Prediction of physicochemical characteristics of Lemon (Citrus limon cv. Montaji Agrihorti) using Vis-NIR spectroscopy and machine learning model

Jihan Nada Salsabila Erha, Dina Wahyu Indriani, Zaqlul Iqbal, Bambang Susilo and Dimas Firmanda Al Riza
Additional contact information
Jihan Nada Salsabila Erha: Department of Biosystems Engineering, Faculty of Agricultural Technology, University of Brawijaya, Malang, Indonesia
Dina Wahyu Indriani: Department of Biosystems Engineering, Faculty of Agricultural Technology, University of Brawijaya, Malang, Indonesia
Zaqlul Iqbal: Department of Biosystems Engineering, Faculty of Agricultural Technology, University of Brawijaya, Malang, Indonesia
Bambang Susilo: Department of Biosystems Engineering, Faculty of Agricultural Technology, University of Brawijaya, Malang, Indonesia
Dimas Firmanda Al Riza: Department of Biosystems Engineering, Faculty of Agricultural Technology, University of Brawijaya, Malang, Indonesia

Research in Agricultural Engineering, 2024, vol. 70, issue 4, 218-225

Abstract: Lemons are fruit products that grow well in Indonesia. Montaji Agrihorti is one of the lemon varieties found in Indonesia, a new variety developed by Balitjestro breeding. This lemon variety is seedless. In fact, lemons are harvested nearly all year-round. Equally important, evaluating the fruit's maturity level is crucial for determining the optimal harvest time. In this study, standardizing measurement on maturity level was conducted through Vis-NIR spectroscopy and machine learning models. In this case, non-destructive data from Vis-NIR spectroscopy were correlated with parameters related to fruit maturity and quality, such as soluble solid content (SSC), acidity, firmness, essential oil yield, and essential oil content. Non-destructive test involved capturing spectral data to be subsequently processed through machine learning models such as SVM, KNN, and random forest. The most accurate results were obtained using the SVM method for SSC and firmness parameters, with accuracy of 72 and 78%, respectively. For visual and acidity parameters, the most accurate result was performed through random forest with visual accuracy value 94% for all features, all features-MA (moving averages) was 97%, 36-PCA (principal component analysis) was 94%, and 36-PCA-MA was 97%. As for acidity, the accuracy for all features was 89%, all features-MA was 81%, 36-PCA was 89%, and 36-PCA-MA was 83%.

Keywords: destructive; KNN; montaji Agrihorti Lemon; random forest; SVM; chemometrics (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://rae.agriculturejournals.cz/doi/10.17221/25/2024-RAE.html (text/html)
http://rae.agriculturejournals.cz/doi/10.17221/25/2024-RAE.pdf (application/pdf)
free of charge

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:caa:jnlrae:v:70:y:2024:i:4:id:25-2024-rae

DOI: 10.17221/25/2024-RAE

Access Statistics for this article

Research in Agricultural Engineering is currently edited by Bc. Michaela Polcarová

More articles in Research in Agricultural Engineering from Czech Academy of Agricultural Sciences
Bibliographic data for series maintained by Ivo Andrle ().