Neonatal seizure detection using blind distributed detection with correlated decisions

Seizure is the result of excessive electrical discharges of neurons, which usually develops synchronously and happens suddenly in the central nervous system. Clinically, it is difficult for physician to identify neonatal seizures visually, while EEG seizures can be recognized by the trained experts. By extending our previous results on multichannel information fusion, we propose an automated distributed detection system consisting of the existing detectors and a fusion centre to detect the seizure activities in the newborn EEG assuming that the decisions of local detectors are correlated. The advantage of this proposed technique is that it accounts for correlated decisions of the local detectors. It has been shown that correlation between local detectors can lead to severe performance degradation if not modelled properly. Therefore our proposed technique can potentially improve the performance of existing single and multichannel neonatal seizure detection algorithms.