EEG-based fuzzy cognitive load classification during logical analysis of program segments

The paper aims at designing a novel scheme for cognitive load classification of subjects engaged in program analysis. The logic of propositions has been employed here to construct program segments to be used for cognitive load analysis and classification. Electroencephalogram signals acquired from the subjects during program analysis are first fuzzified and the resultant fuzzy membership functions are then submitted to the input of a fuzzy rule-based classifier to determine the class of the cognitive load of the subjects. Experimental results envisage that the proposed classifier has a good classification accuracy of 86.2%. Performance analysis of the fuzzy classifier further reveals that it outperforms two most widely used classifiers: Support Vector Machine and Naive Bayes classifier.

[1]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[2]  W. Klimesch.  EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis , 1999, Brain Research Reviews.

[3]  Xiaoming Wu,et al.  Feature extraction and classification of EEG for imagery movement based on mu/beta rhythms , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[4]  Amit Konar,et al.  Interval Type-2 Fuzzy Model for Emotion Recognition from Facial Expression , 2012, PerMIn.

[5]  B. Kotchoubey,et al.  Event-related potentials, cognition, and behavior: A biological approach , 2006, Neuroscience & Biobehavioral Reviews.

[6]  Graham Cooper,et al.  Research into Cognitive Load Theory and Instructional Design at UNSW , 2008 .

[7]  B. Kosko.  Fuzzy Thinking: The New Science of Fuzzy Logic , 1993 .

[8]  Nicole Krämer,et al.  Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces , 2009, Neural Networks.

[9]  Thierry Pun,et al.  A channel selection method for EEG classification in emotion assessment based on synchronization likelihood , 2007, 2007 15th European Signal Processing Conference.

[10]  J. Beatty.  Task-evoked pupillary responses, processing load, and the structure of processing resources. , 1982 .

[11]  Matthias Scheutz,et al.  Brainput: enhancing interactive systems with streaming fnirs brain input , 2012, CHI.

[12]  Kathleen Baynes,et al.  The measurement of everyday cognition (ECog): scale development and psychometric properties. , 2008, Neuropsychology.

[13]  Sander L. Koole,et al.  Tuning down the emotional brain: An fMRI study of the effects of cognitive load on the processing of affective images , 2009, NeuroImage.

[14]  P. Chandler,et al.  Cognitive Load While Learning to Use a Computer Program , 1996 .

[15]  R. Engle.  Working Memory Capacity as Executive Attention , 2002 .

[16]  J. Jonides,et al.  Dissociating verbal and spatial working memory using PET. , 1996, Cerebral cortex.

[17]  Misha Pavel,et al.  Estimating cognitive state using EEG signals , 2005, 2005 13th European Signal Processing Conference.

[18]  Pavlo D. Antonenko,et al.  Using Electroencephalography to Measure Cognitive Load , 2010 .

[19]  S. Sigurdsson,et al.  Reliability of quantitative EEG features , 2007, Clinical Neurophysiology.

[20]  Amit Konar,et al.  Artificial Intelligence and Soft Computing: Behavioral and Cognitive Modeling of the Human Brain , 1999 .

[21]  B. Goldwater.  Psychological significance of pupillary movements. , 1972, Psychological bulletin.

[22]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[23]  Jerry M. Mendel,et al.  Type-2 fuzzy sets made simple , 2002, IEEE Trans. Fuzzy Syst..