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

BMC Bioinformatics

Table 2 Analysis on classifiers using arousal case

Metrics	Tri classifier + SSU-BES	SVM [2]	TQWT [9]	LSTM	DBN	CNN	RNN
Sensitivity	0.93913	0.74576	0.5113	0.84463	0.82392	0.98305	0.83333
FDR	0.062229	0.29223	0.26423	0.17403	0.10469	0.30952	0.31395
Precision	0.93777	0.70777	0.73577	0.82597	0.89531	0.69048	0.68605
FPR	0.072881	0.38112	0.22727	0.22028	0.11417	0.54545	0.47203
F1-Score	0.93845	0.72627	0.60333	0.8352	0.85813	0.81119	0.75255
MCC	0.86636	0.36766	0.29029	0.62624	0.7072	0.53183	0.38257
FNR	0.06087	0.25424	0.4887	0.15537	0.17608	0.016949	0.16667
Specificity	0.92712	0.61888	0.77273	0.77972	0.88583	0.45455	0.52797
NPV	0.92712	0.61888	0.77273	0.77972	0.88583	0.45455	0.52797
Accuracy	0.93359	0.68906	0.62813	0.81563	0.85225	0.74687	0.69688
FOR	0.072881	0.38112	0.22727	0.22028	0.11417	0.54545	0.47203

ISSN: 1471-2105