Electroencephalography (EEG) based Brain-Computer Interface (BCI) systems are a new development in the ﬁeld of applied neurophysiology. This newapproach has been made possible thanks to progress in EEG analysis and in information technology which has led to a better understanding of psychophysicalaspects of the EEG signals. BCI systems enable information ﬂow from the braindirectly to the outside world. For widespread use of brain signals for such objectives, effective signal analysis and pattern recognition techniques are needed.
In this thesis, we have developed a new technique based on hidden Markovmodels, and have demonstrated the effectiveness of our algorithms both on astandard dataset and on the data that we have collected in our laboratory.
We have used HMMs with AR features combined with PCA to classify twoand four class single trial EEG data recorded during imagination of motor actionsutopic at times, still amazingly fun conversations with Serhan Co¸sar, Batu Akan,Erkin Tekeli Ozge Batu, Harun Karabalkan, Saygın Topkaya, Berkay Top¸cu andEmrecan Cokelek.
I should also thank Gozde S¸enocak and Pedro Garcia da Silva for reading themanuscript and Esen Sokullu for her endless support during my whole academiclife.
I am also thankful to Turkish Scientiﬁc and Technological Research Council(TUBIITAK) and Turkish Academy of Sciences (TUBA) for their support duringmy graduate education.
Last but not least, I want to thank Prof. Dr. Emery N. Brown and Dr.Sydney Cash for giving me the opportunity of collaborating with their researchgroups in Massachusetts General Hospital, Charlestown, MA, US and Prof. Dr.Antonio Carlos Roque for accepting me to Latin American School on Computational Neuroscience (LASCON) in Ribeirao Preto, SP, Brazil.