Classifying motor imagery in presence of speech

Abstract

Abstract-In the near future, brain-computer interface (BCI) applications for non-disabled users will require multimodal interaction and tolerance to dynamic environment. However, this conflicts with the highly sensitive recording techniques used for BCIs, such as electroencephalography (EEG). Advanced machine learning and signal processing techniques are required to decorrelate desired brain signals from the rest. This paper proposes a signal processing pipeline and two classification methods suitable for multiclass EEG analysis. The methods were tested in an experiment on separating left/right hand imagery in presence/absence of speech. The analyses showed that the presence of speech during motor imagery did not affect the classification accuracy significantly and regardless of the presence of speech, the proposed methods were able to separate left and right hand imagery with an accuracy of 60%. The best overall accuracy achieved for the 5-class separation of all the tasks was 47% and both proposed methods performed equally well. In addition, the analysis of event-related spectral power changes revealed characteristics related to motor imagery and speech.

Brain computer interfacing: Applications and challenges

“…Analyzing the classification results of motor actions of both paralyzed and non-paralyzed people using EEG and ECoG signals is presented in [105]. Also the presence of speech in the classification of motor imagery has been examined [122] and it has been found that speech existence does not notably affect the accuracy results. Table 1 [123] gives a summary for brain acquisition methods along with their advantages and disadvantages.…”

Brain–computer interfacing under distraction: an evaluation study

“…Ambulatory BCIs, for instance, allow participants to walk indoors [21], outdoors [22] and on a treadmill [23] while using a P300 spelling device. Motor imagery-based BCIs have been investigated under the presence of speech [24] and also applied to control a pinball machine [25], a virtual helicopter [26], a quadcopter [27] and a tetris game [28]. Several patient studies have been carried out on stroke, tetraplegic and even locked-in patients [29][30][31][32][33][34].…”

Robust Brain-Computer Interfaces

“…During gaming, signals produced by facial expressions, speech and eye movement heavily contaminate the, in comparison weak, EEG signals. As such, some of the research at HMI explores the challenges and drawbacks of BCI combined with for example speech recognition [27]. Most of our studies allow the user to behave naturally.…”