Electronic nose (e-nose) and electronic tongue (e-tongue) are among the most modern olfactory and gustatory bionic systems that have been able to compensate for the limitations of the human olfactory and gustatory system. These bionic systems have been very successful in evaluating and measuring the quality of food. The e-nose is capable of evaluating the quality of food through the detection of volatile organic compounds (VOCs) and the e-tongue applies electrochemical methods to assess food quality. Unfortunately, nowadays food fraud is frequently practiced especially in spices that are offered in powdered form in the market. The purpose of this piece of research is thus to evaluate e-nose and e-tongue systems and use machine learning techniques to measure the authenticity and quality of ginger powder. In this study, chickpea powder was used as an adulterant to combine with ginger powder. Ginger powder and fraud samples were prepared in 7 classes (pure chickpea powder, pure ginger powder, 10%, 20%, 30%, 40% and 50% fraud in ginger powder using chickpea powder). Finally, the features extracted from the samples were evaluated and classified using basic CNN, improved CNN, PCA, MLP, Fuzzy, SVM, KNN, GBT and EDT algorithms. The results showed that the e-nose and e-tongue systems in combination with the improved CNN were able to classify the ginger powder and the fraud samples with accuracies of 95.24% and 100%, respectively. In the e-nose system, TGS2620, TGS822 and TGS2610 sensors, and in the e-tongue system, gold and platinum sensors had the strongest performance in detecting and distinguishing ginger powder and fraud samples.
