Correlation clustering for robust gas recognition under mixed interference

Abstract

Abstract Gas recognition by electronic noses under mixed interference is a challenging problem. We propose correlation analysis for robust gas recognition by calculating the similarity of signals between target gases and mixtures. The gas sensing datasets were clustered according to the values of correlation coefficients with the target gases. The correlation analysis outperformed neural networks and other clustering algorithms on robust gas recognition under mixed interference. The correlation analysis maintained 100% accuracy even with a response change of about 40% up to an interference ratio of 13%. The excellent performance of correlation analysis can be ascribed to its powerful capacity for measuring the similarity between signals via relative variation. Correlation analysis is suggested to be a robust clustering algorithm for gas recognition.