![]() | Only 14 pages are availabe for public view |
Abstract Brain computer Interface (BCI) is a communication channel between brain and computer. It provides communication method between Electroencephalography (EEG) signals that are detected from the scalp using signal acquisition device and an exterior device such as (robot arm, wheelchair…). These applications could help people who are paralyzed, having other movement disorders and having problems in speech to provide them with alternative methods for communication and control. BCIs suffer from many problems including low accuracy, high execution time, false positive detections and low signal to noise ratio (SNR) of EEG signals. The purpose of this thesis is to design an offline brain computer interface system. This system could translate the human arm movements into commands to control simulator robot arm to execute the desired movement. It could also use human mental thoughts to move a cursor on the screen to form words and sentences according to Morse scheme. Channel selection was performed to reduce the size of EEG data. Filters have been used to remove unwanted artifacts. Three different feature extraction methods were used: Wavelet Transform (WT), Fast Fourier Transform. |