Autor(es): Ribeiro, Luiz C.F. [UNESP] ; Afonso, Luis C.S. ; Papa, João P. [UNESP]
Data: 2020
Identificador Persistente: http://hdl.handle.net/11449/201208
Origem: Oasisbr
Assunto(s): Bag of samplings; Handwritten dynamics; Parkinson's disease; Recurrent Neural Networks; Bag of samplings; Bag of samplings; Handwritten dynamics; Handwritten dynamics; Parkinson's disease; Parkinson's disease; Recurrent Neural Networks; Recurrent Neural Networks
Made available in DSpace on 2020-12-12T02:26:47Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-12-01
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Parkinson's Disease (PD) is a clinical syndrome that affects millions of people worldwide. Although considered as a non-lethal disease, PD shortens the life expectancy of the patients. Many studies have been dedicated to evaluating methods for early-stage PD detection, which includes machine learning techniques that employ, in most cases, motor dysfunctions, such as tremor. This work explores the time dependency in tremor signals collected from handwriting exams. To learn such temporal information, we propose a model based on Bidirectional Gated Recurrent Units along with an attention mechanism. We also introduce the concept of “Bag of Samplings” that computes multiple compact representations of the signals. Experimental results have shown the proposed model is a promising technique with results comparable to some state-of-the-art approaches in the literature.
UNESP - São Paulo State University School of Sciences
UFSCar - Federal University of São Carlos Department of Computing
UNESP - São Paulo State University School of Sciences
FAPESP: 2013/07375-0
FAPESP: 2014/12236-1
CNPq: 307066/2017-7
CNPq: 427968/2018-6
