<![CDATA[Purpose: Parkinson's is a neurological disorder that causes muscles to weaken and arms and legs to tremor over time. The discovery and identification of the stages of Parkinson's disease can substantially benefit the treatment of its symptoms. Many studies have been conducted in classifying hand-drawn -based Parkinson's disease but the resulting performance is still not optimal. The purpose of this research is to improve the performance of handwritten Parkinson's disease classification accuracy using an ensemble soft voting model.Methods: The model adopted the Parkinson's Disease Augmented Data of Handwritten dataset taken from the Kaggle Repository, where the dataset contains Healthy and Parkinson's classes with a total of 3264 images. Then, the dataset was augmented again, resulting in 2612 images in the training data and 652 images in the validation data. After that, the dataset was optimized with VGG19 feature extraction and fine-tuning and then modeled with the Ensemble Learning model. The model was evaluated with a confusion matrix, and the classification report was viewed.Result: The results of the proposed evaluation test discovered the effectiveness of the Ensemble Learning model with Fine Tuning VGG19 feature extraction by producing an accuracy of 98.9%.Novelty: This research has successfully contributed to the proposed ensemble model for Parkinson's handwriting and improved the accuracy performance of the model.]]>
Copyrights © 2023
