Variable Selection for Multivariate Time Series Prediction with Neural Networks

Authors:
Min Han;Ru Wei
Affiliations:
School of Electronic and Information Engineering, Dalian University of Technology, Dalian, China 116023;School of Electronic and Information Engineering, Dalian University of Technology, Dalian, China 116023
Venue:
Neural Information Processing
Year:
2007

Citing 5
Cited 0

Skeletonization: a technique for trimming the fat from a network via relevance assessment

Advances in neural information processing systems 1
Dynamics from multivariate time series

Physica D
Feature selection with neural networks

Pattern Recognition Letters
Study of nonlinear multivariate time series prediction based on neural networks

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
An iterative pruning algorithm for feedforward neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a variable selection algorithm based on neural networks for multivariate time series prediction. Sensitivity analysis of the neural network error function with respect to the input is developed to quantify the saliency of each input variables. Then the input nodes with low sensitivity are pruned along with their connections, which represents to delete the corresponding redundant variables. The proposed algorithm is tested on both computer-generated time series and practical observations. Experiment results show that the algorithm proposed outperformed other variable selection method by achieving a more significant reduction in the training data size and higher prediction accuracy.