Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison
Visible and near infrared spectroscopy is a non-destructive, green, and rapid technology that can be utilized to estimate the components of interest without conditioning it, as compared with classical analytical methods. The objective of this paper is to compare the performance of artificial neural...
Main Authors: | , , |
---|---|
Format: | Article |
Published: |
Springer International Publishing
2012
|
Subjects: |
_version_ | 1796859169133821952 |
---|---|
author | Chia, Kim Seng Abdul Rahim, Herlina Abdul Rahim, Ruzairi |
author_facet | Chia, Kim Seng Abdul Rahim, Herlina Abdul Rahim, Ruzairi |
author_sort | Chia, Kim Seng |
collection | ePrints |
description | Visible and near infrared spectroscopy is a non-destructive, green, and rapid technology that can be utilized to estimate the components of interest without conditioning it, as compared with classical analytical methods. The objective of this paper is to compare the performance of artificial neural network (ANN) (a nonlinear model) and principal component regression (PCR) (a linear model) based on visible and shortwave near infrared (VIS-SWNIR) (400-1000 nm) spectra in the non-destructive soluble solids content measurement of an apple. First, we used multiplicative scattering correction to pre-process the spectral data. Second, PCR was applied to estimate the optimal number of input variables. Third, the input variables with an optimal amount were used as the inputs of both multiple linear regression and ANN models. The initial weights and the number of hidden neurons were adjusted to optimize the performance of ANN. Findings suggest that the predictive performance of ANN with two hidden neurons outperforms that of PCR. |
first_indexed | 2024-03-05T19:23:12Z |
format | Article |
id | utm.eprints-47583 |
institution | Universiti Teknologi Malaysia - ePrints |
last_indexed | 2024-03-05T19:23:12Z |
publishDate | 2012 |
publisher | Springer International Publishing |
record_format | dspace |
spelling | utm.eprints-475832020-02-29T13:48:57Z http://eprints.utm.my/47583/ Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison Chia, Kim Seng Abdul Rahim, Herlina Abdul Rahim, Ruzairi Q Science Visible and near infrared spectroscopy is a non-destructive, green, and rapid technology that can be utilized to estimate the components of interest without conditioning it, as compared with classical analytical methods. The objective of this paper is to compare the performance of artificial neural network (ANN) (a nonlinear model) and principal component regression (PCR) (a linear model) based on visible and shortwave near infrared (VIS-SWNIR) (400-1000 nm) spectra in the non-destructive soluble solids content measurement of an apple. First, we used multiplicative scattering correction to pre-process the spectral data. Second, PCR was applied to estimate the optimal number of input variables. Third, the input variables with an optimal amount were used as the inputs of both multiple linear regression and ANN models. The initial weights and the number of hidden neurons were adjusted to optimize the performance of ANN. Findings suggest that the predictive performance of ANN with two hidden neurons outperforms that of PCR. Springer International Publishing 2012 Article PeerReviewed Chia, Kim Seng and Abdul Rahim, Herlina and Abdul Rahim, Ruzairi (2012) Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison. Journal of Zheijiang University-Science B, 13 (2). pp. 145-151. ISSN 1673-1581 https://dx.doi.org/10.1631/jzus.B11c0150 DOI:10.1631/jzus.B11c0150 |
spellingShingle | Q Science Chia, Kim Seng Abdul Rahim, Herlina Abdul Rahim, Ruzairi Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title | Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title_full | Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title_fullStr | Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title_full_unstemmed | Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title_short | Technical report: neural network and principal component regression in non-destructive soluble solids content assessment: a comparison |
title_sort | technical report neural network and principal component regression in non destructive soluble solids content assessment a comparison |
topic | Q Science |
work_keys_str_mv | AT chiakimseng technicalreportneuralnetworkandprincipalcomponentregressioninnondestructivesolublesolidscontentassessmentacomparison AT abdulrahimherlina technicalreportneuralnetworkandprincipalcomponentregressioninnondestructivesolublesolidscontentassessmentacomparison AT abdulrahimruzairi technicalreportneuralnetworkandprincipalcomponentregressioninnondestructivesolublesolidscontentassessmentacomparison |