SEARCH RESULT

Researchers have been studying to understand and classify biological signals for better diagnose diseases and developing assistive technologies. These technologies are sometimes making it possible to communicate in ALS (Amyotrophic lateral sclerosis) patients, sometimes possible to use our computer, faster and more efficient without using our muscular systems. The steady state visual evoked potential (SSVEP) approach currently provides the high performance and reliable communication for the implementation of these technologies. Performance is usually measured by Information Transfer Rate (ITR) and the most important factor affecting ITR is signal window length. In the presented paper a SSVEP based BCI (Brain Computer Interface) speller application is introduced and system performance is analyzed for different signal window lengths in experiments. The BCI speller has six box which has six letters in each box on the screen. The six letters in the selected box are distributed as one letter each box after the first selection by application. With the second selection, the letter which desired is displayed on the screen. The application contains Latin letters as well as Turkish letters. Experiments are performed on 3 healthy subjects. Subjects try to choose letter by focusing boxes which has flickering different frequencies. The minimum energy combination (MEC) method is applied to EEG segments that are different length in order to detect SSVEPs. The highest ITR value of 77.55 bit/min is obtained for subject 1 with 2 s signal window length. High accuracy and more useful a BCI system observed when system signal window length set 3 s.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

E. ERKAN Mehmet Akbaba