A Novel Sparse Subspace Correlation Analysis-Based Domain Adaptation Method for Sensor Drift Suppression in E-nose

Abstract

Sensor drift caused by the sensor aging and environmental factors is an urgent problem that seriously affects the detection performance and service life of electronic nose (E-nose). It is necessary to research the sensor drift suppression methods to realize the long-term and stable detection of E-nose. In this paper, a highly efficient sparse subspace correlation analysis-based domain adaptation(SSCA-DA) method is proposed to suppress the sensor drift. This method is to find the optimal subspace for each dataset, and the transformed data after transforming to the optimal subspace is sparsely reconstructed, which can realize the knowledge transfer in the data domains with and without drift information. From the experiment results, it can be found that the sensor drift can be satisfactorily solved by the proposed method.