Classification Of Brainwave Using Data Mining In Producing An Emotional Model

In this paper, classification of brainwave using real world data from Parkinson’s patients is presented. Emotional model is produced from the classification of brainwave. Electroencephalograph (EEG) signal is recorded on eleven Parkinson’s patients. This paper aim to find the “best” classification for the emotional model in brainwave patterns for the Parkinson’s disease. The work performed based on the two method phases which are using the raw data and pre-processing data. In each of the method, we performed for steps in the sum of the hertz and divided by total hertz. In the pre-processing data we are using statistic mean and standard deviation. We used WEKA Application for the classification with 11 fold validation. As a results, implecart from the classification tree performed the “best” classification for the emotional model for Parkinson Patients. The Simplecart classification result is 84.42% accuracy.