Review article: Human scalp EEG processing: Various soft computing approaches
Applied Soft Computing
| Hi-index | 0.00 |
The effects of chronic toxic occupational factors and functionaldisorders of the central nervous system (CNS) in chemical industrywere studied. These factors cause various stages of chronicchemical stress on the human CNS together with changes of thevigilance levels. On the basis of QEEG data analysis andpsychometric tests we identified three stages of occupationalchemical stress syndromes according to the CNS vigilance level(ordered from light to severe): hypersthenic syndrome, hyposthenicsyndrome, and organic psychosyndrome. Each syndrome ischaracterized by specific changes in the QEEG data. Aperceptron-based neural network was developed for theclassification of the QEEG data to one of the above-mentionedsyndrome classes. The data of 77 patients and 10 healthy subjectswere selected to test the algorithm. Different combinations of theQEEG data as input features to the classifier were chosen. The mostreliable classification was obtained when QEEG data measured duringthe visual stimulation of the CNS were used. However, sometimes thealgorithm was unable to solve the classification problem, or ittook a very long time to train the perceptron. In part,difficulties arose from using a perceptron-based algorithm, whichcan classify only linearly separable data.