P300 intention recognition based on phase lag index (PLI)-rich-club brain functional network.
Zhongmin Wang1,2,3, Leihua Xiang1, Rong Zhang1,2,3
1School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, Shaanxi 710121, China.
The Review of Scientific Instruments
|April 16, 2024
Summary
This study introduces a novel brain-computer interface (BCI) method using P300 signals and a rich-club network analysis. The approach enhances intention recognition by identifying key brain electrodes, achieving high accuracy in BCI datasets.
Area of Science:
- Neuroscience
- Computational Neuroscience
- Biomedical Engineering
Background:
- Brain-computer interface (BCI) technology utilizing P300 signals shows promise for clinical diagnostics and control systems.
- Identifying critical electrodes for wearable intention recognition is a significant research challenge.
Purpose of the Study:
- To propose a P300-based intention recognition method leveraging the rich-club phenomenon in brain networks.
- To identify and extract features from key 'rich-club' electrodes for improved BCI performance.
Main Methods:
- Constructed brain functional networks using the Phase Lag Index (PLI).
- Identified rich-club nodes based on node degree and betweenness centrality.
- Extracted non-linear and frequency domain features from rich-club nodes.
- Classified intentions using a Support Vector Machine (SVM).
Main Results:
- The range of rich-club coefficients differed significantly between intentional and non-intentional states.
- Achieved high recognition accuracy (96.93% and 94.93%) on BCI Competition III dataset with reduced channels.
- Demonstrated 95.50% recognition accuracy on the BCI Competition II dataset with reduced channels.
Conclusions:
- The PLI-rich-club-based method effectively identifies key electrodes for P300-based BCI.
- This approach offers a promising strategy for developing efficient wearable intention recognition systems.
- The findings support the utility of network science principles in advancing BCI technology.
