Role of attribute selection on tuning the learning performance of Parkinson’s data using various intelligent classifiers

Abstract

Dr James Parkinson first defined the Parkinson's Disease (PD) as "shaking palsy" in 1817. PD is one of the most common neurological syndromes of the central nervous system. It is a serious disease targeting aged persons above 60 years of age. PD is identified as a brain disorder [1] that causes the nerve cells to be lost or impaired. These impaired or lost nerve cells will stop the dopamine fluid production in the area of Substantia Nigra. Dopamine is an essential chemical fluid in the brain, which makes nerve cells passes the message to other nerve cells. Due to the lack of dopamine, information has to pass to another nerve cell to be stopped.

Optimal feature selection for cricket talent identification

“…The feature selection is a crucial step in any predictive model including the machine learning models. It helps us to select a relevant and most important subset of features from the feature space and remove (or lessen the contributed impact of) irrelevant and redundant features, maintaining the accuracy of the model [11,12]. The feature selection techniques are also being utilized to rank and weight the features of our dataset.…”