Recurrent Neural Networks for Multivariate Time Series with Missing Values
Authors:
Top Cited Papers
Open Access
- 17 April 2018
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 8 (1) , 1-12
Abstract
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness. There is very limited work on exploiting the missing patterns for effective imputation and improving prediction performance. In this paper, we develop novel deep learning models, namely GRU-D, as one of the early attempts. GRU-D is based on Gated Recurrent Unit (GRU), a state-of-the-art recurrent neural network. It takes two representations of missing patterns, i.e., masking and time interval, and effectively incorporates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also utilizes the missing patterns to achieve better prediction results. Experiments of time series classification tasks on real-world clinical datasets (MIMIC-III, PhysioNet) and synthetic datasets demonstrate that our models achieve state-of-the-art performance and provide useful insights for better understanding and utilization of missing values in time series analysis.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- A Systems Engineering Perspective on Homeostasis and DiseaseFrontiers in Bioengineering and Biotechnology, 2013
- MissForest—non-parametric missing value imputation for mixed-type dataBioinformatics, 2011
- Comparison of correlation analysis techniques for irregularly sampled time seriesNonlinear Processes in Geophysics, 2011
- Multiple imputation by chained equations: what is it and how does it work?International Journal of Methods in Psychiatric Research, 2011
- Multiple imputation using chained equations: Issues and guidance for practiceStatistics in Medicine, 2010
- Pattern classification with missing data: a reviewNeural Computing and Applications, 2009
- Wavelet variance analysis for gappy time seriesAnnals of the Institute of Statistical Mathematics, 2008
- Temporal reasoning with medical data—A review with emphasis on medical natural language processingJournal of Biomedical Informatics, 2007
- Missing data: Our view of the state of the art.Psychological Methods, 2002
- Long Short-Term MemoryNeural Computation, 1997