Abstract— Fruit adulteration may seriously harm human health and cause substantial financial losses for both growers and consumers. Traditional methods for fruit adulteration detection can be time-consuming and sometimes call for specialised equipment. A rapid and accurate method of spotting fruit adulteration is offered by machine learning. Using this technique, information on both healthy and tainted fruit samples is gathered, including information on their chemical makeup. Then, utilising these data and attributes taken from the chemical composition data, machine learning models are developed. The models may then be used to precisely determine whether a fruit sample has been tampered with or not, assisting in the reduction of dangerous or fraudulent items that are consumed. Machine learning's application to the detection of fruit adulteration has the potential to increase food safety, shield consumers from dishonest business practises, and lessen financial losses for farmers and other food industry participants.
|
DOI:
10.17148/IJARCCE.2023.125102
