Brainwave Authentication And Brain-Computer Interface Using In-Ear EEG

Brainwave Authentication And Brain-Computer Interface Using In-Ear EEG

Max Curran, Nick Merrill, Jong-Kai Yang, John Chuang

Brain-computer interfaces (BCIs) enable the control of a computer without muscular action. BCIs based on electroencephalography (EEG) have improved dramatically over the past five years, but their head-worn form factor and awkward visibility have challenged their wider adoption.

In these projects, we used a home-rigged, single-electrode EEG placed inside the ear canal (above) to investigate how signals from the ear could be used for “mental gestures,” and for passthought-style authentication (see our past work on passthoughts). Eventually, this research could provide hands-free interaction, authentication, and a seamless and comfortable user experience, all in the form-factor of a typical earbud.

More recently we created custom-fit earpieces with embedded electrodes and tested this paradigm, finding significant improvements in authentication accuracy compared to the single-electrode hardware. By capturing inherence and knowledge authentication factors via passthoughts, and the potential for a possession factor built in to a custom earpiece, we demonstrate a proof of concept for a highly secure and highly usable form of authentication.

PUBLICATIONS

Max T. Curran, Jong-Kai Yang, Nick Merrill, John Chuang. 2016. Passthoughts Authentication with Low Cost EarEEG IEEE Engineering in Medicine and Biology Society (EMBC’16)[PDF]

Nick Merrill, Max T. Curran, Jong-Kai Yang, John Chuang. 2016. Classifying Mental Gestures with In-Ear EEG. 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN ’16)[PDF]

Max T. Curran, Nick Merrill, Swapan Gandhi, John Chuang. 2018. Exploring the Feasibility and Performance of One-step Three-factor Authentication with Ear-EEG. In Proceedings of the 5th International Conference on Physiological Computing Systems (PhyCS ’18). [PDF]

PRESS

Kron4: New brainwave reading tech from Cal Berkeley released