Gap imputation in related multivariate time series through recurrent neural network-based denoising autoencoder
[EN] Technological advances in industry have made it possible to install many connected sensors, generating a great amount of observations at high rate. The advent of Industry 4.0 requires analysis capabilities of heterogeneous data in form of related multivariate time series. However, missing data...
| Autores: | , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2024 |
| País: | España |
| Institución: | Universidad Rey Juan Carlos |
| Repositorio: | BULERIA. Repositorio Institucional de la Universidad de León |
| OAI Identifier: | oai:buleria.unileon.es:10612/19963 |
| Acceso en línea: | https://hdl.handle.net/10612/19963 |
| Access Level: | acceso abierto |
| Palabra clave: | Ingeniería de sistemas Sensor observations Denoising autoencoder Gap imputation Missing data Multivariate time series Recurrent neural network 3310.03 Procesos Industriales 3311.01 Tecnología de la Automatización |
| Sumario: | [EN] Technological advances in industry have made it possible to install many connected sensors, generating a great amount of observations at high rate. The advent of Industry 4.0 requires analysis capabilities of heterogeneous data in form of related multivariate time series. However, missing data can degrade processing and lead to bias and misunderstandings or even wrong decision-making. In this paper, a recurrent neural network-based denoising autoencoder is proposed for gap imputation in related multivariate time series, i.e., series that exhibit spatio-temporal correlations. The denoising autoencoder (DAE) is able to reproduce input missing data by learning to remove intentionally added gaps, while the recurrent neural network (RNN) captures temporal patterns and relationships among variables. For that reason, different unidirectional (simple RNN, GRU, LSTM) and bidirectional (BiSRNN, BiGRU, BiLSTM) architectures are compared with each other and to state-of-the-art methods using three different datasets in the experiments. The implementation with BiGRU layers outperforms the others, effectively filling gaps with a low reconstruction error. The use of this approach is appropriate for complex scenarios where several variables contain long gaps. However, extreme scenarios with very short gaps in one variable or no available data should be avoided. © 2024 - The authors. Published by IOS Press. |
|---|