Table 11 Evaluation of Metrics for Different Models using the COGN-26 data set. The best result for each metric is reported in bold.

From: Recurrent and convolutional neural networks in classification of EEG signal for guided imagery and mental workload detection

Model

ACC

Loss

F1

Precision

Recall

Avg. fold time (s)

EEGNet

0.7646

0.5423

0.7538

0.7998

0.7764

60.03

LSTM

0.6833

3.5559

0.7166

0.6824

0.8333

219.89

1D-CNN

0.8094

0.5223

0.7806

0.8970

0.7396

98.68

1D-CNN-LSTM

0.7556

0.8383

0.7445

0.8056

0.7807

113.25

Back to article page