Feasibility and pragmatics of classifying working memory load with an electroencephalograph
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Towards affective learning with an EEG feedback approach
MTDL '09 Proceedings of the first ACM international workshop on Multimedia technologies for distance learning
A real-time EEG-based BCI system for attention recognition in ubiquitous environment
Proceedings of 2011 international workshop on Ubiquitous affective awareness and intelligent interaction
EEG: a way to explore learner's affect in pervasive learning systems
GPC'10 Proceedings of the 5th international conference on Advances in Grid and Pervasive Computing
International Journal of Artificial Intelligence and Soft Computing
Hi-index | 0.00 |
This paper describes analysis of EEG data collectedwhile participants performed a gauge-monitoring taskwhich simulated an industrial process. Participantsperformed the task on two separate occasions, and themean interval between sessions was 13 weeks. Analysisof EEG involved derivation of 5166 separate dependentvariables, and these included measures of inter-electrodecorrelation, spectral power, coherence, cross phase andcross power. A central aim was to identify those EEGmeasures which provided the most reliable prediction oftask demand. In particular, a major question waswhether each participant might have unique aspects oftheir EEG which predicted cognitive load. This stemmedfrom a concern that attention to individual differencesmight provide a means for improving prediction. Resultsindicated that there were idiosyncratic aspects ofphysiological response which were highly predictive oftask load. Furthermore, the predictive power of thesevariables survived across sessions despite the mean 3month interval between them. Analyses also indicated thepresence of EEG predictors which were common to allparticipants. It is concluded that idiosyncratic aspects ofEEG patterns reflect genuine and reproducibleindividual differences. Such differences may prove avaluable tool for improving prediction. Furthermore,exploration of these variables may result in a deeperunderstanding of different types of cognitive style.