Pseudo-online framework for BCI evaluation: a MOABB perspective using various MI and SSVEP datasets.

Abstract

<i>Objective</i>. BCI (Brain-Computer Interfaces) operate in three modes:<i>online</i>,<i>offline</i>, and<i>pseudo-online</i>. In<i>online</i>mode, real-time EEG data is constantly analyzed. In<i>offline</i>mode, the signal is acquired and processed afterwards. The<i>pseudo-online</i>mode processes collected data as if they were received in real-time. The main difference is that the<i>offline</i>mode often analyzes the whole data, while the<i>online</i>and<i>pseudo-online</i>modes only analyze data in short time windows.<i>Offline</i>processing tends to be more accurate, while<i>online</i>analysis is better for therapeutic applications.<i>Pseudo-online</i>implementation approximates<i>online</i>processing without real-time constraints. Many BCI studies being<i>offline</i>introduce biases compared to real-life scenarios, impacting classification algorithm performance.<i>Approach</i>. The objective of this research paper is therefore to extend the current MOABB framework, operating in<i>offline</i>mode, so as to allow a comparison of different algorithms in a<i>pseudo-online</i>setting with the use of a technology based on overlapping sliding windows. To do this will require the introduction of a idle state event in the dataset that takes into account all different possibilities that are not task thinking. To validate the performance of the algorithms we will use the normalized Matthews correlation coefficient and the information transfer rate.<i>Main results</i>. We analyzed the state-of-the-art algorithms of the last 15 years over several motor imagery and steady state visually evoked potential multi-subjects datasets, showing the differences between the two approaches from a statistical point of view.<i>Significance</i>. The ability to analyze the performance of different algorithms in<i>offline</i>and<i>pseudo-online</i>modes will allow the BCI community to obtain more accurate and comprehensive reports regarding the performance of classification algorithms.