Gesture Decoding Using ECoG Signals from Human Sensorimotor Cortex: A Pilot Study

Figure 4

The decoding performance varies as a function of the number of channels. The green curves represent the decoding performance using the channels selected by greedy selection, and the red curves represent the result of the channels selected by single channel selection. The performance of greedy selection significantly yields higher performance than that of single channel selection when the same number of channels was used. The upside-down triangles indicate that the greedy selection performance is significantly higher than the single channel selection performance. The yellow stars indicate that the decoding performance obtained from the channel subset reaches the saturated point in the greedy selection. No significant improvement of decoding performance was found after adding more channels into the subset.