EARLY DETECTION OF PARKINSON’S DISEASE USING MACHINE LEARNING
Unknown authors
Abstract
Parkinson's complaint (PD) is one of the major public health conditions in the world which is precipitously adding day by day and had its effect on numerous countries.therefore, it's veritably important to prognosticate it in early age which has been grueling task among experimenters because the symptoms of complaint come into actuality in either middle or late middle age.So, this thesis focuses on the speech articulation difficulty symptoms of PD affected people and formulates the model using colorful machine literacy ways similar as adaptive boosting, bagging, neural networks, support vector machine, decision tree, arbitrary timber and direct retrogression.Performance of these classifiers is estimated using colorful criteria i.e., accuracy, receiver operating characteristic wind (ROC), perceptivity, perfection, particularity.At last, XGboost is used to find the most important features among all the point to prognosticate the Parkinson's complaint.