Skip to main content

Table 5 Classification accuracy using original combined EEG feature set against the optimal combined feature subset

From: Automatic seizure detection based on the combination of newborn multi-channel EEG and HRV information

Algorithm EEG (linear classifier) HRV (1-NN classifier) Feature fusion (1-NN classifier) Classifier fusion: linear classifier & 1-NN classifier
SEN SPE SEN SPE SEN SPE SEN SPE
Proposed classifiers + optimal feature sets 80.90 86.50 85.70 84.60 95.20 88.60 95.20 94.30
Proposed classifiers + full feature sets 76.19 64.70 56.90 70.90 46.90 80.90 92.30 61.50