Statistical Granular Framework Towards Dealing Inconsistent Scenarios for Parkinson's Disease Classification Big Data.

TLDR: A novel statistical granular framework that deals with inconsistent instances, knowledge discovery, and further performs classification-based disease prediction is presented and the experimental results and comparative analysis prove the novelty and optimality of the proposed prototype.

Abstract: While the medicinal and healthcare services sector is being changed by the competence to record gigantic measures of data about individual patients, the tremendous volume of information being gathered is outlandish for people to dissect/analyze. Over the past years, numerous techniques have been proposed so as to manage inconsistent data frameworks. Statistical applied ML facilitates an approach to consequently discover examples and reasoning about information. How one can transform raw data into valuable information that can empower healthcare professionals to make inventive automated clinical choices. The prior forecast and the location of disease cells can be profitable in curing the ailment in medical/healthcare appliances. This paper presents a novel statistical granular framework that deals with inconsistent instances, knowledge discovery, and further performs classification-based disease prediction. The experimental simulation is carried out on Parkinson’s disease classification dataset. The experimental results and comparative analysis with some significant existing approaches prove the novelty and optimality of our proposed prototype.