A comparison of principal component regression and artificial neural network in fruits quality prediction

Generally, non-linear predictive models should be superior to linear predictive models. The objective of this study is to compare the performance of soluble solid content (SSC) prediction via Artificial Neural Network with Principal Components (PCs-ANN) and Principal Component Regression (PCR) in Vi...

Full description

Saved in:
Bibliographic Details
Main Authors: Kim, Seng Chia, Abdul Rahim, Herlina, Abdul Rahim, Ruzairi
Format: Conference or Workshop Item
Published: 2011
Online Access:http://eprints.utm.my/id/eprint/45475/
http://dx.doi.org/10.1109/CSPA.2011.5759884
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.45475
record_format eprints
spelling my.utm.454752017-09-20T00:45:50Z http://eprints.utm.my/id/eprint/45475/ A comparison of principal component regression and artificial neural network in fruits quality prediction Kim, Seng Chia Abdul Rahim, Herlina Abdul Rahim, Ruzairi Generally, non-linear predictive models should be superior to linear predictive models. The objective of this study is to compare the performance of soluble solid content (SSC) prediction via Artificial Neural Network with Principal Components (PCs-ANN) and Principal Component Regression (PCR) in Visible and Shortwave Near Infrared (VIS-SWNIR) (400 - 1000 nm) spectrum. The spectra of 116 Fuji Apple samples were separated into calibration set of 84 apple samples and testing set of 32 apple samples randomly. Firstly, multiplicative scattering correction (MSC) was used to pre-process the spectra. Secondly, Principal Component Regression (PCR) was used to obtain the optimal number of principal components (PCs). Thirdly, the optimal PCs were used as the inputs of both multiple linear regression (MLR) and Artificial Neural Network (ANN) models. The results from this study showed that the predictive performance was improved significantly when PCs-ANN with two neurons was used compared to the PCR. 2011 Conference or Workshop Item PeerReviewed Kim, Seng Chia and Abdul Rahim, Herlina and Abdul Rahim, Ruzairi (2011) A comparison of principal component regression and artificial neural network in fruits quality prediction. In: IEEE 7th International Colloqium On Signal Processing And Its Applications (CSPA). http://dx.doi.org/10.1109/CSPA.2011.5759884
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
description Generally, non-linear predictive models should be superior to linear predictive models. The objective of this study is to compare the performance of soluble solid content (SSC) prediction via Artificial Neural Network with Principal Components (PCs-ANN) and Principal Component Regression (PCR) in Visible and Shortwave Near Infrared (VIS-SWNIR) (400 - 1000 nm) spectrum. The spectra of 116 Fuji Apple samples were separated into calibration set of 84 apple samples and testing set of 32 apple samples randomly. Firstly, multiplicative scattering correction (MSC) was used to pre-process the spectra. Secondly, Principal Component Regression (PCR) was used to obtain the optimal number of principal components (PCs). Thirdly, the optimal PCs were used as the inputs of both multiple linear regression (MLR) and Artificial Neural Network (ANN) models. The results from this study showed that the predictive performance was improved significantly when PCs-ANN with two neurons was used compared to the PCR.
format Conference or Workshop Item
author Kim, Seng Chia
Abdul Rahim, Herlina
Abdul Rahim, Ruzairi
spellingShingle Kim, Seng Chia
Abdul Rahim, Herlina
Abdul Rahim, Ruzairi
A comparison of principal component regression and artificial neural network in fruits quality prediction
author_facet Kim, Seng Chia
Abdul Rahim, Herlina
Abdul Rahim, Ruzairi
author_sort Kim, Seng Chia
title A comparison of principal component regression and artificial neural network in fruits quality prediction
title_short A comparison of principal component regression and artificial neural network in fruits quality prediction
title_full A comparison of principal component regression and artificial neural network in fruits quality prediction
title_fullStr A comparison of principal component regression and artificial neural network in fruits quality prediction
title_full_unstemmed A comparison of principal component regression and artificial neural network in fruits quality prediction
title_sort comparison of principal component regression and artificial neural network in fruits quality prediction
publishDate 2011
url http://eprints.utm.my/id/eprint/45475/
http://dx.doi.org/10.1109/CSPA.2011.5759884
_version_ 1643651751722614784
score 13.154949