DocumentCode :
619638
Title :
Modelling of suspended matter by hybrid RBF-IGNG network
Author :
Alilat, Parid ; Loumi, Saliha
Author_Institution :
Lab. of Image Process. & Radiat., Inst. of Electron., Algiers, Algeria
fYear :
2013
fDate :
8-9 May 2013
Firstpage :
1
Lastpage :
7
Abstract :
The aim of this paper is to look for efficient algorithms allowing to deal with taking into account the modelization and the cartography of the sea components. Through the analysis carried on the family of Growing Neural Gas with an evolutive (scalable) architecture and with non supervised competitive learning, some modifications and improvements (modified IGNG) have been brought in order to associate them with the neural network of modelization; this modification is essentially focused on the automation of parameters. So as to improve the results, we propose in our technique to widen the sphere of influence of the RBF by multiplying the Gaussian widths by a factor which is automatically sought for so as to minimize the error of modelization on the learning basis. A study on the type of Gaussian widths of the REF and their shapes has been carried. The developed methodology, the implemented procedures and the proposed networks all yielded satisfying results.
Keywords :
Gaussian processes; cartography; geophysics computing; oceanographic techniques; radial basis function networks; unsupervised learning; Gaussian width; hybrid RBF-IGNG network; incremental growing neural gas; neural network; nonsupervised competitive learning; parameter automation; sea component cartography; sea component modelization; suspended matter modelling; Atmospheric measurements; Image resolution; Optical imaging; Optical variables measurement; Particle measurements; Weight measurement; Classification; IGNG; Neural network; RBF; Remote sensing; Suspended matter;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Systems: Theories and Applications (SITA), 2013 8th International Conference on
Conference_Location :
Rabat
Print_ISBN :
978-1-4799-0297-2
Type :
conf
DOI :
10.1109/SITA.2013.6560808
Filename :
6560808
Link To Document :
بازگشت