Automatically Identified EEG Signals of Movement Intention Based on CNN Network (End-To-End)

Movement-based brain–computer Interfaces (BCI) rely significantly on the automatic identification of movement intent. They also allow patients with motor disorders to communicate external devices. The extraction and selection discriminative characteristics, which often boosts computer complexity, is one issues automatically discovered intentions. This research introduces a novel method for categorizing two-class three-class movement-intention situations utilizing EEG data. In suggested technique, raw input applied directly convolutional neural network (CNN) without feature or selection. According previous research, this complex approach. Ten layers are included in design, followed by two fully connected layers. approach could be employed BCI applications due its high accuracy.