Utilization of Data Analytics-Based Approaches for Hassle-Free Prediction Parkinson Disease
Individuals with Parkinson’s disease don’t have a sufficient substance called dopamine since a few nerves in the brain lose their functionality. Individuals with Parkinson’s disease are in deceptive and damaging condition . Diagnosing this disease on the basis of the motor and cognitive shortage is extremely critical. Machine learning approaches are utilized to settle on prescient choices via preparing the machines to learn with the trained information. It assumes a fundamental role in foreseeing Parkinson’s disease in its beginning periods. In this paper, our primary goal is to build up an advanced algorithm to accomplish good classification accuracy utilizing data mining techniques. In this procedure, we distinguish some current algorithms (e.g., Naïve Bayes, decision tree, discriminant, and random forest) and its execution is broken down. Result acquired through these grouping algorithms is moderately prescient. During the time spent in the computation of these algorithms, Naïve Bayes can construct the framework with the high precision rate of 94.11%.
KeywordsParkinson’s disease Naïve Bayes Decision tree Random forest Classification Regression
- 1.Parkinson’s Australia: Parkinson’s—description, incidence and theories of causation. http://www.parkinsons.org.au/information_sheets
- 6.Kalman, Y.M.: HCI markers: a conceptual framework for using human-computer interaction data to detect disease processes. In: The 6th mediterranean conference on information systems (MCIS), Limassol, Cyprus (2011)Google Scholar