Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network

Figure 1

Experimental paradigm. (a) The position of EEG channels in 10/20 system. The EEG were collected from F3, Fz, F4, C3, Cz, C4, P3, Pz, P4, O1, and O2 positions as indicated by red circle. (b) Experimental setting schematics. Subjects were sat on a chair and were asked to mentally count the occurrence of target icon. The ERP speller system for this paper was implemented with RSVP. The icon appeared on the center of the monitor. (c) Schematics of CNN architecture. The architecture consisted of 2 convolutional layers, 2 max-pool layers, and 2 fully connected layers. The number on top of each layer indicates size of feature map.

(a)

(b)

(c)