Inicio  /  Applied Sciences  /  Vol: 10 Par: 23 (2020)  /  Artículo
ARTÍCULO
TITULO

A User-Specific Hand Gesture Recognition Model Based on Feed-Forward Neural Networks, EMGs, and Correction of Sensor Orientation

Marco E. Benalcázar    
Ángel Leonardo Valdivieso Caraguay and Lorena Isabel Barona López    

Resumen

Hand gesture recognition systems have several applications including medicine and engineering. A gesture recognition system should identify the class, time, and duration of a gesture executed by a user. Gesture recognition systems based on electromyographies (EMGs) produce good results when the EMG sensor is placed on the same orientation for training and testing. However, when the orientation of the sensor changes between training and testing, which is very common in practice, the classification and recognition accuracies degrade significantly. In this work, we propose a system for recognizing, in real time, five gestures of the right hand. These gestures are the same ones recognized by the proprietary system of the Myo armband. The proposed system is based on the use of a shallow artificial feed-forward neural network. This network takes as input the covariances between the channels of an EMG and the result of a bag of five functions applied to each channel of an EMG. To correct the rotation of the EMG sensor, we also present an algorithm based on finding the channel of maximum energy given a set of synchronization EMGs, which for this work correspond to the gesture ?????????????? w a v e o u t . The classification and recognition accuracies obtained here show that the recognition system, together with the algorithm for correcting the orientation, allows a user to wear the EMG sensor in different orientations for training and testing, without a significant performance reduction. Finally, to reproduce the results obtained in this paper, we have made the code and the dataset used here publicly available.

 Artículos similares

       
 
Abraham López-Vivancos, Noelia González-Gálvez, Francisco Javier Orquín-Castrillón, Rodrigo Gomes de Souza Vale and Pablo Jorge Marcos-Pardo    
Bodybuilding training professionals and users who use bench press (BP) should be aware of the implication in choosing another exercise, either to improve muscle activation or to maintain activation levels while seeking another parallel objective. Dependi... ver más
Revista: Applied Sciences

 
Muhammad Tufail, HaeBin Lee, YangGyu Moon, Hwang Kim and KwanMyung Kim    
The rehabilitation practices encounter multifaceted problems inherent in the current context of the elderly with chronic low back pain (LBP). We addressed a particular multifaceted problem in the current context using an interdisciplinary co-design resea... ver más
Revista: Applied Sciences

 
Nidal Farhat, Pau Zamora, David Reichert, Vicente Mata, Alvaro Page and Angel Valera    
We present and validate a computationally efficient lower limb musculoskeletal model for the control of a rehabilitation robot. It is a parametric model that allows the customization of joint kinematics, and it is able to operate in real time. Methods: S... ver más
Revista: Applied Sciences

 
Krzysztof Strzecha, Marek Krakós, Boguslaw Wiecek, Piotr Chudzik, Karol Tatar, Grzegorz Lisowski, Volodymyr Mosorov and Dominik Sankowski    
This work deals with electromyography (EMG) signal processing for the diagnosis and therapy of different muscles. Because the correct muscle activity measurement of strongly noised EMG signals is the major hurdle in medical applications, a raw measured E... ver más
Revista: Applied Sciences

 
Bong-Jun Choi, Ju-Hwan Kim, Woo-Jin Yang, Dong-Jun Han, Jaewon Park and Dong-Wook Park    
Miniaturized flexible microelectrode arrays are desirable for small-area surface electromyography (sEMG) to detect the electrical activity generated by muscles in a specific area of the body. Here, we present a flexible 8-channel microelectrode array wit... ver más
Revista: Applied Sciences