DETECTION AND SIMULTANEOUS IDENTIFICATION OF MICROORGANISMS FROM HEADSPACE SAMPLES USING AN ELECTRONIC NOSE

The detection and simultaneous identification of a range of microorgan isms by measuring the volatile compounds produced from plate cultures has been carried out using an electronic nose and a neural network cla ssifier. Headspace samples were taken from static atmospheres formed f rom inoculated agar plates after a suitable growth period at 37 degree s C and analysed using a standard 16 sensor array operating in transie nt flow mode. The response of the sensor array to water and to the con trol media in the absence of microbial growth was also determined, all owing greater discrimination of microbial volatiles. The response curv es produced were processed using standard back propagation neural netw ork techniques to provide identification. The overall classification r ate for 12 different bacteria and one pathogenic yeast was 93.4%. Data for a sub-set of seven bacteria gave 100% classification using the sa me methods. In a second experiment three similar yeast cultures were c ompared and correctly classified at a level of 96.3% with no pre-proce ssing to remove the sample signal generated by the media. Principal co mponent analysis on selected data gave clear discrimination between wa ter vapour and the test samples. (C) 1997 Elsevier Science S.A.