[A review of researches on electroencephalogram decoding algorithms in brain-computer interface]

Area of Science:

• Neuroscience
• Artificial Intelligence
• Biomedical Engineering

Background:

• Brain-computer interfaces (BCI) enable direct communication between the brain and external devices.
• Effective electroencephalogram (EEG) feature decoding is crucial for BCI system performance.
• Algorithm efficiency in feature extraction and classification significantly impacts BCI accuracy.

Purpose of the Study:

• To provide a comprehensive overview of commonly used EEG features in BCI systems.
• To introduce classical and advanced algorithms for EEG feature extraction and classification.
• To present novel BCI algorithms developed recently to enhance system performance.

Main Methods:

• Review and categorization of established EEG features utilized in BCI.
• Analysis of fundamental and enhanced classical algorithms for BCI data processing.
• Introduction and discussion of recent algorithmic advancements in BCI research.

Main Results:

• A structured overview of EEG features relevant to BCI applications.
• Comparison of the efficacy of classical versus advanced BCI algorithms.
• Identification of emerging trends and new algorithms in the BCI field.

Conclusions:

• Understanding EEG features and algorithms is key to developing high-performance BCIs.
• The evolution of algorithms continuously improves BCI decoding capabilities.
• This review aims to stimulate further research and development in advanced BCI systems.