Association Mining of the Brain Data: An EEG Study

Abstract

Many neuroscience researchers have explored how various parts of the brain are connected. No one has performed association mining using the brain data. In this study, we used SAS® Enterprise MinerTM 7.1 for association mining of the brain data collected by a 14-channel EEG device. An application of the association mining technique is presented in this novel context of brain activities and by linking our results to theories of cognitive neuroscience. The brain waves are collected while a user processes the information about Facebook, the most well known social networking site. The data is cleaned using Independent Component Analysis via an open source MATLAB package. Next, by applying the LORETA algorithm, activations at a fraction of a second are recorded. The data is codified into transactions to perform association mining. Results showing how various parts of brain that get excited while processing the information are reported. This study provides preliminary insights into how brain wave data may be analyzed by commonly available data mining techniques to enhance a researcher’s understanding of brain activation patterns.