Multiple Kernel Based Region Importance Learning for Neural Classification of Gait States from EEG Signals

Abstract

With the development of Brain Machine Interface (BMI) systems, people with motor disabilities are able to control external devices to help them restore movement abilities. Longitudinal validation of these systems is critical not only to assess long-term performance reliability but also to investigate adaptations in electrocortical patterns due to learning to use the BMI system. In this paper, we decode the patterns of user's intended gait states (e.g., stop, walk, turn left, and turn right) from scalp electroencephalography (EEG) signals and simultaneously learn the relative importance of different brain areas by using the multiple kernel learning (MKL) algorithm. The region of importance (ROI) is identified during training the MKL for classification. The efficacy of the proposed method is validated by classifying different movement intentions from two subjects—an able-bodied and a spinal cord injury (SCI) subject. The preliminary results demonstrate that frontal and fronto-central regions are the most important regions for the tested subjects performing gait movements, which is consistent with the brain regions hypothesized to be involved in the control of lower-limb movements. However, we observed some regional changes comparing the able-bodied and the SCI subject. Moreover, in the longitudinal experiments, our findings exhibit the cortical plasticity triggered by the BMI use, as the classification accuracy and the weights for important regions—in sensor space—generally increased, as the user learned to control the exoskeleton for movement over multiple sessions.

Brain–machine interfaces for controlling lower-limb powered robotic systems

“…Only two of the identified studies tested more than ten subjects, albeit healthy able-bodied subjects (García-Cossio et al 2015, Kwak et al 2015. Among the four studies that recruited both healthy subjects and patients: He et al (2014) and Zhang et al (2017) only had one patient each; García-Cossio et al (2015) and López-Larraz et al (2016) used different protocols in the two groups.…”

“…Many MRCP components have been identified, such as P300 and N100. MRCP is the most commonly used neural feature among identified studies (Kilicarslan et al 2013, He et al 2014, Donati et al 2016, López-Larraz et al 2016, Zhang et al 2017. Although the time domain signals were usually sent to a decoder without explicitly specifying which components to analyze among these studies.…”

“…Based on the continuity of states being decoded, they can be grouped into two categories: (1) Those featuring continuous reconstruction of trajectories, such as linear regression (Vouga et al 2017) (Kilicarslan et al 2013(Kilicarslan et al , 2016, random forest , multiple kernel learning (Zhang et al 2017), and maximizing canonical correlation coefficients (Kwak et al 2015).…”

“…BMIs in most of the identified studies classified discrete tasks such as walk versus stop: four studies solely implemented this binary classification in their analysis (Do et al 2013, Kilicarslan et al 2013, López-Larraz et al 2016. In addition to walk versus stop, four studies added left/right turns to their tasks (Kwak et al 2015, Donati et al 2016, Zhang et al 2017. Other tasks include passive versus active walking in Lokomat (García-Cossio et al 2015), sit and stand (Kwak et al 2015), and perform kicking motion (Donati et al 2016).…”

“…Kwak et al (2015) and Zhang et al (2017) are the only two identified studies that reported confusion matrices. Pattern of high values on the diagonal was clearly shown.…”