A Novel Machine Learning and Sensor-Driven System for Nondestructive Detection of Jaggery Adulteration

Abstract

Food adulteration is a major challenge on a global scale impacting 10% of the food supply and leading to financial losses up to $30–40 billion annually. A developing country, such as India, is also not an exception to this widespread concerning issue and has significant adulteration cases reported across various categories, including Jaggery, which is its major product sharing 55% of the total world Jaggery production. While the literature reports a few methods for detecting various food adulterations, jaggery—the most popular food in India—has received meagre attention. Moreover, the reported methods have limited success and need further experimentation on a variety of diverse datasets before they are practically deployable. This research presents a classical, novel color-based method for detecting the adulteration in the jaggery. A color sensor is used to detect the color of melted jaggery samples, and an Arduino Uno is used to further analyze the color for reliable detection of adulteration. This research exploits the direct relationship between the captured pixel intensities of the jaggery and its purity to develop a linear regression model. The developed product is validated using samples having varying percentages of adulterations (10%–70%) caused due to single and multiple adulterants (sugar and food color) in jaggery. The machine learning-based novel approach developed in this research gives promising results with an accuracy of 94.67% and a precision as 92.6%. The developed method for identifying tampered jaggery is user-friendly, affordable, portable, and nondestructive and the experimental results confirm its superiority.