EEG Visual and Non- Visual Learner Classification Using LSTM Recurrent Neural Networks

The purpose of this study is to distinguish the visual learners from non-visual learners while learning, having no background knowledge of the contents. The learners are distinguished analysing their brain patterns. EEG data were recorded during learning and memory tasks using 128 channels machine from a sample of thirty -four healthy university students. The students were shown the animated learning content in video format for eight minutes. The brain waves were measured during learning task. The study characterizes and distinguishes between the visual learners and non-visual learners considering the extracted brain patterns. The wavelet features are computed for the recorded EEG and are filtered into alpha and beta sub bands. These features are then given as an input to the Long-Short Term Memory (LSTM) Recurrent neural network (RNN). Feature classification using LSTM Recurrent neural network has attained training accuracy of 89% and 85% for beta and alpha bands for Learning session 1(Learning 1), 86% and 87% for Learning session 2(Learning 2).