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

Table 4

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	90.3692	57	90.9779
Fp2	90.7681	57	91.9478
F3	95.0380	57	95.6088
F4	91.3297	57	91.3627
C3	93.3561	57	93.3813
C4	93.6448	57	93.8244
P3	88.7797	57	89.0716
P4	90.1133	57	89.3159
O1	86.5848	57	87.8883
O2	90.8300	57	92.5787
F7	93.7438	57	94.3815
F8	94.4563	57	94.8470
T3	93.9221	57	94.3731
T4	93.8322	57	94.1035
T5	93.5670	57	93.1092
T6	94.1287	57	95.3485
FZ	88.9061	57	88.6571
CZ	88.6708	57	89.2548
PZ	91.2450	57	91.8549
E	91.8499	57	93.2420
PG1	82.7552	57	83.0715
PG2	86.7638	57	87.3141
A1	90.7149	57	91.0081
A2	87.3506	57	87.7646
T1	84.1250	57	85.0581
T2	89.7853	57	90.4835
X1	90.9339	57	94.5756
X2	92.9365	57	93.3816
X3	86.3529	57	85.7929
X4	86.2634	57	85.8934
X5	69.7540	57	71.9493
X6	81.2648	57	81.9323
X7	82.0801	57	81.3344