Share Email Print

Proceedings Paper

Near infrared spectrometric technique for testing fruit quality: optimisation of regression models using genetic algorithms
Author(s): J. Frédéric Isingizwe Nturambirwe; Willem J. Perold; Umezuruike L. Opara
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Near infrared (NIR) spectroscopy has gained extensive use in quality evaluation. It is arguably one of the most advanced spectroscopic tools in non-destructive quality testing of food stuff, from measurement to data analysis and interpretation. NIR spectral data are interpreted through means often involving multivariate statistical analysis, sometimes associated with optimisation techniques for model improvement. The objective of this research was to explore the extent to which genetic algorithms (GA) can be used to enhance model development, for predicting fruit quality.

Apple fruits were used, and NIR spectra in the range from 12000 to 4000 cm-1 were acquired on both bruised and healthy tissues, with different degrees of mechanical damage. GAs were used in combination with partial least squares regression methods to develop bruise severity prediction models, and compared to PLS models developed using the full NIR spectrum.

A classification model was developed, which clearly separated bruised from unbruised apple tissue. GAs helped improve prediction models by over 10%, in comparison with full spectrum-based models, as evaluated in terms of error of prediction (Root Mean Square Error of Cross-validation). PLS models to predict internal quality, such as sugar content and acidity were developed and compared to the versions optimized by genetic algorithm. Overall, the results highlighted the potential use of GA method to improve speed and accuracy of fruit quality prediction.

Paper Details

Date Published: 3 February 2017
PDF: 7 pages
Proc. SPIE 10036, Fourth Conference on Sensors, MEMS, and Electro-Optic Systems, 100360N (3 February 2017); doi: 10.1117/12.2244535
Show Author Affiliations
J. Frédéric Isingizwe Nturambirwe, Stellenbosch Univ. (South Africa)
Willem J. Perold, Stellenbosch Univ. (South Africa)
Umezuruike L. Opara, Stellenbosch Univ. (South Africa)

Published in SPIE Proceedings Vol. 10036:
Fourth Conference on Sensors, MEMS, and Electro-Optic Systems
Monuko du Plessis, Editor(s)

© SPIE. Terms of Use
Back to Top