A novel attention-based hybrid CNN-RNN
architecture
for sEMG-based gesture recognition
ABCD PBi
A novel attention-based hybrid CNN-RNN
architecture
for sEMG-based gesture recognition
Autor:
Hu, Yu
;
Wong, Yongkang
;
Wei, Wentao
;
Du, Yu
;
Kankanhalli, Mohan
;
Geng, Weidong
He, Huiguang
Assuntos:
Algorithms
;
Analysis
;
Architecture
;
Artificial intelligence
;
Artificial neural networks
;
Benchmarks
;
Computer and Information Sciences
;
Computer science
;
Deep learning
;
Electromyography
;
Engineering and Technology
;
Feature extraction
;
Gesture recognition
;
International conferences
;
Machine learning
;
Methods
;
Neural networks
;
Object recognition
;
Recurrent neural networks
;
Research and Analysis Methods
;
Researchers
;
Sign language
;
Spatial data
;
State of the art
;
Voice recognition
É parte de:
PloS one, 2018-10, Vol.13 (10), p.e0206049-e0206049
Notas:
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Competing Interests: The authors have declared that no competing interests exist.
Descrição:
The surface electromyography (sEMG)-based gesture recognition with deep learning approach plays an increasingly important role in human-computer interaction. Existing deep learning architectures are mainly based on Convolutional Neural Network (CNN)
architecture
which captures spatial information of electromyogram signal. Motivated by the sequential nature of electromyogram signal, we propose an attention-based hybrid CNN and RNN (CNN-RNN)
architecture
to better capture temporal properties of electromyogram signal for gesture recognition problem. Moreover, we present a new sEMG image representation method based on a traditional feature vector which enables deep learning architectures to extract implicit correlations between different channels for sparse multi-channel electromyogram signal. Extensive experiments on five sEMG benchmark databases show that the proposed method outperforms all reported state-of-the-art methods on both sparse multi-channel and high-density sEMG databases. To compare with the existing works, we set the window length to 200ms for NinaProDB1 and NinaProDB2, and 150ms for BioPatRec sub-database, CapgMyo sub-database, and csl-hdemg databases. The recognition accuracies of the aforementioned benchmark databases are 87.0%, 82.2%, 94.1%, 99.7% and 94.5%, which are 9.2%, 3.5%, 1.2%, 0.2% and 5.2% higher than the state-of-the-art performance, respectively.
Editor:
United States: Public Library of Science
Idioma:
Inglês