Combining newborn EEG and HRV information for automatic seizure detection

We propose a new seizure detection framework based on combination of information extracted from newborn multi-channel electroencephalogram (EEG) and heart rate variability (HRV). Two approaches are investigated for the combination of EEG and HRV, namely; feature fusion and classifier/decision fusion. The feature fusion was performed by concatenating the features vectors extracted from the EEG and the HRV signals while the classifier fusion was accomplished by fusing the independent decisions from individual classifiers of EEG and HRV. Both proposed schemes consist of a sequence of processing steps, namely; preprocessing, feature extraction, feature selection and finally the combination. We have shown that both proposed approaches lead to improved performance of newborn seizure detection compared to either EEG or HRV based seizure detectors.