Dark formation detection using recurrent neural networks and SAR data

Topouzelis, K; Karathanassi, V; Pavlakis, P; Rokos, D

dc.contributor.author	Topouzelis, K	en
dc.contributor.author	Karathanassi, V	en
dc.contributor.author	Pavlakis, P	en
dc.contributor.author	Rokos, D	en
dc.date.accessioned	2014-03-01T02:50:19Z
dc.date.available	2014-03-01T02:50:19Z
dc.date.issued	2006	en
dc.identifier.issn	0277786X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35062
dc.subject	Dark formation	en
dc.subject	Neural networks	en
dc.subject	Oil spill	en
dc.subject	Recurrent	en
dc.subject	Remote sensing	en
dc.subject	SAR	en
dc.subject.other	Dark formation detection	en
dc.subject.other	Jordan's recurrent networks	en
dc.subject.other	Satellite images	en
dc.subject.other	Spatially finite functions	en
dc.subject.other	Classification (of information)	en
dc.subject.other	Data reduction	en
dc.subject.other	Mathematical models	en
dc.subject.other	Neural networks	en
dc.subject.other	Radar imaging	en
dc.subject.other	Synthetic aperture radar	en
dc.subject.other	Pattern recognition	en
dc.title	Dark formation detection using recurrent neural networks and SAR data	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1117/12.687852	en
heal.identifier.secondary	http://dx.doi.org/10.1117/12.687852	en
heal.identifier.secondary	636511	en
heal.publicationDate	2006	en
heal.abstract	In this paper a classification scheme based on recurrent neural networks is presented. Neural networks may be viewed as a mathematical model composed of many non-linear computational elements, called neurons, operating in parallel and massively connected by links characterized by different weights. It is well known that conventional feedforward neural networks can be used to approximate any spatially finite function given a set of hidden nodes. Recurrent neural networks are fundamentally different from feedforward architectures in the sense that they not only operate on an input space but also on an internal state space - a trace of what already has been processed by the network. This capability is referred as internal memory of the recurrent networks. The general objectives of this paper are to describe, demonstrate and test the potential of simple recurrent artificial neural networks for dark formation detection using SAR satellite images over the sea surface. The type and the architecture of the network are subjects of research. Input to the networks is the original SAR image. The network is called to classify the image into dark formations and clean sea. Elman's and Jordan's recurrent networks have been examined. Jordan's networks have been recognized as more suitable for dark formation detection. The Jordan's specific architecture with five inputs, three hidden neurons and one output is proposed for dark formation detection as it classifies correctly more than 95.5% of the data set.	en
heal.journalName	Proceedings of SPIE - The International Society for Optical Engineering	en
dc.identifier.doi	10.1117/12.687852	en
dc.identifier.volume	6365	en