Tri-model classifiers for EEG based mental task classification: hybrid optimization assisted framework

BMC Bioinformatics

Table 6 Evaluation of proposed over other features for arousal case

Metrics	Tri classifier + SSU-BES	Proposed + Conventional entropy	Proposed + Conventional DBN	No optimization
NPV	0.92712	0.91541	0.44411	0.83686
Accuracy	0.93359	0.65312	0.6375	0.59375
FPR	0.072881	0.084592	0.55589	0.16314
Sensitivity	0.93913	0.37217	0.84466	0.33333
MCC	0.86636	0.34498	0.31351	0.19765
FNR	0.06087	0.62783	0.15534	0.66667
Specificity	0.92712	0.91541	0.44411	0.83686
FDR	0.062229	0.1958	0.41348	0.34395
F1-Score	0.93845	0.50885	0.69231	0.44206
Precision	0.93777	0.8042	0.58652	0.65605
FOR	0.072881	0.084592	0.55589	0.16314

ISSN: 1471-2105