Prediction of flexion and extension movements of 4 fingers of the hand using a new labeled method

This work presents a neural network classifier for identifying the flexion and extension m ovements for four fingers from the hand, out of the surface electromyography signals in the forea rm muscles. A new la beled data m ethod was proposed based on time segmentation to relate the sEMG signa l with the corresponding finger m ovement. This is a different wa y of la beling the da ta for training the neural network, a llowing to reduce the amount of training gesture hand. The experim ent consists of 10 sessions in which the fingers a re flexed ra ndomly, one a t a time for 2 m inutes with a 16ms sample time. The a bsolute m ean value (MAV) is used a s a feature extra ctor in the tim e domain to a verage 5 samples a nd the normalized data is used for the neural network. Results show that this system with the la beled da ta m ethod, provides a 98.83% precision value for the index finger, 93.46% for the ring finger, 80.34% for the m iddle finger, a nd 68.46% for the little finger. The results are simila r to those found in the literature where they cla ssify different gestures using the conventional la beling m ethod.