Acquiring physiological data for automated educational feedback in virtual learning environments

Abstract

The authors present, on the basis of their own experiments and a large variety of recent studies, dealing with neurology, psychiatry, psychology, cognitive brain activi- ties, etc., the great potential of data, obtained from physiological measurement, for immediate and individualized reaction to the learning process of the learning subject in virtual learning environments. They emphasized simple, non-invasive methods, easily available, for eyes tracking, blink rate and blink speed measurements electro- dermal activities (e.g., galvanic skin response) measurements, and heart/respiration rate for their potential to reflect decreasing attention, increasing visual or cognitive information load, task difficulty, tension, arousal, stress and fatigue of the learning subject. The present paper highlights the advantages and constraints of different data acquisition approaches and methods (including technical and physiological), as well as constraints, caused by the hardware and sof{hook} ware limits, by the necessity of individual setup (of{hook}ten continuous), by the problems with real time data processing, including wrong data recognition and elimination, etc. Analyzing the data of GSR, EEG and eye tracking studies (with the sample size of 6, later 8) employing a wide range of cognitive tasks, the authors recommend fast signal processing methods, e.g., real time fast Fourier transformation, which, till now, have been rarely used for physiological data mining and processing in virtual learning environments.