A new honey adulteration detection approach using hyperspectral imaging and machine learning

Abstract This paper develops a new approach to fraud detection in honey. Specifically, we examine adulterating honey with sugar and use hyperspectral imaging machine learning techniques detect adulteration. The main contributions of this are introducing feature smoothing technique conform the classification model used adulterated samples perpetration an data set using imaging, which has been made available online for first time. Above $$95\%$$ 95 % accuracy was achieved binary adulteration multi-class between different adulterant concentrations. system developed can be prevent as reliable, low cost, data-driven solution.