A comparison of neural network input vector selection techniques

Authors:
Belinda Choi;Tim Hendtlass;Kevin Bluff
Affiliations:
Department of Information Technology, La Trobe University, Bendigo;Department of Information Technology, La Trobe University, Bendigo;School of Information Technology, Swinburne University of Technology, Melbourne
Venue:
IEA/AIE'2004 Proceedings of the 17th international conference on Innovations in applied artificial intelligence
Year:
2004

Citing 0
Cited 3

Dealing with limited data in ballistic impact scenarios: an empirical comparison of different neural network approaches

Applied Intelligence
An effective feature selection scheme via genetic algorithm using mutual information

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part II
Feature selection in SVM based on the hybrid of enhanced genetic algorithm and mutual information

MDAI'06 Proceedings of the Third international conference on Modeling Decisions for Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of the difficulties of using Artificial Neural Networks (ANNs) to estimate atmospheric temperature is the large number of potential input variables available. In this study, four different feature extraction methods were used to reduce the input vector to train four networks to estimate temperature at different atmospheric levels. The four techniques used were: genetic algorithms (GA), coefficient of determination (CoD), mutual information (MI) and simple neural analysis (SNA). The results demonstrate that of the four methods used for this data set, mutual information and simple neural analysis can generate networks that have a smaller input parameter set, while still maintaining a high degree of accuracy.