Wheelchair movement signal classification from EEG for motor-impaired individuals using novel deep learning architecture

Key Points

• This research aims to develop an EEG-based system for controlling powered wheelchairs using deep learning techniques.
• Utilized a novel LSTM-CNN architecture with skip connections
• Collected EEG data from motor-impaired individuals during movement tasks
• Analyzed the effectiveness of the deep learning model in classifying EEG signals
• Achieved high accuracy in classifying EEG signals for wheelchair control
• Demonstrated that the model enhances safety and independence for users
• Indicated potential for future integration into EEG-responsive wheelchair systems