Multiclass Classification of Imagined Speech Vowels and Words of Electroencephalography Signals Using Deep Learning

Table 4

Comparison of the proposed model with the state of the art.

Sl. no.	Authors	Model	Accuracy (%)
1	Saha et al. [13]	CNN + DAE	83.42
2	Cooney et al. [14]	CNN and TL	35.68
3	Panachakel et al. [15]	DNN	71.8
4	Panachakel et al. [21]	TL ResNet50	86.34
5	Li et al. [19]	Dilated CNN	54.31
6	Sarmiento et al. [20]	CNN	85.66
7	Proposed method	TCN + CNN	96.49

In the absence of average classification accuracy in the paper, the overall accuracy was estimated as the mean of all subjects’ accuracy.