Surface EMG-based signal acquisition for decoding hand movements

Biosignal processing plays a crucial role in modern hand prosthetics. The challenge is to restore functionality of a lost limb based on the signals acquired from the surface of the stump. The number of sensors (emg channels) used for signal acquisition influence the quality of a prosthetic hand. Modern algorithms (including neural networks) can significantly increase the acquired signal classification and therefore contribute to increased functionality of the prosthetic hand.
This data set contains EMG signals acquired for 12 different hand gestures. The EMG signals were recorded one at a time. The subject was asked to perform selected gesture within 1500ms. The data were acquired from 3 channels (1,2 column - ch1; 3,4 collumn - ch2; 5,6 collumn - ch3; ). The signals corresponding to each of 12 gestures are stored in separate files, the gesture repetitions are separated with "#". The data contains the emg envelope (1,3,5 column) and raw signals (2,4,6 column). and The EMG signals were recorded from 3 channels with one common electrode. The sampling frequency was 1000Hz. The data set can be used to design or test new algorithms for hand gestures recognition that can be further implemented in bio-prosthesis