Identifying motor imagery activities in brain computer interfaces based on the intelligent selection of most informative timeframe

The estimation of covariance matrices is of prime importance to analyze the distribution of multivariate signals. In motor imagery–based brain-computer interfaces (MI-BCI), covariance matrices play a central role in the extraction of features from recorded electroencephalograms (EEGs); therefore, correctly estimating covariance is crucial for EEG classification. This letter discusses algorithms to average sample covariance matrices (SCMs) for the selection of the reference matrix in tangent space mapping (TSM)–based MI-BCI. Tangent space mapping is a powerful method of feature extraction and strongly depends on the selection of a reference covariance matrix. In general, the observed signals may include outliers; therefore, taking the geometric mean of SCMs as the reference matrix may not be the best choice. In order to deal with the effects of outliers, robust estimators have to be used. In particular, we discuss and test the use of geometric medians and trimmed averages (defined on the basis of several metrics) as robust estimators. The main idea behind trimmed averages is to eliminate data that exhibit the largest distance from the average covariance calculated on the basis of all available data. The results of the experiments show that while the geometric medians show little differences from conventional methods in terms of classification accuracy in the classification of electroencephalographic recordings, the trimmed averages show significant improvement for all subjects.

Download Full-text

Guidelines for Feature Matching Assessment of Brain–Computer Interfaces for Augmentative and Alternative Communication

American Journal of Speech-Language Pathology ◽

10.1044/2018_ajslp-17-0135 ◽

2018 ◽

Vol 27 (3) ◽

pp. 950-964 ◽

Cited By ~ 4

Author(s):

Kevin M. Pitt ◽

Jonathan S. Brumberg

Keyword(s):

Motor Imagery ◽

Augmentative And Alternative Communication ◽

Feature Matching ◽

Full Range ◽

Brain Computer Interfaces ◽

Alternative Communication ◽

Access Methods ◽

Computer Interfaces ◽

Sensory Motor ◽

Selection Of

Purpose Brain–computer interfaces (BCIs) can provide access to augmentative and alternative communication (AAC) devices using neurological activity alone without voluntary movements. As with traditional AAC access methods, BCI performance may be influenced by the cognitive–sensory–motor and motor imagery profiles of those who use these devices. Therefore, we propose a person-centered, feature matching framework consistent with clinical AAC best practices to ensure selection of the most appropriate BCI technology to meet individuals' communication needs. Method The proposed feature matching procedure is based on the current state of the art in BCI technology and published reports on cognitive, sensory, motor, and motor imagery factors important for successful operation of BCI devices. Results Considerations for successful selection of BCI for accessing AAC are summarized based on interpretation from a multidisciplinary team with experience in AAC, BCI, neuromotor disorders, and cognitive assessment. The set of features that support each BCI option are discussed in a hypothetical case format to model possible transition of BCI research from the laboratory into clinical AAC applications. Conclusions This procedure is an initial step toward consideration of feature matching assessment for the full range of BCI devices. Future investigations are needed to fully examine how person-centered factors influence BCI performance across devices.

Download Full-text