Data Restoration by Linear Estimation of the Principal Components From Lossy Data

Abstract

In this article, we propose a method based on principal component analysis (PCA) to restore data after the occurrence of data loss due to sensor defects or environmental factors. In the L2-PCA feature space, the feature vector, which consists of principal components of the data, converges to a point known as the “convergence point” as the extent of data loss increases. Using these characteristics, we approximately linearly estimated the principal components of the original data from the feature vectors of the lossy data. The estimated principal components are used as coefficients in the linear combination of the projection vectors of the PCA feature space for data restoration. The restoration performance of the proposed method is not only superior; the method is also computationally more efficient than other data restoration methods. Experimental results for gas measurement data and facial image data confirm the excellent data restoration performance of the proposed method.

Keywords

• Data restoration
• principal components
• lossy data
• approximately linear estimation
• feature space
• convergence point