A Deep Structural Model for Analyzing Correlated Multivariate Time Series

@article{Hu2019ADS,
  title={A Deep Structural Model for Analyzing Correlated Multivariate Time Series},
  author={Changwei Hu and Yifan Hu and Sungyong Seo},
  journal={2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)},
  year={2019},
  pages={69-74}
}
  • Changwei Hu, Yifan Hu, Sungyong Seo
  • Published 1 December 2019
  • Computer Science, Mathematics
  • 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)
Multivariate time series are routinely encountered in real-world applications, and in many cases, these time series are strongly correlated. In this paper, we present a deep learning structural time series model which can (i) handle correlated multivariate time series input, and (ii) forecast the targeted temporal sequence by explicitly learning/extracting the trend, seasonality, and event components. The trend is learned via a 1D and 2D temporal CNN and LSTM hierarchical neural net. The CNN… Expand
Novel Radar-based Gesture Recognition System using Optimized CNN-LSTM Deep Neural Network for Low-power Microcomputer Platform
TLDR
This research project proposes an alternative signal processing approach – using the continuous wavelet transform, which enables us to see the distribution of frequencies formed by every gesture, thus enabling a human-machine interface implementation on the embedded devices. Expand
MRC-LSTM: A Hybrid Approach of Multi-scale Residual CNN and LSTM to Predict Bitcoin Price
TLDR
A novel approach, which combines a Multi-scale Residual Convolutional neural network (MRC) and a Long Short-Term Memory (LSTM) to implement Bitcoin closing price prediction, and experimental results show that MRC-L STM significantly outperforms a variety of other network structures. Expand

References

SHOWING 1-10 OF 21 REFERENCES
Long-term recurrent convolutional networks for visual recognition and description
TLDR
A novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and shows such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized. Expand
The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
  • S. Hochreiter
  • Mathematics, Computer Science
  • Int. J. Uncertain. Fuzziness Knowl. Based Syst.
  • 1998
TLDR
The de-caying error flow is theoretically analyzed, methods trying to overcome vanishing gradients are briefly discussed, and experiments comparing conventional algorithms and alternative methods are presented. Expand
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. Expand
Minute-ahead stock price forecasting based on singular spectrum analysis and support vector regression
  • S. Lahmiri
  • Computer Science, Mathematics
  • Appl. Math. Comput.
  • 2018
TLDR
The presented SSA-PSO-SVR largely outperforms the conventional WT-FFNN, ARMA, polynomial regression, and naive model in terms of MAE, MAPE and RMSE and shows evident potential for noisy financial time series analysis and forecasting. Expand
Analysis of Financial Time Series
  • E. Ziegel
  • Mathematics, Computer Science
  • Technometrics
  • 2002
TLDR
The overall objective of the book is to provide some knowledge of financial time series, introduce some statistical tools useful for analyzing these series and gain experience in financial applications of various econometric methods. Expand
Structural Time Series Models
1 Trend and Cycle Decomposition y t = t + t where y t is an n 1 vector and t and t represent trend and cycle components respectively. This decomposition into components is not unique. Beveridge andExpand
Estimation Procedures for Structural Time Series Models
A univariate structural time series model based on the traditional decomposition into trend, seasonal and irregular components is defined. A number of methods of computing maximum likelihoodExpand
Time series forecasting using a hybrid ARIMA and neural network model
  • G. Zhang
  • Computer Science
  • Neurocomputing
  • 2003
TLDR
Experimental results with real data sets indicate that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately. Expand
Deep Learning: A Practitioner's Approach
TLDR
This hands-on guide provides the most practical information available on the subject of deep learning, and helps you get started building efficient deep learning networks. Expand
Character-Aware Neural Language Models
TLDR
A simple neural language model that relies only on character-level inputs that is able to encode, from characters only, both semantic and orthographic information and suggests that on many languages, character inputs are sufficient for language modeling. Expand
...
1
2
3
...