Hyperspectral imagery analysis using neural network techniques
Gautreaux, Mark M.
Olsen, Richard Christopher
Walters, Donald L.
MetadataShow full item record
Every material has a unique electromagnetic reflectance/emission signature which can be used to identify it. Hyperspectral imagers, by collecting high spectral resolution data, provide the ability to identify these spectral signatures. Utilization and exploitation of hyperspectral data is challenging because of the enormous data volume produced by these imagers. Most current processing and analyzation techniques involve dimensionality reduction, during which some information is lost. This thesis demonstrates the ability of neural networks and the Kohonen Self-Organizing Map to classify hyperspectral data. The possibility of real time processing is addressed. (AN)
Showing items related by title, author, creator and subject.
Bernatovich, David. (Monterey, California. Naval Postgraduate School, 1999-09);It is unclear what impact presence has on a virtual environment's (VE) ability to enhance learning and performance. Currently, there are many theories and conjectures about the effects of presence in VEs. To better the ...
Deguzman, Alan; Ebken, John; Ho, Nancy; Lai, Ray; Nunez, Denis; Raizada, Mike; Ross, Phylecia; Tran, Ngo (Monterey, California. Naval Postgraduate School, 2011-12); NPS-SE-11-014however, a design solution was not developed. It was determined through the results of the simulation, that by effectively using the bandwidth and incorporating WiMAX on various ships throughout the fleet that the disadvantaged ...
Knowles, Edwin James Jr. (1986-12);This thesis analyzes the effect of innate ability on earnings differentials by using a standard human capital earnings function. The data used is the 1984 panel (Round 6) of the National Longitudinal Survey for Youth ...