• Corpus ID: 52116677

Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results

@article{Cirstea2018CorrelatedTS,
  title={Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results},
  author={Razvan-Gabriel Cirstea and Darius-Valer Micu and Gabriel-Marcel Muresan and Chenjuan Guo and B. Yang},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.09794}
}
Cyber-physical systems often consist of entities that interact with each other over time. Meanwhile, as part of the continued digitization of industrial processes, various sensor technologies are deployed that enable us to record time-varying attributes (a.k.a., time series) of such entities, thus producing correlated time series. To enable accurate forecasting on such correlated time series, this paper proposes two models that combine convolutional neural networks (CNNs) and recurrent neural… 

Figures and Tables from this paper

Correlated Time Series Forecasting using Multi-Task Deep Neural Networks
TLDR
To enable accurate forecasting on correlated time series, this paper proposes two models that combine convolutional neural networks (CNNs) and recurrent neural Networks (RNNs) that outperform baselines in most settings.
KENN: Enhancing Deep Neural Networks by Leveraging Knowledge for Time Series Forecasting
TLDR
This paper proposes a novel knowledge fusion architecture, Knowledge Enhanced Neural Network (KENN), for time series forecasting that specifically aims towards combining strengths of both knowledge and data domains while mitigating their individual weaknesses and shows that KENN not only reduces data dependency of the overall framework but also improves performance by producing predictions that are better than the ones produced by purelyknowledge and data driven domains.
An Ensemble Model Based on Adaptive Noise Reducer and Over-Fitting Prevention LSTM for Multivariate Time Series Forecasting
TLDR
A novel ensemble three-phase model called adaptive noise reducer-stacked auto-encoder-validating-AdaBoost-based long short-term memory (ANR-SAE-VALSTM) is proposed, which has achieved the best prediction performance in all prediction horizons.
Towards Better Forecasting by Fusing Near and Distant Future Visions
TLDR
Inspired by the Construal Level Theory of psychology, this model aims to improve the predictive performance by fusing forecasting information (i.e., future visions) of different future time by combining traditional Autoregression model with the neural network to solve the scale insensitive problem.
Traffic Flow Forecast of Road Networks With Recurrent Neural Networks
TLDR
A variety of model architectures, forecast horizons and input data were investigated and most often the vector output model with gated recurrent units achieved the smallest error on the test set over all considered prediction scenarios.
Federated Multi-task Learning with Hierarchical Attention for Sensor Data Analytics
TLDR
A novel federated multi-task hierarchical attention model (FATHOM) that jointly trains classification/regression models from multiple distributed devices and allows for the visual characterization of key features learned at the input task level and the global temporal level is designed.
Can deep learning beat numerical weather prediction?
TLDR
It is thought that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach.
Federated Multi-task Hierarchical Attention Model for Sensor Analytics
TLDR
A novel federated multi-task hierarchical attention model (FATHOM) that jointly trains classification/regression models from multiple sensors and outperforms a wide range of competitive baselines in both classification and regression settings on activity recognition and environment monitoring datasets.
Distinguishing Trajectories from Different Drivers using Incompletely Labeled Trajectories
TLDR
A Trajectory-to-Image( T2I) encoding scheme that captures both geographic features and driving behavior features of trajectories in 3D images and a multi-task, deep learning model called T2INet for estimating the total number of drivers in the unlabeled trajectories.
WLA4ND: a Wearable Dataset of Learning Activities for Young Adults with Neurodiversity to Provide Support in Education
TLDR
WLA4ND, a dataset of learning activities performed by eight young adults with neurodiversity collected from smartwatch sensors, demonstrates that existing activity recognition technologies can be applied to neurodiverse populations.
...
1
2
...

References

SHOWING 1-10 OF 25 REFERENCES
A Robust Approach for Multivariate Time Series Forecasting
TLDR
An approach based on convolutional neural network with a feature extraction layer added before convolution layer to extract multivariate features and handle multivariate time series data, as well as decreases the effect of distortion by transforming the sample into a denser representation.
Time series forecasting using neural networks vs. Box- Jenkins methodology
TLDR
It is found that for time series of different complexities there are optimal neural network topologies and parameters that enable them to learn more efficiently and are also parsimonious in their data requirements.
Outlier Detection for Multidimensional Time Series Using Deep Neural Networks
TLDR
A framework for outlier detection in time series that can be used for identifying dangerous driving behavior and hazardous road locations is proposed and proposed autoencoders based on convolutional neural networks and long-short term memory neural networks are studied.
Time-series Extreme Event Forecasting with Neural Networks at Uber
TLDR
A novel endto-end recurrent neural network architecture is proposed that outperforms the current state of the art event forecasting methods on Uber data and generalizes well to a public M3 dataset used for time-series forecasting competitions.
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
TLDR
This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.
Time series forecasting using a hybrid ARIMA and neural network model
  • G. Zhang
  • Computer Science
    Neurocomputing
  • 2003
A hybrid neural network and ARIMA model for water quality time series prediction
Travel Cost Inference from Sparse, Spatio-Temporally Correlated Time Series Using Markov Models
TLDR
This work uses spatio-temporal hidden Markov models (STHMM) to model correlations among different traffic time series to predict travel cost from GPS tracking data from probe vehicles, and provides algorithms that are able to learn the parameters of an STHMM while contending with the sparsity, spatiotemporal correlation, and heterogeneity of the time series.
Long Short-Term Memory
TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
...
1
2
3
...