Feature selection and analysis on correlated gas sensor data with recursive feature elimination

Support vector machine recursive feature elimination (SVM-RFE) is a powerful feature selection algorithm. However, when the candidate feature set contains highly correlated features, the ranking criterion of SVM-RFE will be biased, which would hinder the application of SVM-RFE on gas sensor data. In this paper, the linear and nonlinear SVM-RFE algorithms are studied. After investigating the correlation bias, an improved algorithm SVM-RFE + CBR is proposed by incorporating the correlation bias reduction (CBR) strategy into the feature elimination procedure. Experiments are conducted on a synthetic dataset and two breath analysis datasets, one of which contains temperature modulated sensors. Large and comprehensive sets of transient features are extracted from the sensor responses. The classification accuracy with feature selection proves the efficacy of the proposed SVM-RFE + CBR. It outperforms the original SVM-RFE and other typical algorithms. An ensemble method is further studied to improve the stability of the proposed method. By statistically analyzing the features' rankings, some knowledge is obtained, which can guide future design of e-noses and feature extraction algorithms.