Decoding EEG rhythms offline and online during motor imagery for standing and sitting based on a brain-computer...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Technology

Background:

• Motor imagery (MI)-based brain-computer interface (BCI) systems show potential for lower limb motor rehabilitation.
• Developing effective MI-BCI systems for daily activities like standing and sitting is crucial for enhancing functional independence.

Purpose of the Study:

• To develop and evaluate an MI-based BCI system for controlling sit-to-stand and stand-to-sit transitions.
• To assess the performance of the developed MI-BCI system in both offline and online experimental settings.

Main Methods:

• Utilized electroencephalography (EEG) with 17 active electrodes from 32 healthy subjects.
• Employed a combination of filter bank common spatial pattern (FBCSP) and regularized linear discriminant analysis (RLDA) for EEG decoding.
• Tested the system for motor imagery decoding during sit-to-stand and stand-to-sit actions.

Main Results:

• Offline analysis demonstrated high classification accuracy for motor imagery and idle states: 88.51% for sit-to-stand and 85.29% for stand-to-sit.
• Online experiments yielded even higher mean accuracies: 94.69% for sit-to-stand and 96.56% for stand-to-sit.
• The FBCSP and RLDA methods proved effective for decoding EEG signals related to standing and sitting motor imagery.

Conclusions:

• The developed MI-based BCI system is effective for decoding motor intentions related to standing and sitting.
• High accuracies achieved in both offline and online tests indicate the system's viability.
• This MI-BCI technology holds promise for future brain-controlled standing systems, potentially aiding individuals with mobility impairments.