Period-aware content attention RNNs for time series forecasting with missing values
Explore this paper's citation graph
Summary
An extended attention model is proposed for sequence-to-sequence RNNs designed to capture periods in time series with or without missing values, and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series.
- Type
- article
- Published
- 2018-10-01
- Cited by
- 101
- References
- 44
- OpenAlex
- https://openalex.org/W2807482674
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:51879389
Keywords
Recurrent neural network, Univariate, Series (stratigraphy), Computer science, Time series
References
- Attention-Based Models for Speech Recognition
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Learning representations by back-propagating errors
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Application of critical support vector machine to time series prediction
- Generalization of backpropagation with application to a recurrent gas market model
- On Periodicity in Series of Related Terms
- An investigation of neural networks for linear time-series forecasting
- Modeling Multiple Time Series with Applications
- A review of unsupervised feature learning and deep learning for time-series modeling
- A data-mining approach to predict influent quality
- Long Short-Term Memory
- Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks
- Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm
- Finding Structure in Time
- Automatic Time Series Forecasting: The forecast Package for R
- 25 years of time series forecasting
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
- Bidirectional recurrent neural networks
- A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data
Cited by
- LSTM-based traffic flow prediction with missing data
- Unsupervised EEG feature extraction based on echo state network
- DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction
- Convolution is outer product
- Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison:A case study in hangzhou, China.
- A Wireless Sensor Network for Monitoring Environmental Quality in the Manufacturing Industry
- Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
- Convolution, attention and structure embedding.
- The Temperature Forecast of Ship Propulsion Devices from Sensor Data
- Influenza-like illness prediction using a long short-term memory deep learning model with multiple open data sources
- Prediction of early stabilization time of electrolytic capacitor based on ARIMA-Bi_LSTM hybrid model
- CAME: Content- and Context-Aware Music Embedding for Recommendation
- Hybrid time-aligned and context attention for time series prediction
- Forecasting Ambient Air Pollutants by Box-Jenkins Stochastic Models in Tehran
- Smoothed LSTM-AE: A spatio-temporal deep model for multiple time-series missing imputation
- A Period-Aware Hybrid Model Applied for Forecasting AQI Time Series
- Quasi-Periodic Time Series Clustering for Human Activity Recognition
- A Novel Hybrid Spatial-Temporal Attention-LSTM Model for Heat Load Prediction
- LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting
- Sequential Prediction of Glycosylated Hemoglobin Based on Long Short-Term Memory with Self-Attention Mechanism
Related papers
- Comparing multivariate and univariate subject-specific reference regions for blood constituents in healthy persons.
- Theory and practice of multivariate arma forecasting
- A multivariate approach to a specific problem of grouping maize cultivars.
- Outliers in multivariate time series
- Forecasting Precious Metal Returns with Multivariate Random Forests
- Forecasting precious metal returns with multivariate random forests
- Multivariate trend testing of lake water quality
- When univariate model-free time series prediction is better than multivariate
- Multivariate rank-based forecast combining techniques
- Comparison of Missing Data Infilling Mechanisms for Recovering a Real-World Single Station Streamflow Observation