الفهرس | Only 14 pages are availabe for public view |
Abstract Electroencephalography (EEG) is an electrophysiological monitoring method to record the electrical activity of the human brain. EEG signals can be acquired from human brain in order to classify the activities of the person. One of the most important applications of the EEG signals is the seizure detection and prediction. EEG signals by nature are multi-channel. Not all channels are effective in EEG seizure prediction in the proposed approach. So, a channel selection technique is used to reduce complexity. This thesis is concerned with statistical channel selection for seizure prediction. The basic idea of the channel selection and seizure prediction strategy is to segment the signal into 10-second segments from pre-ictal and normal periods. The probability density functions (PDFs) for some signal attributes including signal amplitude, derivative, local mean, local variance, and median, for estimated in both pre-ictal and normal states. |