Title | ||
---|---|---|
Comparison of Kohonen, scale-invariant and GTM self-organising maps for interpretation of spectral data |
Abstract | ||
---|---|---|
We investigate the use of artificial neural networks in classifying hyperspectral data. Such data when collected from remote sensors provides extremely detailed coverage of e.g. the mineralogical composition of planetary surfaces, however the volume of data supplied often overwhelms traditional classifiers. When we wish to investigate such data sets in an open-ended manner, the use of unsupervised learning is a pre-requisite. A set of remotely sensed spectral images are use to train several different topology preserving neural networks. In each met hod, the data is projected onto a two dimensional grid designed to visualise the data set in a low dimensional space. Such mappings allow graceful degradation of the classifications given by the mappings since nearby data points are mapped to the same or similar classifications. |
Year | Venue | Keywords |
---|---|---|
1999 | ESANN | remote sensing,neural network,graceful degradation,scale invariance,artificial neural network,unsupervised learning,spectral imaging |
Field | DocType | Citations |
Data mining,Data set,Computer science,Self-organizing map,Unsupervised learning,Artificial intelligence,Artificial neural network,Data point,Pattern recognition,Hyperspectral imaging,Fault tolerance,Machine learning,Grid | Conference | 3 |
PageRank | References | Authors |
0.86 | 2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Donald Macdonald | 1 | 117 | 9.79 |
Stephen Mcglinchey | 2 | 9 | 2.94 |
John Kawala | 3 | 3 | 0.86 |
Colin Fyfe | 4 | 508 | 55.62 |