| Title |
|
|
|
Genetic feature selection combined with fuzzy k-NN for hyperspectral satellite imagery
|
|
| Author |
|
|
|
|
|
| Abstract |
|
|
|
| Advances in sensor technology for Earth observation make it possible to collect multispectral data in high dimensionality. For example,the NASA/JPL Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) generates image data in 220 spectral bands simultaneously. For such high-dimensionality, the appropriate selection of features has a significant effect on the cost and accuracy of an automated classifier. In this paper, a feature selection technique using genetic algorithms is applied. For the classification it has been shown that fuzzy approaches are superior in terms of performance and have the advantage that the resulting membership values give a confidence measure of the classification. In this paper, hard and fuzzy kNN classification are compared. Experiments are conducted on AVIRIS data, and the results are evaluated in the paper. | |
|
| Language |
|
|
|
English
|
|
| Source (book) |
|
|
|
Intelligent techniques and soft computing in nuclear science and engineering / Ruan, D. [edit.] |
|
| Publication |
|
|
|
Singapore : World Scientific, 2000
|
|
| ISBN |
|
|
|
981-02-4356-1
|
|
| Volume/pages |
|
|
|
p. 281-288
|
|
| ISI |
|
|
|
000186424600034
|
|
| Full text (Publisher's DOI) |
|
|
| |
|