No abstract

No abstract

Parkinson's disease is a disease of the central nervous system that leads to severe difficulties in motor functions. Developing computational tools for recognition of Parkinson's disease at the early stages is very desirable for alleviating the symptoms. In this paper, we developed a discriminative model based on a selected feature subset and applied several classifier algorithms in the context of disease detection. All classifier performances from the point of both stand-alone and rotation-forest ensemble approach were evaluated on a Parkinson's disease data-set according to a blind testing protocol. The new method compared to hitherto methods outperforms the state-of-the-art in terms of both predictions of accuracy (98.46%) and area under receiver operating characteristic curve (0.99) scores applying rotation-forest ensemble k-nearest neighbour classifier algorithm.

No abstract

Deep learning techniques have become vital in many fields in the modern era because they are excellent at analysing and predicting real big data to act in different situations. Although it is marvellous in many aspects, it is prone to misinterpretation of data, so teams of experienced specialists cannot be dispensed with in following up on the execution stages of data analysis. Convolutional Neural Network is one of the most significant deep learning techniques. It is widely employed in visual image analysis. In this article, R-CNN and Fast R-CNN are summarised and compared and are the best in image analysis. This article concluded that the most suitable performance is for Fast R-CNN in testing and training.