Features selection and classification to estimate elbow movements

5th International Workshop on New Computational Methods for Inverse Problems

物理学;计算机科学

Rubiano, A.^1,3 ; Ramírez, J.L.^1 ; El Korso, M.N.^1 ; Jouandeau, N.^2 ; Gallimard, L.^1 ; Polit, O.^1

LEME, Université Paris Ouest Nanterre la Défense, 50 rue de Sévres, Ville d'Avray

92410, Italy^1

LIASD, Université Paris 8, 2 Rue de la Libert, Saint-Denis

93526, France^2

Universidad Militar Nueva Granada, Cr 11 101-80, Bogotá

110111, Colombia^3

关键词: EMG signal;    Estimation results;    Features selection;    Kinematic information;    Non linear;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/657/1/012012/pdf
DOI  :  10.1088/1742-6596/657/1/012012

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In this paper, we propose a novel method to estimate the elbow motion, through the features extracted from electromyography (EMG) signals. The features values are normalized and then compared to identify potential relationships between the EMG signal and the kinematic information as angle and angular velocity. We propose and implement a method to select the best set of features, maximizing the distance between the features that correspond to flexion and extension movements. Finally, we test the selected features as inputs to a non-linear support vector machine in the presence of non-idealistic conditions, obtaining an accuracy of 99.79% in the motion estimation results.