A new honey adulteration detection approach using hyperspectral imaging and machine learning
Tessa Phillips, Waleed H. Abdulla
Abstract
Abstract This paper develops a new approach to fraud detection in honey. Specifically, we examine adulterating honey with sugar and use hyperspectral imaging and machine learning techniques to detect adulteration. The main contributions of this paper are introducing a new feature smoothing technique to conform to the classification model used to detect the adulterated samples and the perpetration of an adulterated honey data set using hyperspectral imaging, which has been made available online for the first time. Above $$95\%$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>95</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> accuracy was achieved for binary adulteration detection and multi-class classification between different adulterant concentrations. The system developed in this paper can be used to prevent honey fraud as a reliable, low cost, data-driven solution.