Analyzing elementary cognitive tasks with Bloom's taxonomy using low cost commercial EEG device

摘要

Cognitive load primarily depends on how an individual perceives, assimilates and responds to an external stimulus. We intend to create Electroencephalogram (EEG) models for the cognitive skills defined in the Bloom's taxonomy using low cost, commercial EEG devices. This could be applied in educational psychology to provide individual assistance according to one's learning style and abilities. The major challenge in using low resolution EEG device lies in signal analysis with reduced number of channels. In this paper, we present the signature of EEG signals for such low cost devices using three basic tasks namely, number matching; finding characters in text; finding hidden patterns and figures. These tasks map with understand, remember and analyze sub categories of Bloom's taxonomy. Different brain regions are activated while performing the above tasks. However, the EEG signals observed on the scalp are the manifestation of the combined effects of various brain regions. The cleaned EEG signals are analyzed using unsupervised clustering of features obtained from different frequency bands. A study is performed on 10 subjects using 14 lead Emotiv neuroheadset, so that one can get further insights on how an individual perceives certain cognitive tasks.