Performance of a Self-Paced Brain Computer Interface on Data Contaminated with Eye-Movement Artifacts and on Data Recorded in a Subsequent Session

Abstract

The performance of a specific self-paced BCI (SBCI) is investigated using two different datasets to determine its suitability for using online: (1) data contaminated with large-amplitude eye movements, and (2) data recorded in a session subsequent to the original sessions used to design the system. No part of the data was rejected in the subsequent session. Therefore, this dataset can be regarded as a “pseudo-online” test set. The SBCI under investigation uses features extracted from three specific neurological phenomena. Each of these neurological phenomena belongs to a different frequency band. Since many prominent artifacts are either of mostly low-frequency (e.g., eye movements) or mostly high-frequency nature (e.g., muscle movements), it is expected that the system shows a fairly robust performance over artifact-contaminated data. Analysis of the data of four participants using epochs contaminated with large-amplitude eye-movement artifacts shows that the system's performance deteriorates only slightly. Furthermore, the system's performance during the session subsequent to the original sessions remained largely the same as in the original sessions for three out of the four participants. This moderate drop in performance can be considered tolerable, since allowing artifact-contaminated data to be used as inputs makes the system available for users at ALL times.

A Long-Term BCI Study With ECoG Recordings in Freely Moving Rats

“…The present study showed that ECoG recordings provide high quality data for analysis with specific algorithm software. This is one of the major findings of this study compared to previous studies presenting different BCI systems based on recordings of ECoGs over several days but not a year, as in the study by Blakely that related a control of 7 days of implantation or EEG signals with acute experiments each day, but not long‐term .…”

“…Experimental Set Up The present study showed that ECoG recordings provide high quality data for analysis with specific algorithm software. This is one of the major findings of this study compared to previous studies presenting different BCI systems based on recordings of ECoGs over several days but not a year, as in the study by Blakely (32) that related a control of 7 days of implantation or EEG signals with acute experiments each day, but not long-term (33)(34)(35)(36)(37). This first step on rodents gave us a lot of information for future BCI experiments: Brain ECoGs can be used up to one year, they are stable, usable for data processing during one year, the performances of this BCI system in offline analysis were high (67.82% of True Positive Rate with a small 2.17 false positive/minute) and our results show encouraging data for the online use of this BCI (control of the effector by mental task).…”

Automatic artefact removal in a self-paced hybrid brain- computer interface system

“…Although some studies have clearly shown that artefacts affect the performance of pure self-paced BCI systems [ 10 , 11 ], little attention has been paid to handle artefacts so far.…”

Making brain-computer interfaces better : improving usability through post-processing

“…For the categorization, these papers have been combined and are represented by just one of the articles. Fatourechi et al [75,76] and Fatourechi, Ward, and Birch [53] all discuss the p o s t -p r o c e s s i n g i n b c i l i t e r a t u When systems use multiple methods, they are repeated for each.…”

“…Cooldown Fatourechi, Ward, and Birch [53] decreased their false positive rates with an average of 6% by adding a short cooldown period of only 1 decision sample, while reducing the true positive rate by just 1%. Verschore et al [63] decreased the necessary number of repetitions from 12 to only 2.69 on average.…”