POTENTIAL OF GAS SENSOR ARRAY BASED PRINCIPAL COMPONENT ANALYSIS HYBRID FOR ESCHERICHIA COLI DETECTION

Subadra Murugan and Marimuthu N. Sankaralingam

Keywords

Escherichia coli, electronic nose (Enose), principal component analysis (PCA), artificial neural network (ANN), genetic algorithm (GA), hybrid neural network (PCANN), sterile body fluids

Abstract

Recent advances in odour-sensing technology and pattern recognition algorithms promise to resurrect olfaction as an important diagnostic option. Electronic nose is an array of chemical sensors connected with a suitable pattern recognition system. This is a rapid, sensitive, specific, non-destructive and easy-to-use tool which can be utilized for detection and identification of pathogenic bacteria such as Escherichia coli in clinical specimen to improve the clinical diagnosis. In this investigation, 100 samples of different kinds of bacteria which were the major cause for sepsis and urinary tract infection were inoculated in 20 ml growth medium and incubated for 2 hours for volatile generation. These samples were analyzed with a metal oxide semiconductor based electronic nose for detecting and differentiating Escherichia coli. The instrument was used to generate a pattern of the volatile compounds present in the pathological samples. The sensor responses were evaluated by principal component analysis (PCA) and then with hybrid neural network (PCANN optimized by genetic algorithm). Good results were obtained in the classification of bacterial samples and the methodology was simple and rapid. These results suggest that the electronic nose could be used as a tool for the detection of Escherichia coli.

Important Links:



Go Back