Open AccessComparative Analysis of Intellectual Methods for Muscular Contraction Interpretation for Gesture Interface Implementation
Author(s) -
E V Bunyaeva,
І. В. Кузнецов,
Yu. V. Ponomarchuk,
P S Timosh
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2096/1/012190
Subject(s) - computer science , gesture , decision tree , support vector machine , random forest , electromyography , artificial intelligence , gesture recognition , interface (matter) , logistic regression , machine learning , pattern recognition (psychology) , speech recognition , physical medicine and rehabilitation , medicine , bubble , maximum bubble pressure method , parallel computing
The paper considers comparative analysis results of the machine learning methods used for the gesture recognition based on the surface single-channel electromyography (sEMG) data. The data were processed using multilayer perceptron, support vector machine, decision tree ensemble (Random Forest) and logistic regression for the chosen four gesture types. The conclusion was derived on the analysis efficiency of these methods using commonly recommended accuracy metrics.