Classification of Bee Pollen and Prediction of Sensory and Colorimetric Attributes—A Sensometric Fusion Approach by e-Nose, e-Tongue and NIR

Sipos, László and Végh, Rita and Bodor, Zsanett and Zaukuu, John-Lewis Zinia and Hitka, Géza and Bázár, György and Kovács, Zoltán (2020) Classification of Bee Pollen and Prediction of Sensory and Colorimetric Attributes—A Sensometric Fusion Approach by e-Nose, e-Tongue and NIR. SENSORS, 20 (23). pp. 1-21. ISSN 1424-8220

Preview

Text Eye-Tracker Analysis of the Contrast Sensitivity of Anomalous.pdf - Published Version Download (4MB) | Preview

Abstract

The chemical composition of bee pollens di�ers greatly and depends primarily on the botanical origin of the product. Therefore, it is a crucially important task to discriminate pollens of di�erent plant species. In our work, we aim to determine the applicability of microscopic pollen analysis, spectral colour measurement, sensory, NIR spectroscopy, e-nose and e-tongue methods for the classification of bee pollen of five different botanical origins. Chemometric methods (PCA, LDA) were used to classify bee pollen loads by analysing the statistical pattern of the samples and to determine the independent and combined e�ects of the above-mentioned methods. The results of the microscopic analysis identified 100% of sunflower, red clover, rapeseed and two polyfloral pollens mainly containing lakeshore bulrush and spiny plumeless thistle. The colour profiles of the samples were di�erent for the five di�erent samples. E-nose and NIR provided 100% classification accuracy, while e-tongue > 94% classification accuracy for the botanical origin identification using LDA. Partial least square regression (PLS) results built to regress on the sensory and spectral colour attributes using the fused data of NIR spectroscopy, e-nose and e-tongue showed higher than 0.8 R2 during the validation except for one attribute, which was much higher compared to the independent models built for instruments.

Actions (login required)

Edit Item