Multivariate Time Series Missing Data Imputation Using Recurrent Denoising Autoencoder
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
This paper presents a novel method for imputing missing data of multivariate time series by adapting the Long Short Term-Memory(LSTM) and Denoising Autoencoder(DAE). Missing data are ubiquitous in many domains; proper imputation methods can improve performance on many tasks. Our method focus on multivariate time series, applying bidirectional LSTM to learn temporal information and DAE to learn correlation between variables, and we combine these two models by using LSTM as the encoder component of DAE. Several real-world datasets, including electroencephalogram(EEG), electromyogram(EMG) and electronic health records(EHRs), are extracted to test the performance of our method. Through simulation studies, we compare the proposed recurrent denoising autoencoder with several baseline imputation methods and demonstrate its effectiveness in both missing data estimation and label prediction after imputation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
RUBIN, D. B. (1976) · Biometrika · doi:10.1093/biomet/63.3.581 · Cited by 9,925
Multiple imputation using chained equations: Issues and guidance for practice
White, I. R., Royston, P., & Wood, A. M. (2011) · Statistics in Medicine · doi:10.1002/sim.4067 · Cited by 9,792 · cited 2×
“State-of-the-art static imputation methods include MICE [3], MissForest [4] based on random forest, algorithms based on Expectation-Maximization [5].”
MethodExtracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
MissForest—Non-parametric missing value imputation for mixed-type data
Stekhoven, D. J., & Bühlmann, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/btr597 · Cited by 6,156
Recurrent Neural Networks for Multivariate Time Series with Missing Values
Che, Z., Purushotham, S., Cho, K., Sontag, D., & Liu, Y. (2018) · Scientific Reports · doi:10.1038/s41598-018-24271-9 · Cited by 2,370
Pollard, T. J., Johnson, A. E. W., Raffa, J. D., Celi, L. A., Mark, R. G., & Badawi, O. (2018) · Scientific Data · doi:10.1038/sdata.2018.178 · Cited by 1,993
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710 · cited 1×
“Autoencoder(AE) is an unsupervised representation learning model via non-linear transformation, which has often been used for EHR phenotyping, EEG feature representation or dimensionality reduction [7] [9] [12] [16] [17] [18] [19].”
MethodPattern classification with missing data: a review
García-Laencina, P. J., Sancho-Gómez, J.-L., & Figueiras-Vidal, A. R. (2010) · Neural Computing and Applications · doi:10.1007/s00521-009-0295-6 · Cited by 759
Multiple-Imputation Inferences with Uncongenial Sources of Input
Meng, X.-L. (1994) · Statistical Science · doi:10.1214/ss/1177010269 · Cited by 756
Candanedo, L. M., & Feldheim, V. (2016) · Energy and Buildings · doi:10.1016/j.enbuild.2015.11.071 · Cited by 586
GAIN: Missing Data Imputation using Generative Adversarial Nets
Yoon, J., Jordon, J., & van der Schaar, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.02920 · Cited by 570
Estimating Missing Data in Temporal Data Streams Using Multi-Directional Recurrent Neural Networks
Yoon, J., Zame, W. R., & van der Schaar, M. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2874712 · Cited by 341
Deep Computational Phenotyping
Che, Z., Kale, D., Li, W., Bahadori, M. T., & Liu, Y. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783365 · Cited by 239
Modeling Missing Data in Clinical Time Series with RNNs
Lipton, Z. C., Kale, D. C., & Wetzel, R. C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04130 · Cited by 159
Mehdipour Ghazi, M., Nielsen, M., Pai, A., Cardoso, M. J., Modat, M., Ourselin, S., & Sørensen, L. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.01.004 · Cited by 139
Multiple Imputation Using Deep Denoising Autoencoders.Preprint
Gondara, L., & Wang, K. (2017) · arXiv (Cornell University) · Cited by 65
Speech Recognition with Missing Data using Recurrent Neural Nets
Parveen, S., & Green, P. (2001) · Cited by 28
An EEG signal classification method based on sparse auto-encoders and support vector machine
Yan, B., Wang, Y., Li, Y., Gong, Y., Guan, L., & Yu, S. (2016) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccchina.2016.7636897 · Cited by 24
Risk Factor Analysis Based on Deep Learning Models
Suo, Q., Xue, H., Gao, J., & Zhang, A. (2016) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/2975167.2975208 · Cited by 16
Simulation-based sensitivity analysis for non-ignorably missing data
Yin, P., & Shi, J. Q. (2017) · Statistical Methods in Medical Research · doi:10.1177/0962280217722382 · Cited by 15
Self-citationLearning compressed representations of blood samples time series with missing dataPreprint
Bianchi, F. M., Mikalsen, K. Ø., & Jenssen, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.07547 · Cited by 8
Cited by
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“In time series modeling, more than one method can add noise to the input, such as adding Gaussian noise [69], [70] and randomly setting some time steps to zero [71], [72].”
MethodSelf-citationTran, K., Vu, H.-C., Pham, L., Boudaoud, N., & Nguyen, H.-S.-H. (2024) · Mathematics · doi:10.3390/math12101569 · Cited by 14
“Noise Reduction using LSTM-Autoencoder: An unsupervised noise filter was developed based on the LSTM-Autoencoder architecture to reduce noise, remove abnormal data from raw vibration signals, and thus enhance the model’s robustness [32,33].”
Metadata
- Authors
- Zhang, J., & Yin, P.
- Affiliations
- Tsinghua Shenzhen International Graduate School (CN)
- Chinese Academy of Sciences (CN)
- Venue
- 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 760-764
- OpenAlex
- W3004471907
- Cited by
- 47
- References
- 23
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 12 · 2023: 7 · 2022: 7 · 2021: 7 · 2020: 1
- FWCI
- 2.88
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- missing data imputation, multivariate time series, bidirectional LSTM, encoder-decoder architecture, EEG, electromyography, electronic health records
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.