Studying the Independent Component Analysis (ICA) Algorithm for Detection and Separation of Two Conceptual Categories of the Words Danger and Information by Using Traffic Signs

Abstract Background: In various researches, ICA is used for detecting and removing eye artifacts; but here, for innovation, ICA algorithm is used not only for detecting eye artifacts but also for detecting brain signals of two conceptual categories of the words Danger and Information. Materials and Methods: In this descriptive- analytical study, recording is done by using a Micromed device and a 19-channel helmet in unipolar mode that the Cz electrode is selected as reference electrode. The statistical community included four men and four women in the age range of 25-30. In the designed task three groups of traffic signs are considered in which two groups refered to the concept of danger and the other one refered to the concept of information. Results: For two of the eight volunteers, alpha waves were observed with a very high power from back of the head in the test time, but in thinking time it was different. According to this alpha waves, in changing the task from thinking to rest, it takes for two volunteers at least 3 and at most 5 seconds till they go to the absolute rest. For seven of the eight volunteers, danger and information signals well separated; that these differences for five of the eight volunteers observed in the right hemisphere and for the other three volunteers in the left hemisphere. Conclusion: ICA algorithm as one of Blind Source Seperation(BSS) algorithms is suitable for recognizing the word’s concept and its place in the brain. Achieved results from this experiment are the same as the results from other methods like fMRI and methods based on electroencephalograph (EEG) in vowel imagination and covert speech.