Transfer learning in near infrared spectroscopy for stingless bee honey quality prediction across different months

Abstract

Near infrared spectroscopy (NIRS) coupled with machine learning has demonstrated its capability as an efficient secondary measurement method in various applications. However, a NIRS predictive model might be unable to maintain its accuracy when it is applied to samples that were acquired from different periods. Particularly, the qualities of stingless bee honey are affected by various uncontrolled factors, e.g. ecosystem, origins, and weather. Since it is unrealistic to have a NIRS dataset that can represent unforeseen future changes, an algorithm that can adapt existing data for new samples is worth to be investigated. Thus, this study aims to evaluate the feasibility of homogenous transfer learning approaches to overcome data constraints in developing NIRS predictive models of stingless bee honey qualities across different months. First, the near infrared transmittance spectra were acquired across honey samples prior to their respective conventional quality measurements in four different analysis months. Then, data from different analysis months were used as source and target datasets. Next, joint distribution adaptation based partial least square (JDA-PLS) and transfer component analysis based PLS (TCA-PLS) were implemented to establish NIRS predictive models of moisture, hydroxymethylfurfural (HMF), and glucose quality. Results show that the proposed TCA-PLS outperformed JDA-PLS and PLS by achieving the lowest RMSEP of 3.401 % and 0.804 mg/kg in predicting the moisture and glucose of stingless bee honey, respectively, across different months. Lastly, finding shows that both JDA and TCA were inefficacy when the label distributions of the calibration and validation datasets were similar.