“Maximum probability rule” based classification of MRSA infections in hospital environment: Using electronic nose

An electronic nose (e-nose), comprising an array of 32 polymer carbon black composite sensors has been used to identify two species of Staphylococcus aureus bacteria, namely methicillin-resistant S. aureus (MRSA) and methicillinsusceptible S. aureus (MSSA) responsible for ear nose and throat (ENT) infections when present in standard agar solution in the hospital environment. Polymer sensors based e-nose has also been used to identify coagulase-negative staphylococci (C-NS) in the hospital environment. This e-nose based ENT bacteria identification is a classical and challenging problem of classification. In this paper an innovative classification method depending upon “Baye's theorem” and “maximum probability rule” was investigated for these three groups of S. aureus data. Two different statistical scalar feature extraction techniques, namely ‘Kurtosis of the sensory data’, and ‘Skewness of the data’, are also tested. The best results suggest that we are able to identify and classify three bacteria classes with up to 99.83% accuracy rate with the application of adaptive kernel method along with ‘Kurtosis of the sensory data’, and ‘Skewness of the data’ as feature. This type of bacteria data analysis and feature extraction is very difficult. But we can conclude that this study proves that “maximum probability rule” based classification can provide very strong solution for identification of S. aureus infections in hospital environment and very rapid detection.