Arslan, Mustafa TuranEraldemir, Server GökselYıldırım, Esen2025-01-212025-01-2120171308-5514https://dergipark.org.tr/tr/download/article-file/395675https://dergipark.org.tr/tr/pub/umagd/issue/33339/348871https://doi.org/10.29137/umagd.348871https://hdl.handle.net/20.500.12587/20375Inthis study, the electrical activities in the brain were classified duringmental mathematical tasks and silent text reading. EEG recordings are collectedfrom 18 healthy male university/college students, ages ranging from 18 to 25.During the study, a total of 60 slides including verbal text reading andarithmetical operations were presented to the subjects. EEG signals werecollected from 26 channels in the course of slide show. Features were extractedby employing Hilbert Huang Transform (HHT). Then, subject-dependent andsubject-independent classifications were performed using k-Nearest Neighbor (k-NN)algorithm with parameters k=1, 3, 5 and 10. Subject-dependent classificationsresulted in accuracy rates between 95.8% and 99%, whereas the accuracy rateswere between 92.2% and 97% for subject independent classification. The resultsshow that EEG data recorded during mathematical and silent reading tasks can beclassified with high accuracy results for both subject-dependent andsubject-independent analysis.eninfo:eu-repo/semantics/openAccessEEG classificationHilbert Huang Transformk-Nearest NeighborArticle93-18619510.29137/umagd.348871348871