Abstract
This paper attempts to perform a comparative analysis of brain
signals dataset using various machine learning classifiers such as
random forest, gradient boosting, support vector machine, extra trees
classifier. The comparative analysis is accomplished based on the
performance parameters such as accuracy, area under the ROC curve (AUC),
specificity, recall, and precision. The key focus of this paper is to
exercise the machine learning practices over an Electroencephalogram
(EEG) signals dataset provided by Rochester Institute of Technology and
to provide meaningful results using the same. EEG signals are usually
captivated to diagnose the problems related to the electrical activities
of the brain as it tracks and records brain wave patterns to produce a
definitive report on seizure activities of the brain. While exercising
machine learning practices, various data preprocessing techniques were
implemented to attain cleansed and organized data to predict better
results and higher accuracy. Section II gives a comprehensive presurvey
of existing work performed so far on the same; furthermore, section III
sheds light on the dataset used for this research.