TY - JOUR
T1 - Prediction of flexion and extension movements of 4 fingers of the hand using a new labeled method
AU - Torres, J. A.García
AU - Fuentes, A. Ibarra
AU - Sánchez, E. Morales
AU - Zavala, A. Hernández
N1 - Publisher Copyright:
© Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.
PY - 2021/11/15
Y1 - 2021/11/15
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85120816554&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/2008/1/012015
DO - 10.1088/1742-6596/2008/1/012015
M3 - Artículo de la conferencia
AN - SCOPUS:85120816554
SN - 1742-6588
VL - 2008
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012015
T2 - 4th Latin American Conference on Bioimpedance 2021, CLABIO 2021
Y2 - 10 November 2021 through 13 November 2021
ER -