Decoding Motor Imagery through Common Spatial Pattern Filters at the EEG Source Space.

Dimitris Kugiumtzis,Ioannis Xygonakis,Niki Pandria,Panagiotis D. Bamidis,Alkinoos Athanasiou

doi:10.1155/2018/7957408

Dimitris Kugiumtzis, Ioannis Xygonakis + Show 3 more

Open Access

https://doi.org/10.1155/2018/7957408

Copy DOI

Abstract

Brain-Computer Interface (BCI) is a rapidly developing technology that aims to support individuals suffering from various disabilities and, ultimately, improve everyday quality of life. Sensorimotor rhythm-based BCIs have demonstrated remarkable results in controlling virtual or physical external devices but they still face a number of challenges and limitations. Main challenges include multiple degrees-of-freedom control, accuracy, and robustness. In this work, we develop a multiclass BCI decoding algorithm that uses electroencephalography (EEG) source imaging, a technique that maps scalp potentials to cortical activations, to compensate for low spatial resolution of EEG. Spatial features were extracted using Common Spatial Pattern (CSP) filters in the cortical source space from a number of selected Regions of Interest (ROIs). Classification was performed through an ensemble model, based on individual ROI classification models. The evaluation was performed on the BCI Competition IV dataset 2a, which features 4 motor imagery classes from 9 participants. Our results revealed a mean accuracy increase of 5.6% with respect to the conventional application method of CSP on sensors. Neuroanatomical constraints and prior neurophysiological knowledge play an important role in developing source space-based BCI algorithms. Feature selection and classifier characteristics of our implementation will be explored to raise performance to current state-of-the-art.

Highlights

Brain-Computer Interface (BCI) is emerging as a promising rehabilitation technology, that aims to establish a connection between brain activity and external devices
Beyond the BCIC IV 2a dataset that is a common ground for the evaluation of methods decoding multiple MI, we aim to evaluate the improved method on dataset we compiled for the CSI: Brainwave project, containing EEG data of healthy or subjects with spinal cord injury performing multiple motor imagery mainly of the upper limbs [36, 55]
Source estimation and application of Common Spatial Pattern (CSP) filters at the source space constitute a promising solution to increasing classification accuracy of noninvasive BCIs

Summary

Introduction

Brain-Computer Interface (BCI) is emerging as a promising rehabilitation technology, that aims to establish a connection between brain activity and external devices. As invasive BCIs use intracranial electrodes to measure electrical activity of the cerebral cortex, either implanted or directly lying on the cortical surface such as electrocorticography (ECoG), their usage is limited due to ethical, medical, and physiological issues [2]. Ese limitations are not present with noninvasive BCIs, and the most widely used noninvasive modality, electroencephalography (EEG), uses electrodes over the scalp to measure inferred cerebral cortical activity. SMR or mu (μ) rhythm, typically measured at the alpha band of 8–13 Hz over the scalp area overlying the sensorimotor cortex, can be modulated during motor execution or motor imagery (MI) tasks, and the BCIs decoding this type of signal are referred to as SMR-BCIs. Motor imagery displays similar patterns of brain activation and communication to motor execution [4, 5] while research

Objectives

Methods

Results

Discussion

Conclusion