FKEE - Official Portal

FACULTY OF ELECTRICAL &
ELECTRONICS ENGINEERING

Abstract:

This research is meant to classify learners based on the combination of Kolb’s learning style information and Electroencephalogram (EEG) dataset. Slow waves and fast waves EEG of a learners (N = 131) were captured using the waverider pro hardware and processed using the accompanied software called waveware to generate the summative EEG as a final dataset. Next, the learners LS were determined using Kolb’s Learning Style Inventory (KLSI) which clustered them into the LS of diverger assimilator, converger and Accommodator respectively. The SPSS 16 Modules of 2-steps cluster analysis is used to analyze the summative EEG dataset of beta and alpha (fast waves); theta and delta (slow waves). As to establish the LS classification on both waves condition. In term of single EEG band, all LS are correctly clustered (100%) in a homogenous group notwithstanding fast wave or slow wave EEG. On the other hand, in combined EEG bands, both waves group had demonstrated a best classification (100%) for LS diverger. Concurrently, best classification (100%) also obtained for LS accommodator but only in EEG Fast wave condition. Based on the overall findings, the fast wave EEG is found to be a better classifier for Kolb’s LS compared to the slow wave EEG. The research findings could be utilized to impart further attention and focus on Beta and Alpha EEG waves in order to infer the learner’s learning preference based on KLSI.