Sparsely connected neural network-based time series forecasting

Z. X. Guo, Wai Keung Wong, M. Li

Research output: Journal article publicationJournal articleAcademic researchpeer-review

23 Citations (Scopus)

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.
Original languageEnglish
Pages (from-to)54-71
Number of pages18
JournalInformation Sciences
Volume193
DOIs
Publication statusPublished - 15 Jun 2012

Keywords

  • Error measures
  • M3-competition
  • Sparsely connected neural networks
  • Telecommunications data
  • Time series
  • Training sample sizes

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Software
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this