E-nose coupled with an artificial neural network to detection of fraud in pure and industrial fruit juices

Abstract

Consumer demands for fresh foods with desired sensory properties. Lack of easy, cheap, and nondestructive methods to control the quality of fruit juices is one of the main challenges in the beverage industry. The present study has examined two types of natural and industrial juices. Machine olfaction with 9 metal oxide semiconductor (MOS) sensors was used for the experiments. Sensor response patterns were analyzed using artificial neural networks (ANN). PCR method was used to evaluate the discrimination power of the sensors. According to the results, the discrimination power of the sensors used in the electronic nose sensor array was determined, three of which were removed due to improper response power. The proposed method can be used to select the minimum and most effective number of MOS gas sensors to construct an electronic nose system to control the olfactory quality of different foods. The use of a minimum number of sensors reduces the cost of constructing an electronic nose system, decreases the volume of the processor data input, and consequently increases the classification accuracy. Therefore, the MOS-based electronic nose combined with the ANN can be an effective and highly efficient tool in the fast and nondestructive classification of pure and industrial fruit juices.

Keywords

• olfactory machine
• adulteration
• sensors
• nondestructive