DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning

TL;DR

This paper introduces DeepBrain, an end-to-end EEG-based brain-robot interaction system using personalized attention-enhanced stacked LSTM, enabling low-cost, accurate, and real-time control for individuals with movement difficulties.

Contribution

It develops a novel personalized attention-based stacked LSTM model for EEG classification, improving accuracy and efficiency in low-cost brain-computer interface applications.

Findings

Achieves satisfactory accuracy and speed in real-world tests.

Enables fine control of household robots for elderly or disabled users.

Demonstrates low-cost EEG device effectiveness.

Abstract

The "mind-controlling" capability has always been in mankind's fantasy. With the recent advancements of electroencephalograph (EEG) techniques, brain-computer interface (BCI) researchers have explored various solutions to allow individuals to perform various tasks using their minds. However, the commercial off-the-shelf devices to run accurate EGG signal collection are usually expensive and the comparably cheaper devices can only present coarse results, which prevents the practical application of these devices in domestic services. To tackle this challenge, we propose and develop an end-to-end solution that enables fine brain-robot interaction (BRI) through embedded learning of coarse EEG signals from the low-cost devices, namely DeepBrain, so that people having difficulty to move, such as the elderly, can mildly command and control a robot to perform some basic household tasks. Our contributions are two folds: 1) We present a stacked long short term memory (Stacked LSTM) structure with specific pre-processing techniques to handle the time-dependency of EEG signals and their classification. 2) We propose personalized design to capture multiple features and achieve accurate recognition of individual EEG signals by enhancing the signal interpretation of Stacked LSTM with attention mechanism. Our real-world experiments demonstrate that the proposed end-to-end solution with low cost can achieve satisfactory run-time speed, accuracy and energy-efficiency.