Abstract
Parkinson's disease is a neurodegenerative disease, where tremor is the main symptom. Deep brain stimulation can help manage a broad range of neurological ailments like Parkinson's disease. It involves electrical impulses delivered to specific targets in the brain to alter or modulate neural functioning. Our purpose in this study was to adopt deep learning methodologies to classify resting tremors. A novel approach for resting tremor classification in patients with Parkinson's disease using a hybrid model based on bidirectional long-short term memory and support vector machine was proposed to achieve this purpose. The proposed hybrid model combines the key properties of both classifiers. Specifically, this research exploited the efficiency of the bidirectional long short-term memory layers to identify short-term and long-term dependencies in both forward and backward directions. In addition, the support vector machine was used as a binary classifier to obtain a new effectual classification model inspired by the two formalisms for rest tremor classification. In our experiment, we adopted the 10-fold cross-validation method to ensure the reliability of the experimental results. The performed experiments proved that our proposed approach outperforms the best results achieved by other state-of-the-art methods.