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

BMC Bioinformatics

Table 1 Analysis on classifiers using valence case

Metrics	Tri classifier + SSU-BES	SVM [2]	TQWT [9]	LSTM	DBN	CNN	RNN
FDR	0.050877	0.34122	0.28333	0.12371	0.14041	0.094488	0.13433
Sensitivity	0.88399	0.63107	0.41748	0.82524	0.8123	0.74434	0.75081
NPV	0.95659	0.69486	0.84592	0.89124	0.87613	0.92749	0.89124
Specificity	0.95659	0.69486	0.84592	0.89124	0.87613	0.92749	0.89124
FPR	0.043413	0.30514	0.15408	0.10876	0.12387	0.072508	0.10876
F1-Score	0.9154	0.64463	0.52761	0.85	0.83527	0.81705	0.80416
FOR	0.043413	0.30514	0.15408	0.10876	0.12387	0.072508	0.10876
Accuracy	0.92188	0.66406	0.63906	0.85938	0.84531	0.83906	0.82344
MCC	0.84484	0.32666	0.29274	0.71902	0.69067	0.68619	0.65031
Precision	0.94912	0.65878	0.71667	0.87629	0.85959	0.90551	0.86567
FNR	0.11601	0.36893	0.58252	0.17476	0.1877	0.25566	0.24919

ISSN: 1471-2105