Motor Imagery EEG Decoding Based on New Spatial-Frequency Feature and Hybrid Feature Selection Method

<div>The band-pass filtering on each channel of the signal <span class="nowrap"><svg height="8.99889pt" id="M21" style="vertical-align:-0.04980946pt" version="1.1" viewbox="-0.0498162 -8.94908 8.17683 8.99889" width="8.17683pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M574 193C552 131 535 101 511 78C482 51 412 45 334 45C271 45 243 47 210 51C335 250 459 440 584 635L576 650H170C138 650 127 652 112 675H86C84 623 78 553 75 476L108 475C119 522 135 552 147 570C163 594 182 605 284 605H410C286 412 157 211 29 17L40 0H571C581 35 599 136 607 185L574 193Z"></path></g></svg>.</span></div>

Mathematical Problems in Engineering

fig2

Figure 2

Figure 2: Motor Imagery EEG Decoding Based on New Spatial-Frequency Feature and Hybrid Feature Selection Method 