Automatic filling method of time sequence missing value based on long-term and short-term memory network

Abstract

The invention discloses an automatic filling method of time sequence missing value based on long-term and short-term memory network, comprising the steps of obtaining an original data set having no missing value and conducting pre-processing; deleting certain values at random based on the given missing rate and forming a missing data set having different missing rates; introducing residual error based on graph dependence and connecting the residual error to an LSTM model to from a RSU based on deep residual network and thought of graph structure dependence, and conducting blending and transmitting on the every-minute hidden state of the LSTM model and the historical state information of the RSU; training the newly-established model and conducting filling during the propagation process by means of the RSU value according to whether the data is missing before the network training. The invention is advantageous in that the RSU integrates the anterior residual error with the hidden state information, and thereby the established model can be associated with adequate historical information related to missing data, and the end-to-end missing value training conducted on the time sequence data having missing value can be realized.

Description

technical field [0001] The invention relates to the technical field of automatic filling of missing values ​​in time series, in particular to an automatic filling method for missing values ​​in time series that can learn end-to-end data containing missing values ​​based on a long-short-term memory network. Background technique [0002] Time series is one of the most common forms of data in practical applications, including weather, health and medical, motion capture, financial markets and urban traffic control, etc. However, these actual time series data inevitably contain missing values ​​due to sensor failures. Generally, the methods for dealing with missing values ​​include zero filling, mean filling, polynomial fitting method or EM algorithm, etc. to fill missing values. [0003] However, time series imputation is a very challenging task compared to static data imputation. Because missing values ​​often have nonlinear and dynamic correlations with their previous values...

AI Technical Summary

Problems solved by technology

Similarly, the Temporal Regularized Matrix Factorization (TRMF) model proposed by Dhillon et al. uses autoregression to simulate the time dependence between the corresponding latent variables, and they generalize the structure of this autoregression as a graph , used to establish dependencies between missing values ​​and their previous non-missing values ​​at different stages, but this relies on human prior knowledge and requires manual design of the graph structure

In addition to the above-mentioned graph-based methods, Long Short-Term Memory (LSTM) can also be used to establish the transition relationship of time. However, the traditional LSTM model cannot handle time series data with missing values, so it cannot Conduct end-to-end network training

Images