Fully portable and wireless universal brain-machine interfaces enabled by flexible scalp electronics and deep-learning algorithm

Variation in human brains creates difficulty in implementing electroencephalography (EEG) into universal brain-machine interfaces (BMI). Conventional EEG systems typically suffer from motion artifacts, extensive preparation time, and bulky equipment, while existing EEG classification methods require training on a per-subject or per-session basis. Here, we introduce a fully portable, wireless, flexible scalp electronic system, incorporating a set of dry electrodes and flexible membrane circuit. Time domain analysis using convolutional neural networks allows for an accurate, real-time classification of steady-state visually evoked potentials on the occipital lobe. Simultaneous comparison of EEG signals with two commercial systems captures the improved performance of the flexible electronics with significant reduction of noise and electromagnetic interference. The two-channel scalp electronic system achieves a high information transfer rate (122.1 ± 3.53 bits per minute) with six human subjects, allowing for a wireless, real-time, universal EEG classification for an electronic wheelchair, motorized vehicle, and keyboard-less presentation.