Artificial Intelligence Approaches for EEG Signal Acquisition and Processing in Lower-Limb Motor Imagery: A...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Artificial Intelligence

Background:

• Motor imagery (MI) involves mentally simulating movements without physical action.
• Electroencephalography (EEG) signals from lower limb MI are crucial for brain-computer interface (BCI) development.
• BCIs aim to assist individuals with motor disabilities.

Purpose of the Study:

• To systematically review methodologies for acquiring and processing EEG signals for lower limb MI detection.
• To evaluate the effectiveness of artificial intelligence (AI) in identifying lower limb MI within BCI applications.

Main Methods:

• Systematic literature search in Scopus and IEEE Xplore.
• Included 35 studies meeting PRISMA guidelines from 287 records.
• Focused on EEG-based lower limb MI using AI.

Main Results:

• 85% of studies utilized machine/deep learning (e.g., SVM, CNN, LSTM).
• 65% incorporated multimodal fusion; 50% used decomposition algorithms.
• AI methods enhanced classification accuracy, interpretability, and real-time potential, but methodological variability persists.

Conclusions:

• AI-based EEG analysis shows promise for decoding lower limb motor imagery.
• Standardization of methods and datasets is essential for clinical translation.
• Development of portable systems is recommended for improved neurorehabilitation outcomes.