ICA-Based Imagined Conceptual Words Classification on EEG Signals

Independent component analysis (ICA) has been used for detecting and removing the eye artifactsconventionally. However, in this research, it was used not only for detecting the eye artifacts, but also fordetecting the brain-produced signals of two conceptual danger and information category words. In thiscross-sectional research, electroencephalography (EEG) signals were recorded using Micromed and 19-channel helmet devices in unipolar mode, wherein Cz electrode was selected as the reference electrode.In the first part of this research, the statistical community test case included four men and four women,who were 25–30 years old. In the designed task, three groups of traffic signs were considered, in whichtwo groups referred to the concept of danger, and the third one referred to the concept of information. Inthe second part, the three volunteers, two men and one woman, who had the best results, were chosenfrom among eight participants. In the second designed task, direction arrows (up, down, left, and right)were used. For the 2/8 volunteers in the rest times, very high-power alpha waves were observed from theback of the head; however, in the thinking times, they were different. According to this result, alphawaves for changing the task from thinking to rest condition took at least 3 s for the two volunteers, and itwas at most 5 s until they went to the absolute rest condition. For the 7/8 volunteers, the danger andinformation signals were well classified; these differences for the 5/8 volunteers were observed in theright hemisphere, and, for the other three volunteers, the differences were observed in the lefthemisphere. For the second task, simulations showed that the best classification accuracies resultedwhen the time window was 2.5 s. In addition, it also showed that the features of the autoregressive (AR)-15 model coefficients were the best choices for extracting the features. For all the states of neuralnetwork except hardlim discriminator function, the classification accuracies were almost the same andnot very different. Linear discriminant analysis (LDA) in comparison with the neural network yieldedhigher classification accuracies. ICA is a suitable algorithm for recognizing of the word’s concept and itsplace in the brain. Achieved results from this experiment were the same compared with the results fromother methods such as functional magnetic resonance imaging and methods based on the brain signals(EEG) in the vowel imagination and covert speech. Herein, the highest classification accuracy wasobtained by extracting the target signal from the output of the ICA and extracting the features ofcoefficients AR model with time interval of 2.5 s. Finally, LDA resulted in the highest classificationaccuracy more than 60%.