Data reconstruction using iteratively reweighted L1-principal component analysis for an electronic nose system

We propose a method to reconstruct damaged data based on statistical learning during data acquisition. In the process of measuring the data using a sensor, the damage of the data caused by the defect of the sensor or the environmental factor greatly degrades the performance of data classification. Instead of the traditional PCA based on L2-norm, the PCA features were extracted based on L1-norm and updated by iteratively reweighted fitting using the generalized objective function to obtain robust features for the outlier data. The damaged data samples were reconstructed using weighted linear combination using these features and the projection vectors of L1-norm based PCA. The experimental results on various types of volatile organic compounds (VOCs) data show that the proposed method can be used to reconstruct the damaged data to the original form of the undamaged data and to prevent degradation of classification performance due to data corruption through data reconstruction.