Using dynamical embedding to isolate seizure components in the ictal EEG

We present a system for isolating seizure components in segments of ictal EEG. Through the implementation of Independent Component Analysis (ICA) we first separate multichannel EEG segments into their underlying components. We then employ the method of dynamical embedding to extract a dynamic complexity measure for each independent component. By observing the change in complexity, coupled with the topographical distribution, of each component we can identify those seizure-related components extracted by the ICA process. We have applied the method to four seizure EEG segments and are able to identify probable seizure components in each case. As a proof of principle study the method indicates that ICA coupled with dynamical embedding may be useful as a tool in pre-processing seizure EEG segments.