Detection of Parkinson's Disease with Multiple Feature Extraction Models and Darknet CNN Classification

Parkinson's disease (PD) is a neurodegenerative disease in the centralnervous system. Recently, more researches have been conducted in the determina-tion of PD prediction which is really a challenging task. Due to the disorders inthe central nervous system, the syndromes like off sleep, speech disorders, olfac-tory and autonomic dysfunction, sensory disorder symptoms will occur. The ear-liest diagnosing of PD is very challenging among the doctors community. Thereare techniques that are available in order to predict PD using symptoms and dis-order measurement. It helps to save a million lives of future by early prediction. Inthis article, the early diagnosing of PD using machine learning techniques withfeature selection is carried out. In thefirst stage, the data preprocessing is usedfor the preparation of Parkinson's disease data. In the second stage, MFEA is usedfor extracting features. In the third stage, the feature selection is performed usingmultiple feature input with a principalcomponent analysis (PCA) algorithm.Finally, a Darknet Convolutional Neural Network (DNetCNN) is used to classifythe PD patients. The main advantage of using PCA- DNetCNN is that, it providesthe best classification in the image dataset using YOLO. In addition to that, theresults of various existing methods are compared and the proposed DNetCNNproves better accuracy, performance in detecting the PD at the initial stages.DNetCNN achieves 97.5 % of accuracy in detecting PD as early. Besides, theother performance metrics are compared in the result evaluation and it is provedthat the proposed model outperforms all the other existing models.