Exploring Imagined Movement for Brain-Computer Interface Control: An fNIRS and EEG Review.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Technology

Background:

• Brain-Computer Interfaces (BCIs) are crucial for restoring motor function in individuals with limb loss.
• Non-invasive neuroimaging techniques like Electroencephalography (EEG) and functional Near-Infrared Spectroscopy (fNIRS) are key to decoding motor intentions.

Purpose of the Study:

• This review evaluates the efficacy of EEG and fNIRS in decoding Motor Imagery (MI) for both offline and online BCI systems.
• To categorize experimental approaches and identify advancements in signal processing for BCI applications.

Main Methods:

• The review analyzes studies based on neuroimaging modality (EEG, fNIRS, hybrid), MI paradigm, and study design.
• Methods for signal acquisition, feature extraction, and classification algorithms, including deep learning, are examined.

Main Results:

• Offline MI decoding shows higher accuracy, while advancements in machine learning enhance online decoding feasibility.
• Hybrid EEG-fNIRS systems leverage the strengths of both modalities, improving performance.
• Online imagined movement prediction is feasible but less reliable than motor execution.

Conclusions:

• Continued integration of neuroimaging techniques and improved classification methods are vital for practical BCI applications.
• Further research and interdisciplinary collaboration are expected to accelerate the development of advanced neuroprosthetic technologies.