Sparsely connected neural network-based time series forecasting

Authors:
Z. X. Guo;W. K. Wong;M. Li
Affiliations:
Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, PR China;Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, PR China;Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, PR China
Venue:
Information Sciences: an International Journal
Year:
2012

Citing 7
Cited 1

An investigation of the use of feedforward neural networks for forecasting

An investigation of the use of feedforward neural networks for forecasting
A neural network ensemble method with jittered training data for time series forecasting

Information Sciences: an International Journal
Improving artificial neural networks' performance in seasonal time series forecasting

Information Sciences: an International Journal
Analysis and modeling of multivariate chaotic time series based on neural network

Expert Systems with Applications: An International Journal
A forecasting solution to the oil spill problem based on a hybrid intelligent system

Information Sciences: an International Journal
Type-2 fuzzy neural networks with fuzzy clustering and differential evolution optimization

Information Sciences: an International Journal
Partially connected feedforward neural networks structured by input types

IEEE Transactions on Neural Networks

Let a biogeography-based optimizer train your Multi-Layer Perceptron

Information Sciences: an International Journal

Quantified Score

Hi-index	0.07

Visualization

Abstract

This study addresses the time series forecasting performance of sparsely connected neural networks (SCNNs). A novel type of SCNNs is presented based on the Apollonian networks. In terms of three types of publicly available benchmark data, extensive experiments were conducted to compare the forecasting performance of the proposed SCNNs, randomly connected SCNNs and traditional feed-forward neural networks. The comparison results show that the proposed networks generate the best time series forecasting performance and the traditional networks generate the worst in terms of training speed and forecasting accuracy. The performance of the proposed SCNNs is evaluated further based on different training sample sizes and training accuracy measures. The experimental results indicate that larger training sample sizes do not necessarily give better forecasts while forecasts based on training accuracy measures, MAD and MAPE are generally superior to those based on MSE and MASE.