Comparative Analysis of Classifiers for Developing an Adaptive Computer-Assisted EEG Analysis System for Diagnosing Epilepsy

Table 6

First column shows the channel label, the second column shows the initial training accuracy, and third one shows the marked correction by a neurologist and the last one shows the final accuracy.

Channel	Accuracy after initial training (%)	Number of epochs marked by the user	Accuracy after retraining (%)
Fp1	89.0861	57	89.7390
Fp2	89.0432	57	90.0443
F3	92.5991	57	92.3307
F4	89.6807	57	90.1430
C3	91.9454	57	90.8942
C4	91.1039	57	90.9973
P3	89.3490	57	90.3629
P4	89.7354	57	89.7726
O1	89.1013	57	90.2593
O2	89.2719	57	91.0779
F7	91.9906	57	92.4641
F8	91.7540	57	91.6937
T3	93.4416	57	93.9856
T4	93.2478	57	92.9901
T5	91.3400	57	92.1312
T6	92.8583	57	92.6363
Fz	88.8938	57	89.7298
Cz	84.0064	57	85.7228
Pz	91.6708	57	92.0561
E	85.2267	57	85.5279
PG1	84.6921	57	85.2892
PG2	85.3189	57	85.3886
A1	91.6580	57	92.0482
A2	90.4476	57	90.6291
T1	84.2211	57	85.0355
T2	87.7382	57	87.7849
X1	94.3820	57	94.7490
X2	94.0092	57	94.1500
X3	86.2930	57	86.6199
X4	84.5908	57	85.6526
X5	77.4855	57	79.1122
X6	88.1346	57	89.2410
X7	80.6365	57	81.5108