An EEG-based approach for Parkinson's disease diagnosis using Capsule network

As the second most common neurodegenerative disease, Parkinson's disease has caused serious problems worldwide. However, the cause and mechanism of PD are not clear, and no systematic early diagnosis and treatment of PD have been established, many patients with PD have not been diagnosed or misdiagnosed. In this paper, we proposed an EEG-based approach to diagnosing Parkinson's disease, it mapping the frequency band energy of EEG signals to 2-dimensional images using the interpolation method and identifying classification using CapsNet, achieved 89.34% classification accuracy for short-time EEG sections, which exceeds the conventional SVM model.A comparison of separate classification accuracy across different EEG bands revealed the highest accuracy in the gamma bands, suggesting that we need pay more attention to the changes in gamma band changes in the early stages of PD.