The Quality Detection and Recognition for Food Seasoning Based on an Artificial Olfactory System

Abstract

The quality of food seasoning affects the flavor and the safety of the food. Traditional detection methods, such as test-paper, cyclotron or chromatography, have some limits in accuracy, detection range, time consumption, portability and cost. The artificial olfactory system (AOS) can detect and identify the food quality by simulating animal olfactory sensors, which has the advantages of short detection cycle, high sensitivity, and no complicated pre-processing. A sample data source for AOS to detect pepper powder was built by collecting the odor data of the condiment powders under different origins and adulteration conditions using the sensor array of the PEN3 electronic nose system (AIRSENSE, Germany). Then, machine learning algorithms including support vector machine, decision tree and random forest were introduced to form the intelligent models to evaluate the quality of the pepper powder from different origins and with different adulterated substances. The results indicated that the recognition accuracy reached to over 98% for all types of pepper samples with the radial basis function-support vector machine (RBF-SVM) model. The pure pepper could be distinguished from the adulterated samples successfully with the accuracy of near 100% using machine leaning models. Finally, other more machine learning algorithms were compared to recognize the states of different pepper powders. The results showed that the SVM method has the highest accuracy in classifying the adulteration of pepper powder among different machine learning models discussed in the research. It is feasible to detect and recognize the quality of the food seasoning with AOS based on machine learning algorithms and sensor array.