Routine electroencephalogram (EEG) is an important test in aiding the diagnosis of patients with suspected epilepsy. These recordings typically last 20-40 minutes, during which signs of abnormal activity (spikes, sharp waves) are looked for in the EEG trace. It is essential that events of short duration are detected during the routine EEG test. The work presented in this paper examines the effect of changing a range of input values to the detection system on its ability to distinguish between normal and abnormal EEG activity. It is shown that the length of analysis window in the range of 0.5s to 1s are well suited to the task. Additionally, it is reported that patient specific systems should be used where possible due to their better performance.
The EEG signal is very often contaminated by electrical activity external to the brain. These artefacts make the accurate detection of epileptiform activity more difficult. A scheme developed to improve the detection of these artefacts (and hence epileptiform event detection) is introduced. A structure of parallel Support Vector Machine classifiers is assembled, one classifier tuned to perform the identification of epileptiform activity, the remainder trained for the detection of ocular and movement-related artefacts. This strategy enables an absolute reduction in false detection rate of 21.6% with the constraint of ensuring all epileptic events are recognized. Such a scheme is desirable given that sections of data which are heavily contaminated with artefact need not be excluded from analysis.
Ambulatory EEG requires signal processing algorithms which are efficient in terms of how much power they use in their computation, while at the same time providing accurate decision-making capabilities. Two methods of achieving this are to downsample the EEG and to perform bitwidth reduction on the data. The effect of performing both of these techniques to varying extents is investigated in this paper. Frequency, time and entropy based features are extracted from the data and used to train a Support Vector Machine (SVM) classification system. The effect of changing the overlap between successive epochs is also investigated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.