Title :
Self Organizing Maps and bit signature: A study applied on signal language recognition
Author :
Neris, Marrony N. ; Silva, Alexandre J. ; Peres, Sarajane M. ; Flores, Franklin C.
Author_Institution :
State Univ. of Maringa (UEM), Maringa
Abstract :
Self organizing map (SOM) is a kind of artificial neural network with a competitive and unsupervised learning. This technique is commonly used to dataset clustering tasks and can be useful in patterns recognition problems. This paper presents an artificial neural network application to signals language recognition problem, where the image representation is given by bit signatures. The recognition results are promising and are presented in this paper. More, some analysis about the combination ldquoSOM + bit signaturerdquo improved our understanding about the characteristics of the LIBRAS signals and the conclusions are also listed in this paper.
Keywords :
gesture recognition; image representation; pattern clustering; self-organising feature maps; unsupervised learning; LIBRAS signals; artificial neural network; bit signature; competitive learning; dataset clustering; image representation; patterns recognition; self organizing maps; signal language recognition; unsupervised learning; Algorithm design and analysis; Artificial neural networks; Deafness; Image recognition; Image representation; Neurons; Pattern recognition; Self organizing feature maps; Signal analysis; Unsupervised learning;
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2008.4634211