Negligible Motion Artifacts in Scalp Electroencephalography (EEG) During Treadmill Walking

Abstract

Recent mobile brain/body imaging (MoBI) techniques based on active electrode scalp electroencephalogram (EEG) allow the acquisition and real-time analysis of brain dynamics during active unrestrained motor behavior involving whole body movements such as treadmill walking, over-ground walking and other locomotive and non-locomotive tasks. Unfortunately, MoBI protocols are prone to physiological and non-physiological artifacts, including motion artifacts that may contaminate the EEG recordings. A few attempts have been made to quantify these artifacts during locomotion tasks but with inconclusive results due in part to methodological pitfalls. In this paper, we investigate the potential contributions of motion artifacts in scalp EEG during treadmill walking at three different speeds (1.5, 3.0, and 4.5 km/h) using a wireless 64 channel active EEG system and a wireless inertial sensor attached to the subject's head. The experimental setup was designed according to good measurement practices using state-of-the-art commercially available instruments, and the measurements were analyzed using Fourier analysis and wavelet coherence approaches. Contrary to prior claims, the subjects' motion did not significantly affect their EEG during treadmill walking although precaution should be taken when gait speeds approach 4.5 km/h. Overall, these findings suggest how MoBI methods may be safely deployed in neural, cognitive, and rehabilitation engineering applications.

Keywords: EEG; artifacts; electroencephalography; walking.

FIGURE 1

(A) Photos of subject and experimental setup showing active EEG cap and triaxial MARG inertial sensor mounted on the forehead (left) and of (B) subject and experimental setup from similar protocol in Castermans et al. (2014), reproduced here with permissions from the author and publisher. (C) Sample raw EEG and Accelerometer data for three gait cycles for all four subjects and all three speeds. The x-, y-, and z-axes for the accelerometer represent the vertical, mediolateral, and anterior–posterior directions respectively. Traces with red labels indicate channels chosen for further analyses. Blue traces are EEG channels after processing with ASR. Vertical black lines indicate onset of Right Heel Strikes (RHS). (D) Flowchart illustrating steps and processes from recording signals to generating ERSPs.

FIGURE 2

Fast fourier transform (FFT) of EEG channels and downward acceleration showing frequency spectra for subject S3 at each speed; tick marks on top of plots indicate harmonics of the fundamental stepping frequency.

FIGURE 3

(A) Event-related spectral perturbations (ERSPs) of EEG channels and magnitude acceleration averaged across all gait cycles for one subject (S3) and all subjects’ averaged data at each speed. (B) ERSP plots of EEG channels and acceleration after processing EEG with Artifact Subspace Reduction.

FIGURE 4

Wavelet coherence of EEG channels with x-axis of acceleration for sample 10 s of walking data for subject S3 at each speed, (A) before and (B) after processing with Artifact Subspace Reduction. Frequency is scaled logarithmically on the y-axis and is limited to the delta band range of EEG (up to 4 Hz). Vertical black lines indicate onset of RHS; horizontal black lines indicate the frequency of stepping. The arrows indicate the relative phase relationship (in-phase pointing right, anti-phase pointing left, and EEG leading acceleration by 90° pointing straight down), and are only shown for regions with coherence greater than 0.5. Thick black contour lines indicate regions are significant against red noise at the 5% level.

FIGURE 5

Wavelet coherence of delta band EEG with x-axis of acceleration averaged across all subjects’ gait cycles at each speed (A) before and (B) after processing with Artifact Subspace Reduction. Vertical black lines indicate onset of gait cycle phase; horizontal black lines indicate the frequency of stepping. The arrows indicate the relative phase relationship (in-phase pointing right, anti-phase pointing left, and EEG leading acceleration by 90° pointing straight down), and are only shown for regions with coherence greater than 0.5.