A CHEAPLY NON-DESTRUCTIVE TECHNIQUE TO PREDICT HONEY QUALITY: THERMAL IMAGING AND MACHINE LEARNING

Abstract

The main purpose was to predict honey quality based on proline and Brix content using a thermal imaging and machine learning algorithm. The proline, Brix and color properties of twenty honey samples were determined. The proline and Brix levels were classified and estimated utilizing the classification and regression tree (CART) algorithm. The mean proline and Brix content in honeys was 678.83±192.16 mg/kg and 83.2±0.79%, respectively. CART analysis revealed that high proline honeys had L values exceeding 48.143 and b* values below 35.416. Conversely, honeys with low Brix values were characterized by L and a* values below 55.860 and 53.660, respectively, and were identified as newly harvested. The CART algorithm successfully classified the proline and Brix levels with 95% and 100% accuracy, respectively (p< 0.001). The most relevant conclusion is that whitish, bluish, blackish and greenish honeys are of higher quality due to high proline and low Brix content.