We construct an attention-based sparse graph convolutional neural network (ASGCNN) for diagnosing PD. Our ASGCNN model uses a graph structure to represent ...

In particular, Chang et al. (2023) obtained 87.67% accuracy for EEG-based Parkinson's disease recognition based on attention-based sparse graph convolutional ...

2023/11/07 · We selected a sparse graph convolutional neural network with an attention mechanism to enhance the effectiveness of EEG-based PD recognition [27] ...

We selected a sparse graph convolutional neural network with an attention mechanism to enhance the effectiveness of EEG-based PD recognition [27]. The model ...

EEG-Based Parkinson's Disease Recognition Via Attention-based Sparse Graph Convolutional Neural Network. H Chang, B Liu, Y Zong, C Lu, X Wang. IEEE Journal of ...

Here, we construct an attention-based sparse graph convolutional neural network (ASGCNN) for diagnosing PD. Our ASGCNN model uses a graph structure to represent ...

2024/08/01 · We proposed a novel graph neural network (GNN) technique for explainable PD detection using resting state EEG.

2024/07/24 · We introduce a novel adaptive method for extracting node features from EEG signals utilizing a distinctive task-induced self-supervised learning technique.

EEG-Based Parkinson's Disease Recognition Via Attention-based Sparse Graph Convolutional Neural Network. H Chang, B Liu, Y Zong, C Lu, X Wang. IEEE Journal of ...

The aim of this study is to develop a PD classification method based on EEG signals. A new EEG classification framework, referred to as 2D-MDAGTS, is proposed.