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds’ viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.

KW - seed quality assessment

KW - near infrared spectroscopy

KW - chemometrics

KW - variable selection for data classification

KW - successive projections algorithm

U2 - 10.1177/09670335221138955

DO - 10.1177/09670335221138955

M3 - Journal article

SN - 0967-0335

VL - 31

SP - 24

EP - 32

JO - Journal of Near Infrared Spectroscopy

JF - Journal of Near Infrared Spectroscopy

IS - 1

ER -

A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater