Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products

Demelza Robinson; Qi Chen; Bing Xue; Daniel Killeen; Sara J. Fraser-Miller; Keith C. Gordon; Indrawati Oey; Mengjie Zhang

doi:10.1109/CEC45853.2021.9504794

Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products

Demelza Robinson, Qi Chen, Bing Xue, Daniel Killeen, Sara J. Fraser-Miller, Keith C. Gordon, Indrawati Oey, Mengjie Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Vibrational spectroscopy can be used for rapid determination of chemical quality markers in horticultural produce to improve quality control, optimize harvest times and maximize profits. Most commonly, spectral data are calibrated against chemical reference data (acquired using traditional, slower analytical methods) using partial least squares regression (PLSR). However, predictive performance of PLSR can be limited by the small number of instances, high dimensionality and collinearity of spectroscopic data. Here, a new genetic algorithm (GA) for PLSR feature and latent variable selection is proposed to predict concentrations of 18 important bioactive components across three New Zealand horticultural products from infrared, near-infrared and Raman spectral data sets. Models generated using the GA-enhanced PLSR method have notably better generalization and are less complex than the standard PLSR method. GA-enhanced PLSR models are produced from each spectroscopic data set individually, and from a data set that combines all three techniques.

Original language	English
Title of host publication	2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings
Place of Publication	Danvers, MA
Publisher	Institute of Electrical and Electronics Engineers
Pages	272-279
Number of pages	8
ISBN (Electronic)	978-1-7281-8393-0
ISBN (Print)	978-1-7281-8394-7
DOIs	https://doi.org/10.1109/CEC45853.2021.9504794
Publication status	Published - Aug 2021
Externally published	Yes
Event	2021 IEEE Congress on Evolutionary Computation - Virtual, Krakow, Poland Duration: 28 Jun 2021 → 1 Jul 2021

Publication series

Name	2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings

Conference

Conference	2021 IEEE Congress on Evolutionary Computation
Abbreviated title	CEC 2021
Country/Territory	Poland
City	Krakow
Period	28/06/21 → 1/07/21

Keywords

Feature selection
Genetic algorithm
Partial least squares regression
Vibrational spectroscopy
Chemical analysis
Feature extraction
Infrared devices
Least squares approximations
Chemical quality
Data set
Feature variable
Features selection
Horticultural products
Latent variable
Least square regression method
Partial least square regression
Spectroscopic data
Variables selections
Genetic algorithms

Access to Document

10.1109/CEC45853.2021.9504794Licence: In Copyright

Cite this

Robinson, D., Chen, Q., Xue, B., Killeen, D., Fraser-Miller, S. J., Gordon, K. C., Oey, I., & Zhang, M. (2021). Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products. In 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings (pp. 272-279). (2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CEC45853.2021.9504794

Robinson, Demelza ; Chen, Qi ; Xue, Bing et al. / Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products. 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings. Danvers, MA : Institute of Electrical and Electronics Engineers, 2021. pp. 272-279 (2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings).

@inproceedings{e4ad059d2e3a4753b0673edfbc462bb2,

title = "Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products",

abstract = "Vibrational spectroscopy can be used for rapid determination of chemical quality markers in horticultural produce to improve quality control, optimize harvest times and maximize profits. Most commonly, spectral data are calibrated against chemical reference data (acquired using traditional, slower analytical methods) using partial least squares regression (PLSR). However, predictive performance of PLSR can be limited by the small number of instances, high dimensionality and collinearity of spectroscopic data. Here, a new genetic algorithm (GA) for PLSR feature and latent variable selection is proposed to predict concentrations of 18 important bioactive components across three New Zealand horticultural products from infrared, near-infrared and Raman spectral data sets. Models generated using the GA-enhanced PLSR method have notably better generalization and are less complex than the standard PLSR method. GA-enhanced PLSR models are produced from each spectroscopic data set individually, and from a data set that combines all three techniques. ",

keywords = "Feature selection, Genetic algorithm, Partial least squares regression, Vibrational spectroscopy, Chemical analysis, Feature extraction, Infrared devices, Least squares approximations, Chemical quality, Data set, Feature variable, Features selection, Horticultural products, Latent variable, Least square regression method, Partial least square regression, Spectroscopic data, Variables selections, Genetic algorithms",

author = "Demelza Robinson and Qi Chen and Bing Xue and Daniel Killeen and Fraser-Miller, {Sara J.} and Gordon, {Keith C.} and Indrawati Oey and Mengjie Zhang",

year = "2021",

month = aug,

doi = "10.1109/CEC45853.2021.9504794",

language = "English",

isbn = "978-1-7281-8394-7",

series = "2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "272--279",

booktitle = "2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings",

address = "United States",

note = "2021 IEEE Congress on Evolutionary Computation, CEC 2021 ; Conference date: 28-06-2021 Through 01-07-2021",

}

Robinson, D, Chen, Q, Xue, B, Killeen, D, Fraser-Miller, SJ, Gordon, KC, Oey, I & Zhang, M 2021, Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products. in 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings. 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings, Institute of Electrical and Electronics Engineers, Danvers, MA, pp. 272-279, 2021 IEEE Congress on Evolutionary Computation, Krakow, Poland, 28/06/21. https://doi.org/10.1109/CEC45853.2021.9504794

Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products. / Robinson, Demelza; Chen, Qi; Xue, Bing et al.
2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings. Danvers, MA: Institute of Electrical and Electronics Engineers, 2021. p. 272-279 (2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products

AU - Robinson, Demelza

AU - Chen, Qi

AU - Xue, Bing

AU - Killeen, Daniel

AU - Fraser-Miller, Sara J.

AU - Gordon, Keith C.

AU - Oey, Indrawati

AU - Zhang, Mengjie

PY - 2021/8

Y1 - 2021/8

N2 - Vibrational spectroscopy can be used for rapid determination of chemical quality markers in horticultural produce to improve quality control, optimize harvest times and maximize profits. Most commonly, spectral data are calibrated against chemical reference data (acquired using traditional, slower analytical methods) using partial least squares regression (PLSR). However, predictive performance of PLSR can be limited by the small number of instances, high dimensionality and collinearity of spectroscopic data. Here, a new genetic algorithm (GA) for PLSR feature and latent variable selection is proposed to predict concentrations of 18 important bioactive components across three New Zealand horticultural products from infrared, near-infrared and Raman spectral data sets. Models generated using the GA-enhanced PLSR method have notably better generalization and are less complex than the standard PLSR method. GA-enhanced PLSR models are produced from each spectroscopic data set individually, and from a data set that combines all three techniques.

AB - Vibrational spectroscopy can be used for rapid determination of chemical quality markers in horticultural produce to improve quality control, optimize harvest times and maximize profits. Most commonly, spectral data are calibrated against chemical reference data (acquired using traditional, slower analytical methods) using partial least squares regression (PLSR). However, predictive performance of PLSR can be limited by the small number of instances, high dimensionality and collinearity of spectroscopic data. Here, a new genetic algorithm (GA) for PLSR feature and latent variable selection is proposed to predict concentrations of 18 important bioactive components across three New Zealand horticultural products from infrared, near-infrared and Raman spectral data sets. Models generated using the GA-enhanced PLSR method have notably better generalization and are less complex than the standard PLSR method. GA-enhanced PLSR models are produced from each spectroscopic data set individually, and from a data set that combines all three techniques.

KW - Feature selection

KW - Genetic algorithm

KW - Partial least squares regression

KW - Vibrational spectroscopy

KW - Chemical analysis

KW - Feature extraction

KW - Infrared devices

KW - Least squares approximations

KW - Chemical quality

KW - Data set

KW - Feature variable

KW - Features selection

KW - Horticultural products

KW - Latent variable

KW - Least square regression method

KW - Partial least square regression

KW - Spectroscopic data

KW - Variables selections

KW - Genetic algorithms

UR - http://www.scopus.com/inward/record.url?scp=85124595297&partnerID=8YFLogxK

U2 - 10.1109/CEC45853.2021.9504794

DO - 10.1109/CEC45853.2021.9504794

M3 - Conference contribution

SN - 978-1-7281-8394-7

T3 - 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings

SP - 272

EP - 279

BT - 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Danvers, MA

T2 - 2021 IEEE Congress on Evolutionary Computation

Y2 - 28 June 2021 through 1 July 2021

ER -

Robinson D, Chen Q, Xue B, Killeen D, Fraser-Miller SJ, Gordon KC et al. Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products. In 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings. Danvers, MA: Institute of Electrical and Electronics Engineers. 2021. p. 272-279. (2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings). doi: 10.1109/CEC45853.2021.9504794

Genetic Algorithm for Feature and Latent Variable Selection for Nutrient Assessment in Horticultural Products

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this