A Data Processing Method of Symbolic Approximation

In data analysis, the analysis efficiency and accuracy can be significantly improved after preprocessing the original data. And Symbolic Aggregate approXimation(SAX) is an effective data compression analysis method. Because of its simple, intuitive and effective characteristics, it has become the most typical symbolic feature representation method. However, in the approximate data compression of segmented aggregation, this method adopts a unified average method regardless of the characteristics of the data, which weakens the prominent characteristics of the data and causes the loss of effective information, which has a negative impact on the accuracy of data mining and analysis. Aiming at this problem, a local gradient search method (LGS) is proposed, which is the LGS-SAX method for piecewise aggregated symbol approximation. It can use gradient transformation to perceive the angle to prevent the loss of feature information, so as to achieve the effect of efficiently compressing data and retaining feature information. Through error analysis and comparison, the method has small error, complete information retention, and the method is efficient and feasible.