Abstract
Brain-machine interfaces (BMIs) have been applied as new rehabilitation tools for motor disabled individuals. Active involvement of cerebral activity has been shown to enhance neuroplasticity and thus to restore mobility. Various studies have focused on the detection of upper-limb movement intention, while the fewer study has investigated the lower-limb movement intention decoding. This study presents a BMI to decode the self-paced lower-limb movement intention, with 10 healthy subjects participating in the experiment. We varied four influence factors including the movement type (dorsiflexion or plantar flexion), the limb side (left or right leg), the processing method (time-series analysis based on MRCP, i.e., movement-related cortical potential or frequency-domain estimation based on SMR, i.e., sensory motor rhythm) and the frequency band (e.g., delta, theta, mu, beta and MRCP band at [0.1 1] Hz), to estimate both single-trial and sample-based performance. Feature analysis was then conducted to show the discriminant power (DP) and brain modulations. The average detection latency was −0.334 ± 0.216 s in single-trial basis across all conditions. An average area under the curve (AUC) of 91.0 ± 3.5% and 68.2 ± 4.6% was obtained for the MRCP-based and SMR-based method in the classification, respectively. The best performance was yielded from plantar flexion with left leg using time-series analysis on the MRCP band. The feature analysis indicated a cross-subject consistency of DP with the MRCP-based method and subject-specific variance of DP with the SMR-based method. The results presented here might be further exploited in a rehabilitation scenario. The comprehensive factor analysis might be used to shed light on the design of an effective brain switch to trigger external robotic devices.
Highlights
A brain-machine interface (BMI), known as a brain-computer interface (BCI), is a communication and control system that does not require any peripheral muscular activity (Wolpaw et al, 2002)
Since the number of idle and preparation epochs was imbalanced, we further reported the results with an area under the curve (AUC) in the receiver operating characteristics (ROC) space, which represented the trade-off between the false positive rates (FPR) and true positive rates (TPR)
Since the movementrelated cortical potentials (MRCPs) has been proved prominent in the frequency band of [0.1,1] Hz (Lew et al, 2012; Garipelli et al, 2013), we only exploited this narrow band in the MRCP-based method
Summary
A brain-machine interface (BMI), known as a brain-computer interface (BCI), is a communication and control system that does not require any peripheral muscular activity (Wolpaw et al, 2002). Decoding of Self-paced Lower-Limb Movement Intention system can improve neuroplasticity and enhance the opportunity of motor recovery (Beldalois et al, 2011; Hatem et al, 2016). In this respect, non-invasive EEG-based BMI has been developed to decode the user’s movement intention based on markers of active brain involvement in the preparation of the desired movement. Self-paced wrist movement onset was detected from ERD-based EEG correlates from healthy subjects (Bai et al, 2011). Another work by Ibánez et al used self-paced wrist extension as the movement type to detect the motor intention from essential tremor patients (Ibánez et al, 2013). In this work, SMRbased intent detection only refers to the power decrease or ERD
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
