Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data

The influence of different data pre-processing methods (smoothing by moving average (MA), multiplicative scatter correction (MSC), Savitzky-Golay (SG), standard normal variate (SNV) and mean normalization (MN) on the prediction of sugar content from sugarcane samples was investigated. The performanc...

Full description

Bibliographic Details
Main Authors: Mat Lazim, Siti Saripa Rabiah, Mat Nawi, Nazmi, Chen, Guangnan, Jensen, Troy, Md Rasli, Ahmad Muslim
Format: Article
Language:English
Published: Faculty of Food Science and Technology, Universiti Putra Malaysia 2016
Online Access:http://psasir.upm.edu.my/id/eprint/50542/
http://psasir.upm.edu.my/id/eprint/50542/1/%2833%29%20IFRJ-16411%20%20Nawi.pdf
_version_ 1848851584414384128
author Mat Lazim, Siti Saripa Rabiah
Mat Nawi, Nazmi
Chen, Guangnan
Jensen, Troy
Md Rasli, Ahmad Muslim
author_facet Mat Lazim, Siti Saripa Rabiah
Mat Nawi, Nazmi
Chen, Guangnan
Jensen, Troy
Md Rasli, Ahmad Muslim
author_sort Mat Lazim, Siti Saripa Rabiah
building UPM Institutional Repository
collection Online Access
description The influence of different data pre-processing methods (smoothing by moving average (MA), multiplicative scatter correction (MSC), Savitzky-Golay (SG), standard normal variate (SNV) and mean normalization (MN) on the prediction of sugar content from sugarcane samples was investigated. The performance of these pre-processing methods was evaluated using spectral data collected from 292 sugarcane internode samples using a visible-shortwave near infrared spectroradiometer (VNIRS). Partial least square (PLS) method was applied to develop both calibration and prediction models for the samples. If no pre-processing method was applied, the coefficient of determination (R2) values for both reflectance and absorbance data were 0.81 and 0.86 respectively. The highest prediction accuracy values were obtained when the data was treated with MSC method, where the R2 values for reflectance and absorbance being 0.85 and 0.87, respectively. From this study, it was concluded that pre-processing can improve the model performances where MSC method was found to give the highest prediction accuracy value.
first_indexed 2025-11-15T10:24:30Z
format Article
id upm-50542
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:24:30Z
publishDate 2016
publisher Faculty of Food Science and Technology, Universiti Putra Malaysia
recordtype eprints
repository_type Digital Repository
spelling upm-505422017-02-28T04:58:42Z http://psasir.upm.edu.my/id/eprint/50542/ Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data Mat Lazim, Siti Saripa Rabiah Mat Nawi, Nazmi Chen, Guangnan Jensen, Troy Md Rasli, Ahmad Muslim The influence of different data pre-processing methods (smoothing by moving average (MA), multiplicative scatter correction (MSC), Savitzky-Golay (SG), standard normal variate (SNV) and mean normalization (MN) on the prediction of sugar content from sugarcane samples was investigated. The performance of these pre-processing methods was evaluated using spectral data collected from 292 sugarcane internode samples using a visible-shortwave near infrared spectroradiometer (VNIRS). Partial least square (PLS) method was applied to develop both calibration and prediction models for the samples. If no pre-processing method was applied, the coefficient of determination (R2) values for both reflectance and absorbance data were 0.81 and 0.86 respectively. The highest prediction accuracy values were obtained when the data was treated with MSC method, where the R2 values for reflectance and absorbance being 0.85 and 0.87, respectively. From this study, it was concluded that pre-processing can improve the model performances where MSC method was found to give the highest prediction accuracy value. Faculty of Food Science and Technology, Universiti Putra Malaysia 2016 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/50542/1/%2833%29%20IFRJ-16411%20%20Nawi.pdf Mat Lazim, Siti Saripa Rabiah and Mat Nawi, Nazmi and Chen, Guangnan and Jensen, Troy and Md Rasli, Ahmad Muslim (2016) Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data. International Food Research Journal, 23 (suppl.). S231-S236. ISSN 1985-4668; ESSN: 2231-7546 http://www.ifrj.upm.edu.my/23%20(06)%202016%20supplementary/(33)%20IFRJ-16411%20%20Nawi.pdf
spellingShingle Mat Lazim, Siti Saripa Rabiah
Mat Nawi, Nazmi
Chen, Guangnan
Jensen, Troy
Md Rasli, Ahmad Muslim
Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title_full Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title_fullStr Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title_full_unstemmed Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title_short Influence of different pre-processing methods in predicting sugarcane quality from near-infrared (NIR) spectral data
title_sort influence of different pre-processing methods in predicting sugarcane quality from near-infrared (nir) spectral data
url http://psasir.upm.edu.my/id/eprint/50542/
http://psasir.upm.edu.my/id/eprint/50542/
http://psasir.upm.edu.my/id/eprint/50542/1/%2833%29%20IFRJ-16411%20%20Nawi.pdf