Visualization representing method for time series data

Abstract

The invention discloses a visualization representing method for time series data. On the basis that time series feature representations of an SAX-based method are adopted as the visualization basis of time series data, the signifying character representations are converted into a Markov transfer matrix, then, a complex network is used for building time series graphic representations, and time series data visualization representations are obtained. The SAX-based discretization method is adopted for time series Markov matrix conversion for the first time, a corresponding Markov transfer matrix obtained after time series discretization is adopted, and time series statistical characteristics can be better extracted; compared with quantile discretization, SAX discretization can better extract time series statistical characteristics, under certain conditions, the complex network visualization result is frequently better than the quantile discretization result on a benchmark data set, the approximation accuracy is closer to that of original data distribution, and the visualization effect is better.

Description

technical field [0001] The invention relates to a visual representation method of time series data. Background technique [0002] Time series data widely exists in the fields of scientific research, production process, and financial services. Especially in recent years, with the application and development of information technology, time series data has also shown an explosive growth trend. Massive data processing and application work increasing day by day. Time series data usually has high-dimensional characteristics, and due to the influence of environmental factors in the production process, it is easy to have certain noise. Therefore, research on such complex data to effectively mine and acquire information and knowledge has important value and significance for both scientific theoretical research and social production practice. [0003] In a large number of problems related to time series data, people try to study the process of physical phenomena changing dynamically...

AI Technical Summary

Problems solved by technology

However, many feature compression algorithms will lead to the loss of classification information, resulting in the decline of data classification ability after dimensionality reduction

The quantile method is used to discretize the time series, and then to perform visual representation. The idea is simple and intuitive, but the problem is that the information loss is large on the one hand, and the KL distance is relatively large on the other hand, that is, in reflecting the original time series. Accuracy is biased

Images