Time sequence classification and retrieval method based on deep multi-task representation learning

Abstract

The invention discloses a time sequence classification and retrieval method based on deep multi-task representation learning. The method comprises the steps: (1) performing normalization processing ona given time sequence data set; (2) inputting the normalized time sequence into a multi-stage wavelet decomposition network, and obtaining a multi-scale subsequence set through n-stage decomposition;(3) inputting the multi-scale sub-sequence set into a residual network, and outputting shared representation after feature extraction and fusion are performed on each sub-sequence; (4) as for a timesequence classification task, inputting the shared representation into a classification network, outputting a classification representation after feature extraction, then inputting the classificationrepresentation into a classifier, and outputting a time sequence classification result after classification; and (5) as for the time sequence retrieval task, inputting the shared representation into aretrieval network, outputting the retrieval representation after feature extraction, and as for the retrieval representation, realizing the retrieval task by constructing a tree-based or hash-based index.

Description

technical field [0001] The invention relates to the field of time series representation learning, in particular to a time series classification and retrieval method based on deep multi-task representation learning. Background technique [0002] Time series widely exist in fields such as medical treatment, electric power and finance. The classification and retrieval of time series are very important basic tasks, which can be realized by calculating the similarity between time series. Dynamic Time Warping (DTW) distance is widely regarded as the best similarity measure for time series. It uses a dynamic programming algorithm to determine the best alignment, taking into account offsets in time, scaling and deformation, etc. But the DTW distance has two limitations. First, the time complexity of the dynamic programming algorithm is the quadratic of the length of the time series, making the scale of classification and retrieval unable to adapt to large data sets. Second, DTW ...

AI Technical Summary

Problems solved by technology

[0005] However, existing methods usually focus on single-task learning

These methods fail to capture the unique information hidden between different tasks, which can be used to improve the performance of each task

Images