FARRASA RANI FAISAL
THESIS
A Comparative Study of Machine Learning Techniques for Optimizing Near Infrared Spectroscopy (NIRS) Models
in Predicting Total Acidity and Vitamin C Content in Mangoes
ABSTRACT
Mango is one of the most popular fruits, highly favored by the public due to its high vitamin content and significant economic value. As such, evaluating anc identifying fruit quality is a critical aspect of post-harvest processing. The quality of mango fruit can be determined by parameters such as total acidity and vitamin C content. Near Infrared Spectroscopy (NIRS) is a rapid and non-destructive analytical technique that serves as an alternative method for assessing quality parameters. Non-linear methods such as Machine Learning (ML) regressior algorithms are required to enhance data analysis accuracy. This study aims to compare various ML techniques for optimizing NIRS models to predict tota acidity and vitamin C content in mangoes, using spectral correction methods including Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV). The best prediction results for total acidity were achieved using the GBR algorithm, with MSC-GBR values (R2: 0.99. r: 0.97. RMSEC: 0.00, RPD: 7.06 and SNV-GBR values (R2: 0.99. r: 0.99. RMSEC: 0.01, RPD: 17.23). The RFR algorithm also provided satisfactory results after GBR. For vitamin C prediction the GBR and RFR algorithms demonstrated the best performance. with MSC GBR values R2: 0.97. r: 0.99. RMSEC: 0.00. RPD: 5.82) and SNV-RFR values (R2: 0.99, R: 0.99, RMSEC: 0.18, RPD: 12.41). On the other hand, the SVR and KNN-R algorithms showed poor performance in predicting total acidity and vitamin C in mangoes. This study successfully demonstrates that NIRS combined with ML techniques can predict total acidity and vitamin C content in mangoes with high accuracy, particularly using GBR and RFR models. The selection of appropriate spectral correction methods and ML algorithms is crucial to achieving optimal results.