Selection of a subset of EEG channels of epileptic patient during seizure using PCA
Tahir Ahmad, Raja Ahmad Fairuz, Fauziah Zakaria, Herman Isa · International Conference on Signal Processing · 2008
One of the major roles of electroencephalography (EEG) is as an aid to diagnose epilepsy. Abnormal patterns such as spikes, sharp waves and, spikes and wave complexes can be seen. Our main interest is to extract information about the dynamics from a few observations of this recorded signal. In this paper, The Principal Component Analysis (PCA) is used in choosing a subset of EEG channels during epileptic seizure. Results from the selection is then compared to the results of clustering on the EEG data obtained from the respective patients. Finally we obtained signature of general epilepsy by superimposing results of the two methods.