Title :
A modular neural architecture for bathythermograms classification
Author :
Stéphan, Y. ; Frachon, B.
Author_Institution :
Centre Mil. d´´Oceanogr., Brest, France
Abstract :
Presents a neural approach for bathythermogram classification. A modular architecture of multi-layer perceptrons (MLP) stemming from a preclassification into five main types of temperature profile is used. The types and classes are issued from a pre-established typology. The performance of this approach is evaluated on a Red Sea profiles database. The results show that the method is efficient but suffers from classes overlapping
Keywords :
feedforward neural nets; oceanographic techniques; pattern recognition; temperature measurement; XBT; bathythermogram; bathythermograph; class overlapping; data classification; feedforward neural net; geophysics computing; measurement technique; method; modular neural architecture; multi-layer perceptron; neural net; neural network; ocean temperature; preclassification; sea; thermal structure; vertical profile; Area measurement; Databases; Extraterrestrial measurements; Marine vehicles; Multilayer perceptrons; Ocean temperature; Oceanographic techniques; Sea measurements; Statistics; Time measurement;
Conference_Titel :
OCEANS '93. Engineering in Harmony with Ocean. Proceedings
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-1385-2
DOI :
10.1109/OCEANS.1993.325963
