Identification of Lower-Limb Motor Tasks via Brain-Computer Interfaces: A Topical Overview

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Technology

Background:

• Brain-computer interface (BCI) systems enhance life quality for individuals with motor disabilities.
• Research predominantly focuses on upper-limb movement intention, with limited studies on lower-limb intentions.
• Lower-limb neurorehabilitation is critical for conditions like multiple sclerosis and paralysis.

Purpose of the Study:

• To provide a topical overview of pattern recognition (PR) techniques for lower-limb motor task identification using BCI and electroencephalography (EEG) signals.
• To identify and compare benchmark and state-of-the-art PR techniques for improved signal classification and interpretability.
• To determine the most accurate algorithms for lower-limb movement intention identification.

Main Methods:

• Conducted a systematic literature search using defined terms and criteria to identify relevant papers.
• Reviewed 22 selected papers focusing on EEG signal recording methodologies for lower-limb tasks.
• Analyzed and compared algorithms used in preprocessing, feature extraction, and classification stages.

Main Results:

• Identified key pattern recognition algorithms applied in lower-limb BCI/EEG studies.
• Evaluated the experimental methodologies and signal analysis techniques employed.
• Compared the performance of various algorithms to determine accuracy.

Conclusions:

• Highlights the need for comparative studies on PR techniques in lower-limb BCI.
• Provides insights into suitable algorithms for lower-limb motor intention identification.
• Aims to guide the selection of effective PR techniques for neurorehabilitation.