Parkinson's disease identification through Optimum-Path Forest

• Autor(a) principal: Spadoto, André A.
• Data de Publicação: 2010
• Outros Autores: Guido, Rodrigo C., Papa, João Paulo [UNESP], Falcão, Alexandre X.
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1109/IEMBS.2010.5627634; http://hdl.handle.net/11449/72041
• topic: Artificial intelligence techniques; Artificial Neural Network; Automatic recognition; Commonly used; Feature space; Kernel mapping; Parkinson's disease; Pattern recognition techniques; PD identification; Supervised classification; Diseases; Pattern recognition; Neural networks

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.