Multi-variable time sequence classifying method based on semantic selection

Abstract

The invention discloses a multi-variable time sequence classifying method based on semantic selection. Time sequence classification as a machine learning hot research branch has wide application prospects in computer vision, financial analysis, biostatistics and the like. According to a sparse adaptive-semantic learning network (SA-SLN), by means of a sparse convolution kernel, the space semanticconcept and time short-term dependence of multi-variable time sequences are extracted at the same time, an attention diversion method is put forward to be used for selecting the semantic concept, andfinally modeling is conducted on the long-term dependence of the sequences through LSTMs. By means of the SA-SLN, based on the situation that inter-frame properties have correlation, automatic space feature extraction and time-sequence dependence multi-step modeling are realized, the defects of an existing method are overcome, and the currently optimum result is obtained on three public data sets.

Description

Technical field [0001] The invention relates to the technical field of time series modeling, in particular to a method for multivariate time series classification based on semantic selection. Background technique [0002] With the development of information technology, perceptrons have become cheaper and more common, and more and more time series data will be collected. How to mine the pattern features in time series has become a research hotspot. Nowadays, time series classification methods can be roughly divided into two categories: based on dynamic systems and based on feature representation. The first method assumes that the data are all generated in implicit dynamic systems, such as: Hierarchical Maximum Entropy Markov Models, Hidden Markov Models (HMMs), Conditional Random Fields and Long Short-term Memory Neural Networks. However, none of these methods consider intra-frame features. The second method is to extract appropriate features or feature representations, such as:...

AI Technical Summary

Problems solved by technology

Although the feature-based method is effective, it does not consider time dependence, and manual design of features is time-consuming and error-prone

Therefore, how to combine the above two methods and automatically extract intra-frame features has become a new breakthrough. W.Zhu et al. "Cooccurrence feature learning for skeleton based action recognition using regularized deep lstm networks." in AAAI, vol.2, 2016, p.8 The co-occurrence feature method proposed in . solves the above problems, but it extracts the same spatial combination features for different types of samples, and cannot achieve sample-oriented extraction.

Images