Classification of the Speech Signal of Parkinson's Patient using Optimized Ensemble Model

One of the most prevalent neural disorders that creates difficulties in walking and speaking of the patients is Parkinson’s. Authors proposed a stacked ensemble classifier to classify the speech signals of the Parkinson's disease patients. The dataset used is from the UCI machine learning repository that consists of the features of the speech signals. The stacked model is a two stage approach where the first stage is the base classifier. As the base classifier four standard deep neural networks (DNNs) are used. The output of the first stage is given to the second stage which is Meta classifier. Support vector machine and optimal gradient boosting meta classifiers are used to compare the model’s performance with each other. The accuracy is found better in optimized Meta classifier as 98 %.