Pattern Recognition Applied to Analysis of Gas Sensors' Array Data

P. Marczyński, A. Szpakowski, C. Tyszkiewicz and T. Pustelny Department of Optoelectronics, Silesian University of Technology, B. Krzywoustego 2, 44-100 Gliwice, Poland

Full Text PDF

For an array of eight chemoresistive gas sensors a computer pattern recognition system was built. Multivariate data analysis was performed for measurements of three gases' dilutions: hydrogen (H2), methane (CH4), and carbon monoxide (CO). The pattern recognition system included a feature subset selection algorithm involving PCA and objective function. Dimensionality reduction was applied to two kinds of patterns: three aforementioned gases and six different concentrations of hydrogen. For patterns of the three gases, classification tests were performed using k-NN algorithm and N-fold based validation method.

DOI: 10.12693/APhysPolA.122.847 PACS numbers: 02.50.Sk, 07.07.Df