Çiçek, Kerime DilşadBayat, OğuzUçan, Osman NuriDuru, Adil Deniz2021-05-152021-05-152019978-1-7281-2420-9https://hdl.handle.net/20.500.12939/780Medical Technologies Congress (TIPTEKNO) -- OCT 03-05, 2019 -- Izmir, TURKEYDuru, Adil Deniz/0000-0003-3014-9626In the concept of this thesis, single trial event related potential measurements were classified. Classification performances of Decision Trees, logistic regression, random forest, Support Vector Machines and XGBoost methods are evaluated. In this context, EEG was collected during the presentation of two different stimulus. The resulting feature set is given as an input to decision trees, logistic regression, random forest, support vector machines, and xgboost classifiers. Due to the limited test data obtained, synthetic Minority oversampling technique(SMOTE) was applied to the data and classification was performed with the updated dataset. As a result of the study, 91% accuracy was obtained for the training dataset in random forest and XGBoost classification methods. For the test set xgboost_tuned has a 62% accuracy and 71% F1 value. To conclude, superior results were found from other classifiers using the xgboost classification method.trinfo:eu-repo/semantics/closedAccessEEGSMOTEXGBoostConference Object3653682-s2.0-85075593498N/AWOS:000516830900094N/A