Channel and Feature Selection for a Motor Imagery-Based BCI System Using Multilevel Particle Swarm Optimization

<div>Feature selection scatterplot. The abscissa represents 64 channels in total, the ordinate represents 35 features extracted from each channel, and the black dot represents the selected feature’s location.</div>

Computational Intelligence and Neuroscience

fig7

Figure 7

Figure 7: Channel and Feature Selection for a Motor Imagery-Based BCI System Using Multilevel Particle Swarm Optimization 