of its abilities to select a suitable kernel function. We used the Pearson VII function-based universal kernel function. The RF is an ensemble learning technique that utilizes the concept of bagging, constructs a collection of decision trees, and takes the average to predict the output. The RF classifier builds a forest based on uncorrelated trees by using decision tree learning, and it is useful for both regression and classification tasks [57]. The graph theory features extracted from the EEG of both groups were used as input for the classifiers. Classification was performed for eyes-open, eyes-closed, and WM tasks. A normalization technique was also used to improve the performance of the classifiers. Classification was performed using WEKA software (Version 3.8.4, Waikato University, New Zealand).
