Dynamic Handwriting Analysis for Parkinson's Disease Identification using C-BiGRU Model
| Autor: | Imran Siddiqi, Uzma Masroor, Momina Moetesum, Farah Javed |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Parkinson's disease
business.industry Computer science Pattern recognition 02 engineering and technology medicine.disease 03 medical and health sciences Identification (information) Parkinsonian Symptoms 0302 clinical medicine Handwriting Feature (computer vision) 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | ICFHR |
| DOI: | 10.1109/icfhr2020.2020.00031 |
| Popis: | Parkinson's disease (PD) is commonly characterized by several motor impairments like tremor, muscular rigidity and bradykinesia, that are collectively termed as ‘Parkinson's disease dysgraphia’. In an attempt to identify these motor-based Parkinsonian symptoms, experts have persistently been evaluating various dynamic attributes of handwriting, like pen pressure/position, stroke speed/trajectory, and on-surface/in-air time taken, captured with the help of online acquisition tools. Such devices not only capture various aspects of handwriting but provide rich sequential information that can be utilized to identify unique patterns from handwriting samples of PD patients. In this paper, we propose a model based on Bidirectional Gated Recurrent Units (BiGRU) to assess the potential of handwriting-based sequential information in the identification of Parkinsonian symptoms. One-dimensional convolution is applied to raw sequences and the resulting feature sequences are employed to train the BiGRU model for prediction. The results of our experiments validate the potential of our proposed technique in comparison to the state-of-the-art. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|