Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization
Spectrometric methods based on near infrared radiation (NIR) are commonly used effectively in the agricultural and food industry. However, these methods still face limitations whereby meeting requirements for application such as nondestructive quality testing of large fruits and automated sorting an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-05-01
|
| Series: | Scientific African |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468227618302278 |
| _version_ | 1819113700316938240 |
|---|---|
| author | Jean Frederic Isingizwe Nturambirwe Helene H. Nieuwoudt Willem J. Perold Umezuruike Linus Opara |
| author_facet | Jean Frederic Isingizwe Nturambirwe Helene H. Nieuwoudt Willem J. Perold Umezuruike Linus Opara |
| author_sort | Jean Frederic Isingizwe Nturambirwe |
| collection | DOAJ |
| description | Spectrometric methods based on near infrared radiation (NIR) are commonly used effectively in the agricultural and food industry. However, these methods still face limitations whereby meeting requirements for application such as nondestructive quality testing of large fruits and automated sorting and grading is still a challenge. A Fourier transform (FT)-NIR spectrometer (emission head, EH mode of Matrix-F) that simulates on-line sample scanning (contactless, large sample size (100 mm)) was used to predict internal properties of apple fruit. The EH was compared to laboratory multipurpose analyzer (MPA) FT-NIR spectrometer using two contact-sample presentation modes with relatively smaller sample size (≤22 mm); namely, the integrating sphere (IS) and the solid probe (SP). Three apple cultivars (Golden Delicious, Granny Smith and Royal Gala) sourced from two retail stores (in Stellenbosch, South Africa) were used to constitute variability in the sample set. Partial least squares regression (PLSR) prediction models for internal quality (total soluble solids (TSS) and titratable acidity (TA)) were developed and validated on external test samples in various scenarios. Genetic algorithm (GA) based optimization of PLS models was used to produce optimal models prior to instrumental comparison.Model optimization using GA improved performance by a margin of 30% of the original root mean square error of cross validation for the contactless system bringing it closer to the performance of models from the MPA. The EH's performance makes it an attractive option for achieving on-line application of NIR spectroscopy for sorting apples based on internal quality. Keywords: FT-NIR, Calibration transfer, Model performance, Genetic algorithm, Apple quality |
| first_indexed | 2024-12-22T04:33:34Z |
| format | Article |
| id | doaj.art-5e84b6753c2448faac264106c17ff8df |
| institution | Directory Open Access Journal |
| issn | 2468-2276 |
| language | English |
| last_indexed | 2024-12-22T04:33:34Z |
| publishDate | 2019-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Scientific African |
| spelling | doaj.art-5e84b6753c2448faac264106c17ff8df2022-12-21T18:38:58ZengElsevierScientific African2468-22762019-05-013Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimizationJean Frederic Isingizwe Nturambirwe0Helene H. Nieuwoudt1Willem J. Perold2Umezuruike Linus Opara3Department of Electrical and Electronic Engineering, Stellenbosch University, Private Bag X1, Matieland 7602, South Africa; Postharvest Technology Research Laboratory, South African Research Chair in Postharvest Technology, Department of Horticultural Science, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South AfricaInstitute for Wine Biotechnology, Department of Viticulture and Oenology, Stellenbosch University, Private Bag X1, Matieland 7602, South AfricaDepartment of Electrical and Electronic Engineering, Stellenbosch University, Private Bag X1, Matieland 7602, South AfricaPostharvest Technology Research Laboratory, South African Research Chair in Postharvest Technology, Department of Horticultural Science, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa; Corresponding author.Spectrometric methods based on near infrared radiation (NIR) are commonly used effectively in the agricultural and food industry. However, these methods still face limitations whereby meeting requirements for application such as nondestructive quality testing of large fruits and automated sorting and grading is still a challenge. A Fourier transform (FT)-NIR spectrometer (emission head, EH mode of Matrix-F) that simulates on-line sample scanning (contactless, large sample size (100 mm)) was used to predict internal properties of apple fruit. The EH was compared to laboratory multipurpose analyzer (MPA) FT-NIR spectrometer using two contact-sample presentation modes with relatively smaller sample size (≤22 mm); namely, the integrating sphere (IS) and the solid probe (SP). Three apple cultivars (Golden Delicious, Granny Smith and Royal Gala) sourced from two retail stores (in Stellenbosch, South Africa) were used to constitute variability in the sample set. Partial least squares regression (PLSR) prediction models for internal quality (total soluble solids (TSS) and titratable acidity (TA)) were developed and validated on external test samples in various scenarios. Genetic algorithm (GA) based optimization of PLS models was used to produce optimal models prior to instrumental comparison.Model optimization using GA improved performance by a margin of 30% of the original root mean square error of cross validation for the contactless system bringing it closer to the performance of models from the MPA. The EH's performance makes it an attractive option for achieving on-line application of NIR spectroscopy for sorting apples based on internal quality. Keywords: FT-NIR, Calibration transfer, Model performance, Genetic algorithm, Apple qualityhttp://www.sciencedirect.com/science/article/pii/S2468227618302278 |
| spellingShingle | Jean Frederic Isingizwe Nturambirwe Helene H. Nieuwoudt Willem J. Perold Umezuruike Linus Opara Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization Scientific African |
| title | Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization |
| title_full | Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization |
| title_fullStr | Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization |
| title_full_unstemmed | Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization |
| title_short | Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization |
| title_sort | non destructive measurement of internal quality of apple fruit by a contactless nir spectrometer with genetic algorithm model optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2468227618302278 |
| work_keys_str_mv | AT jeanfredericisingizwenturambirwe nondestructivemeasurementofinternalqualityofapplefruitbyacontactlessnirspectrometerwithgeneticalgorithmmodeloptimization AT helenehnieuwoudt nondestructivemeasurementofinternalqualityofapplefruitbyacontactlessnirspectrometerwithgeneticalgorithmmodeloptimization AT willemjperold nondestructivemeasurementofinternalqualityofapplefruitbyacontactlessnirspectrometerwithgeneticalgorithmmodeloptimization AT umezuruikelinusopara nondestructivemeasurementofinternalqualityofapplefruitbyacontactlessnirspectrometerwithgeneticalgorithmmodeloptimization |