Title : Brain-Machine teaming: Recent advances for neural language decoding from EEG Signals
Abstract:
Brain-machine teaming is a collaborative interfacing system between the human brain and external machines. It is a bidirectional communication concept based on the brain-machine interface (BMI). Especially, electroencephalogram (EEG)-based BMI has been utilized to help patients regain motor function and has recently been validated for its use in healthy people because of its ability to directly decipher human intentions. In particular, neurolinguistic research using EEGs has been investigated as an intuitive and naturalistic communication tool between humans and machines. In this study, we have focused on the EEG signals with respect to speech imagery tasks, and the proposed deep neurolinguistic learning architecture could be decoded neural languages. Five subjects participated in the experiment and we evaluated whether BMI-based cooperative tasks between multiple users could be accomplished using a variety of neural languages. We successfully demonstrated brain-machine teaming that allows a variety of scenarios, such as essential activity (e.g., drinking juice by the user himself or herself, or providing juice to the partner), collaborative play (e.g., drinking juice with the partner’s help and delivering a phone with a box to the partner), and emotional interaction (e.g., expressing the user’s emotions to the partner). Consequently, a novel BMI frontier can be presented from these outcomes that could extend the boundaries of the bidirectional interaction between the brain and machine team playing.
Audience Take Away
- How to decode the EEG signals using machine and deep learning techniques in real-time
- How to detect user speech intention (i.e., neural language) as sentence-level
- How to collaborative play between multiple users with neuroprosthetic arm
- What are the frontiers of the brain-machine interfacing system
