Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks
This paper describes the use of Bayesian networks for the reduction of irrelevant features [1,2] in the recognition of oceanic structures in satellite images. Bayesian networks are used to validate the symbolic knowledge -provided by neuro symbolic or HLKPs (High Level Knowledge Processors) nets- an...
| Main Authors: | , , , |
|---|---|
| Format: | info:eu-repo/semantics/report |
| Language: | English |
| Published: |
2012
|
| Online Access: | http://hdl.handle.net/10835/1545 |
| _version_ | 1789406600326283264 |
|---|---|
| author | Piedra Fernández, José Antonio Salmerón Cerdán, Antonio Guindos, Francisco J. Cantón-Garbín, Manuel |
| author_facet | Piedra Fernández, José Antonio Salmerón Cerdán, Antonio Guindos, Francisco J. Cantón-Garbín, Manuel |
| author_sort | Piedra Fernández, José Antonio |
| collection | DSpace |
| description | This paper describes the use of Bayesian networks for the reduction of irrelevant features [1,2] in the recognition of oceanic structures in satellite images. Bayesian networks are used to validate the symbolic knowledge -provided by neuro symbolic or HLKPs (High Level Knowledge Processors) nets- and the numeric knowledge. This provides an automatic interpretation of images. The main objective of this work is the construction of an automatic recognition system for processing AVHRR (Advanced Very High Resolution Radiometer) images from NOAA (National Oceanographic and Atmospheric Administration) satellites to detect and locate oceanic phenomena of interest like upwellings, eddies and island wakes. With this aim, this paper reports on a methodology of knowledge selection and validation. In knowledge selection, filter measures are used. For knowledge validation, Bayesian networks (Naïve Bayes, TAN and KDB) are evaluated. |
| format | info:eu-repo/semantics/report |
| id | oai:repositorio.ual.es:10835-1545 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-15452023-04-12T19:40:14Z Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks Piedra Fernández, José Antonio Salmerón Cerdán, Antonio Guindos, Francisco J. Cantón-Garbín, Manuel This paper describes the use of Bayesian networks for the reduction of irrelevant features [1,2] in the recognition of oceanic structures in satellite images. Bayesian networks are used to validate the symbolic knowledge -provided by neuro symbolic or HLKPs (High Level Knowledge Processors) nets- and the numeric knowledge. This provides an automatic interpretation of images. The main objective of this work is the construction of an automatic recognition system for processing AVHRR (Advanced Very High Resolution Radiometer) images from NOAA (National Oceanographic and Atmospheric Administration) satellites to detect and locate oceanic phenomena of interest like upwellings, eddies and island wakes. With this aim, this paper reports on a methodology of knowledge selection and validation. In knowledge selection, filter measures are used. For knowledge validation, Bayesian networks (Naïve Bayes, TAN and KDB) are evaluated. 2012-05-28T08:15:58Z 2012-05-28T08:15:58Z 2005 info:eu-repo/semantics/report Actas de la VI Jornadas de Transferencia de Tecnología en I.A., pp. 133-140. http://hdl.handle.net/10835/1545 en info:eu-repo/semantics/openAccess VI Jornadas de Transferencia de Tecnología en I.A. |
| spellingShingle | Piedra Fernández, José Antonio Salmerón Cerdán, Antonio Guindos, Francisco J. Cantón-Garbín, Manuel Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title | Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title_full | Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title_fullStr | Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title_full_unstemmed | Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title_short | Reduction of Irrelevant Features in Oceanic Satellite Images by means of Bayesian Networks |
| title_sort | reduction of irrelevant features in oceanic satellite images by means of bayesian networks |
| url | http://hdl.handle.net/10835/1545 |
| work_keys_str_mv | AT piedrafernandezjoseantonio reductionofirrelevantfeaturesinoceanicsatelliteimagesbymeansofbayesiannetworks AT salmeroncerdanantonio reductionofirrelevantfeaturesinoceanicsatelliteimagesbymeansofbayesiannetworks AT guindosfranciscoj reductionofirrelevantfeaturesinoceanicsatelliteimagesbymeansofbayesiannetworks AT cantongarbinmanuel reductionofirrelevantfeaturesinoceanicsatelliteimagesbymeansofbayesiannetworks |