Application of Fuzzy Lattice Neurocomputing (FLN) in Ocean Satellite Images for Pattern Recognition
Summary. The main objective of this work is to improve the automated interpretation of ocean satellite images using a fuzzy lattice system that recognizes the most important ocean structures in satellite AVHRR (Advanced Very High Resolution Radiometer) images. This chapter presents a hybrid model based on an expert system segmentation method, a method of correlation-based feature selection, and a few classi.ers including Bayesian nets (BN) and fuzzy lattice neural networks. The results obtained by the fuzzy lattice system are clearly better than the results obtained by ANNs (Artificial Neural Nets), knowledge based reasoning systems, and graphic expert system (GES).
KeywordsFeature Selection Bayesian Network Fuzzy Rule Cyclonic Eddy Linguistic Label
Unable to display preview. Download preview PDF.