ParViT: A modified Vision Transformer architecture for Parkinson’s Disease identification using EEG signals
Published in IEEE ICSSES 2024, 2024
Parkinson’s disease (PD) is a degenerative neurological condition that affects millions of individuals worldwide and is marked by both motor and non-motor indicators. Prompt detection and forecasting of PD is essential to enhance patient outcomes through timely intervention, and early detection of PD risk factors can help with the execution of management and treatment strategies that are beneficial in delaying the progression of the ailment.
This work presents a novel hybrid framework for prediction of PD. The methodology begins by employing the Short-Time Fourier Transform (STFT) to process raw electroencephalography (EEG) data, facilitating the extraction of pertinent time-frequency characteristics. These features are then organized into time-frequency blocks and inputted into an enhanced Vision Transformer (ViT) architecture, named ParViT, for classification of subjects into PD and Healthy Controls (HC).
The proposed method demonstrates superior performance compared to existing techniques in PD identification tasks, achieving an accuracy rate of 98.25%, along with precision, recall, specificity, and F1 scores of 98.20%, 98.27%, 98.47%, and 98.24% respectively, as evidenced by experiments conducted on the publicly available UC San Diego dataset.
Recommended citation: De, S., Sayyad, A., Kotian, H., & Gupta, A. K. (2024). "ParViT: A modified Vision Transformer architecture for Parkinson's Disease identification using EEG signals." IEEE ICSSES.
Download Paper