A self-paced BCI system with low latency for motor imagery onset detection based on time series prediction paradigm

TL;DR

This paper introduces a low-latency self-paced motor imagery BCI system using an LSTM-based time series prediction approach to detect MI onsets more quickly and accurately.

Contribution

It proposes a novel encoder-decoder LSTM network for predicting EEG signals to reduce detection latency in self-paced MI-BCI systems.

Findings

Improved average F1-score by 26.7% over the competition winner

Achieved MI onset detection with less than one second latency

Validated on BCI competition dataset IVc

Abstract

In a self-paced motor-imagery brain-computer interface (MI-BCI), the onsets of the MI commands presented in a continuous electroencephalogram (EEG) signal are unknown. To detect these onsets, most self-paced approaches apply a window function on the continuous EEG signal and split it into long segments for further analysis. As a result, the system has a high latency. To reduce the system latency, we propose an algorithm based on the time series prediction concept and use the data of the previously received time samples to predict the upcoming time samples. Our predictor is an encoder-decoder (ED) network built with long short-term memory (LSTM) units. The onsets of the MI commands are detected shortly by comparing the incoming signal with the predicted signal. The proposed method is validated on dataset IVc from BCI competition III. The simulation results show that the proposed algorithm improves the average F1-score achieved by the winner of the competition by 26.7% for latencies shorter than one second.