Key point-based data sequence linear fitting method

Abstract

The invention discloses a key point-based data sequence linear fitting method. An important extreme point in a non-monotone sequence can be reserved by only scanning the sequence data set once with a customized threshold of a middle line distance and a threshold of the holding time interval of the extreme point in the non-monotone sequence; and a judgment that whether the middle data point is the key point to be reserved according to the length of the middle line of a triangle formed by three continuous data points in the non-monotone sequence is made; and only the main key points which reflect the change mode of the data sequence are reserved during the implementation of the method, so the data storage capacity is greatly reduced and the calculating speed is increased. The theoretical analysis and experimental result show that: compared with a traditional method, the method provided by the invention has the advantages of more efficiently selecting the key point, holding the original variation tread of the data sequence under the condition of high compression ratio and accurately positioning discontinuity points in the sequence.

Description

technical field [0001] The invention relates to a data sequence linear fitting method based on key points. Background technique [0002] As an important data object arranged in chronological order, time series widely exists in many fields such as economy, science, and industry. How to analyze and process these massive time-series data and discover some previously unknown and valuable information is attracting more and more attention and attention from researchers. Because these massive data series have the characteristics of frequent short-term fluctuations, a large amount of noise interference, and unsteady state, directly performing similarity query, classification and clustering, and pattern mining on the original time series not only has low storage and computing efficiency, but also affects The accuracy and reliability of the method make it difficult to obtain satisfactory results. [0003] About the piecewise linear representation of data sequences is a simple and in...

AI Technical Summary

Problems solved by technology

When the data subsequence formed by three consecutive data points is a monotonous mutation sequence (such as figure 1 As shown), the fitting effect of the included angle method is better than that of the extreme value method: according to the self-defined midline distance threshold, the included angle method can timely and accurately find the turning point x i ; but due to the data sequence x i-1 , x i , x i+1 is a monotonic sequence (here x i-1 =x i i+1 ), so the extreme value method cannot find the turning point x in the sequence i , so the sequence fitting result is figure 2 The line segment x in i-1 x i+1 , filtering the turning point x i

Images