A penalized time-frequency band feature selection and classification procedure for improved motor intention decoding in multichannel EEG.

OBJECTIVE

Motor imagery brain-computer interfaces (MI-BCIs) based on electroencephalography (EEG), a promising technology to provide assistance and support rehabilitation of neurological patients with sensorimotor impairments, require a reliable and adaptable subject-specific model to efficiently decode motor intention. The most popular EEG feature extraction algorithm for MI-BCIs is the common spatial patterns (CSP) method, but its performance strongly depends on the predefined frequency band and time segment length for analyzing the EEG signal.

APPROACH

In this work, a novel method for efficiently decoding motor intention for EEG-based BCIs performing multiple frequency band analysis in multiple EEG segments is presented. This decoding algorithm uses raw multichannel EEG data which are decomposed into specific [Formula: see text] temporal and [Formula: see text] frequency bands. Features are extracted at each [Formula: see text]-[Formula: see text] band by using CSP. Feature selection and classification are simultaneously performed by means of a fast procedure, based on elastic-net regression, which allows for the inclusion of a priori discriminative information into the model. The effectiveness of the proposed method is tested off-line on two public EEG-based MI-BCI datasets and on a self-acquired dataset in two configurations: multiple temporal windows and single temporal window.

MAIN RESULTS

The experimental results show that the proposed multiple time-frequency band method yields overall accuracy improvements of up to [Formula: see text] (average accuracy of 84.8%) as compared to the best current state-of-the-art methods based on filter bank analysis and CSP for MI detection. Also, classification variability is reduced, making the proposed method more robust to intra-subject EEG fluctuations.

SIGNIFICANCE

This paper presents a novel approach for improving motor intention detection by automatically selecting subject-specific spatio-temporal-spectral features, especially when MI has to be detected against rest condition. This technique contributes to the further advancement and application of EEG-based MI-BCIs for assistance and neurorehabilitation therapy.