Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/111876
Title: Sequence-based Dynamic Handwriting Analysis for Parkinson's Disease Detection with One-dimensional Convolutions and BiGRUs
Authors: Díaz Cabrera, Moisés 
Momina Moetesum
Imran Siddiqi
Gennaro Vessio
UNESCO Clasification: 3304 Tecnología de los ordenadores
320507 Neurología
Keywords: Computer-aided diagnosis
Dynamic handwriting analysis
Parkinson's disease
Recurrent neural networks
Issue Date: 2021
Journal: Expert Systems with Applications 
Abstract: Parkinson's disease (PD) is commonly characterized by several motor symptoms, such as bradykinesia, akinesia, rigidity, and tremor. The analysis of patients' fine motor control, particularly handwriting, is a powerful tool to support PD assessment. Over the years, various dynamic attributes of handwriting, such as pen pressure, stroke speed, in-air time, etc., which can be captured with the help of online handwriting acquisition tools, have been evaluated for the identification of PD. Motion events, and their associated spatio-temporal properties captured in online handwriting, enable effective classification of PD patients through the identification of unique sequential patterns. This paper proposes a novel classification model based on one-dimensional convolutions and Bidirectional Gated Recurrent Units (BiGRUs) to assess the potential of sequential information of handwriting in identifying Parkinsonian symptoms. One-dimensional convolutions are applied to raw sequences as well as derived features; the resulting sequences are then fed to BiGRU layers to achieve the final classification. The proposed method outperformed state-of-the-art approaches on the PaHaW dataset and achieved competitive results on the NewHandPD dataset.
URI: http://hdl.handle.net/10553/111876
ISSN: 0957-4174
DOI: 10.1016/j.eswa.2020.114405
Source: Expert Systems with Applications [ISSN 0957-4174], v. 168, 114405, (Abril 2021)
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

55
checked on Oct 6, 2024

WEB OF SCIENCETM
Citations

44
checked on Oct 6, 2024

Page view(s)

116
checked on Sep 28, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.