Multivariate time series classification method and system based on full convolution attention

Abstract

The invention relates to a multivariate time sequence classification method and system based on full convolution attention, and the method comprises the steps: capturing the local variable features of a multivariate time sequence through employing a 2D convolution filter through employing a design idea of full convolution in the field of images, so as to learn the linkage relation between adjacent variables; capturing local time features of the multivariate time sequence by using a 2D convolution filter to learn trend information between adjacent time, and weakening the influence of mutation information on a result; adopting a convolution and self-attention model, obtaining multiple local features through multi-kernel convolution, enabling the self-attention model to calculate the weights of the multiple local features and non-local features, and providing different visual angles for reviewing multivariate time series data; adopting an attention model to respectively fuse variables and time characteristics of corresponding visual angles, and learning a global dependency relationship of the variables and a global dependency relationship of time; adopting a weight matrix method to fuse multi-view features, and learning more comprehensive and more accurate time variable interaction features.

Description

technical field [0001] The invention relates to a packaging box, in particular to a method and system for multivariate time series classification based on full convolutional attention. Background technique [0002] A time series is a set of random variables sorted by time, which is usually the result of observing a certain underlying process at a given sampling rate in an equally spaced time period. Time series data essentially reflects the trend of one or some random variables changing over time, and the core of the time series classification method is to mine this rule from the data and use it to make category predictions for future data . In real life, observing data at a series of time points is a common activity, and research fields such as agriculture, commerce, meteorology, military and medical care contain a large amount of time series data. In summary, time series data is currently being generated at an unpredictable rate in almost every application domain in real...

AI Technical Summary

Problems solved by technology

The above is aimed at the research of time series classification technology, and there are few studies on multivariate time series classification technology. Time series classification technology cannot solve the dependence relationship between multiple variables.

Images