Research On Missing Data Filling Algorithm Based On Savitzky-Golay Denoising Algorithm And Principal Component Analysis

In this thesis we discuss two issues in missing data filling:1.We give an optimization model based on principal component analysis to fill missing data,and prove that this model is effective under some reasonable assumptions.2.Based on the above model and the Savitzky-Golay denoising algorithm,we design the SG-PCA algorithm to fill missing data.Numerical experiments show that this algorithm has higher accuracy than several widely used algorithms.