EEG spike detection using backpropagation networks

Summary form only given, as follows. The design of a system to analyze electroencephalogram (EEG) signals for the detection of epileptiform spikes is described. The ultimate goal is real-time multichannel spike detection. Two main areas of development are reviewed. The first is the processing and characterization of the raw EEG data, including issues related to data rates, the number of data channels, and the tradeoffs between the amount of data preprocessing and the complexities of the neural net work required. The second is the selection and implementation of the neural net work architecture, including choices between supervised and unsupervised learning schemes, and among the many available learning algorithms for each network architecture. Interim results involving the analysis of single-channel EEG data are discussed. The relationship of the spike detection project to a similar effort in seizure detection is described.<>