UC2018 DualMyo Hand Gesture Dataset

<p>This is&nbsp;set of data obtained from two consumer-market EMG sensors (Myo) with&nbsp;a subject performs 8 distinct&nbsp;hand gestures.</p> <p>There are a total of 110 repetitions of each class of gesture obtained across 5 recording sessions.</p> <p>Besides the data set, which is saved in a python pickle file, we include a python test script to load the data, generate random synthetic sequences of gestures and classify them with multiple models.</p> <p><strong>Gesture library:</strong></p> <ol> <li>Rest</li> <li>Closed fist</li> <li>Open hand</li> <li>Wave in</li> <li>Wave out</li> <li>Double-tap</li> <li>Hand down</li> <li>Hand up</li> </ol> <p><strong>Device placement:</strong></p> <ol> <li>The two Myos are placed on the forearm with the usb port pointing outwards, palm and sensor 5 facing upwards.</li> <li>The Myos are next to one another with their middle position close the the thickest section of the forearm.</li> <li>The outwards Myo is rotated slightly so that sensor 5 is aligned with&nbsp;&nbsp;the axis of the palmaris longus tendon.</li> <li>The Myo inside is rotated so that it has an angle of 22.5 degrees with the first Myo, in clockwise direction (subject perspective).</li> </ol> <p><strong>Acquisition protocol:</strong></p> <p>The subjects wear the armbands according to the instructions above. The sensors are run for a few minutes to warm-up.</p> <p>The subjects are requested to hold the positions of the gestures for a few seconds while we record 2 seconds of data. The gestures are repeated in random order in several sessions.</p>