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

Table 6

Comparison between our proposed method and existing methods.

Feature extraction	Channel selection	Feature selection	Classification	Accuracy (%)
MST	√	√	BLDA	99
ST [6]	—	√	BLDA	96
, fractal intercept, and lacunarity [21]	√	—	Gradient boosting	95
Band power [22]	√	—	FLDA	94
UDWT [23]	√	√	LDA	93
CSP [24]	√	—	FLDA	90