Time Series Prediction With Incomplete Dataset Based on Deep Bidirectional Echo State Network
Authors:
Open Access
- 21 October 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 152533-152544
Abstract
In the complex industrial environment, data missing situation is often occurred in the process of data acquisition and transition. The major contribution of the paper is the proposal of a deep bidirectional echo state network (DBESN) framework for time series prediction with such incomplete dataset. Instead of data imputation methodology, a bidirectional fusion reservoir is here designed to extract the deep bidirectional feature along with forward and backward time scales, based on which a deep autoencoder echo state network (DAESN) and a deep bidirectional state echo state network (DBSESN) are constructed for the incomplete output and input samples, respectively. As for such two networks, a bidirectional echo state network (BESN) is proposed for connecting them to constitute the DBESN framework for prediction. To verify the effectiveness of the proposed method, one synthetic time series as well as two real-world industrial datasets are employed to conduct the comparative experiments. The experimental results demonstrate that the proposed method outperforms other comparative ones at various missing rates.Keywords
Funding Information
- National Key R&D Program of China (2017YFA0700300)
- National Natural Science Foundation of China (61833003, 61533005, 61873048)
- Northwestern Polytechnical University (DUT18TD07, DUT19JC40)
- Outstanding Youth Sci-Tech Talent Program of Dalian (2018RJ01)
This publication has 31 references indexed in Scilit:
- Financial time series prediction using a dendritic neuron modelKnowledge-Based Systems, 2016
- A Probabilistic Just-in-Time Learning Framework for Soft Sensor Development With Missing DataIEEE Transactions on Control Systems Technology, 2016
- Generalized type-2 fuzzy weight adjustment for backpropagation neural networks in time series predictionInformation Sciences, 2015
- Prediction of telephone calls load using Echo State Network with exogenous variablesNeural Networks, 2015
- Improved methods for the imputation of missing data by nearest neighbor methodsComputational Statistics & Data Analysis, 2015
- Tree-based prediction on incomplete data using imputation or surrogate decisionsInformation Sciences, 2015
- Back propagation neural network with adaptive differential evolution algorithm for time series forecastingExpert Systems with Applications, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask LearningIEEE Transactions on Intelligent Transportation Systems, 2014
- The theoretic framework of local weighted approximation for microarray missing value estimationPattern Recognition, 2010