Neural networks : A new analysis tool for GIS and remote sensing
This paper discusses new techniques for data analysis which may help to provide innovative and more accurate GIS products derived automatically from satellite imagery. Artificial neural networks (ANNs) consist of several layers of processing elements connected together by weighted pathways which dictate how patterns presented at the input layer are to be classified and output. Research into the use of ANNs is discussed and their ability to provide land-cover information with high classification accuracies is examined.
Bibliographic Reference: Article: GIS Europe, October 1993 (1993) pp. 38-40
Record Number: 199410830 / Last updated on: 1994-11-28
Original language: en
Available languages: en