Conception and Development of a Portable Electronic Nose System for Classification of Raw Milk Using Principal Component Analysis Approach

Abstract

The analysis of the aroma of milk is an especially complex problem due to the heterogeneous nature of milk. In the present study, a portable electronic nose has been fabricated and characterized using an oxide semiconductor gas sensor array. The portable electronic nose system, based on Taguchi Gas Sensors (TGS), consists of a microcontroller PIC16F877 as CPU, an LCD for displaying gas conductance and a LabVIEW© PC interface for data acquisition, etc. To check its separation capability a pattern recognition method namely Principal Component Analysis (PCA) has been performed. The PCA method permits a good classification between three types of raw milks from different dairy farms. On the other hand, the data coming from the response of the sensors have been elaborated by PCA and Support Vectors Machines (SVMs) in order to obtain a classification of the data clusters related to different milk ageing days and so track the dynamic evolution of milk rancidity. It was found that the portable electronic nose system together with a pattern recognition technique, PCA or SVMs is able to show a characteristic development of the milk quality, when it is stored at 4 °C, dependent on storage time. The last section draws the evaluation of the hygienic quality of raw milk, the following microbiological counts were determined: yeast and mould counts, total coliform count and total aerobic mesophilic flora count.