Skip to main content

Reliability Analysis For Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional Networks

Lin, Yuzhou, Palaniappan, Ramaswamy, De Wilde, Philippe, Li, Ling (2022) Reliability Analysis For Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional Networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, . ISSN 1534-4320. E-ISSN 1558-0210. (doi:10.1109/TNSRE.2022.3141593) (KAR id:92603)

PDF Publisher pdf
Language: English


Download (907kB) Preview
[thumbnail of Reliability_Analysis_For_Finger_Movement_Recognition_With_Raw_Electromyographic_Signal_by_Evidential_Convolutional_Networks.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
PDF Author's Accepted Manuscript
Language: English

Restricted to Repository staff only

Contact us about this Publication
[thumbnail of FINAL VERSION.pdf]
PDF (The edited version with corrections) Publisher pdf
Language: English


Download (1MB) Preview
[thumbnail of The edited version with corrections]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
http://dx.doi.org/10.1109/TNSRE.2022.3141593

Abstract

Hand gesture recognition with surface electromyography (sEMG) is indispensable for Muscle-Gesture-Computer Interface. The usual focus of it is upon performance evaluation involving the accuracy and robustness of hand gesture recognition. However, addressing the reliability of such classifiers has been absent, to our best knowledge. This may be due to the lack of consensus on the definition of model reliability in this field. An uncertainty-aware model has the potential to self-evaluate the quality of its inference, thereby making it more reliable. Moreover, uncertainty-based rejection has been shown to improve the performance of sEMG-based hand gesture recognition. Therefore, we first define model reliability here as the quality of its uncertainty estimation and propose an offline framework to quantify it. To promote reliability analysis, we propose a novel end-to-end uncertainty-aware finger movement classifier, i.e., evidential convolutional neural network (ECNN), and illustrate the advantages of its multidimensional uncertainties such as vacuity and dissonance. Extensive comparisons of accuracy and reliability are conducted on NinaPro Database 5, exercise A, across CNN and three variants of ECNN based on different training strategies. The results of classifying 12 finger movements over 10 subjects show that the best mean accuracy achieved by ECNN is 76.34%, which is slightly higher than the state-of-the-art performance. Furthermore, ECNN variants are more reliable than CNN in general, where the highest improvement of reliability of 19.33% is observed. This work demonstrates the potential of ECNN and recommends using the proposed reliability analysis as a supplementary measure for studying sEMG-based hand gesture recognition.

Item Type: Article
DOI/Identification number: 10.1109/TNSRE.2022.3141593
Uncontrolled keywords: Convolutional neural network, Evidential deep learning, Hand gesture recognition, Model reliability, Surface electromyography (sEMG), Uncertainty-awareness
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.9.H85 Human computer interaction
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Yuzhou Lin
Date Deposited: 09 Jan 2022 15:58 UTC
Last Modified: 28 Jan 2022 03:03 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/92603 (The current URI for this page, for reference purposes)
Lin, Yuzhou: https://orcid.org/0000-0003-3184-0523
Palaniappan, Ramaswamy: https://orcid.org/0000-0001-5296-8396
De Wilde, Philippe: https://orcid.org/0000-0002-4332-1715
Li, Ling: https://orcid.org/0000-0002-4026-0216
  • Depositors only (login required):

Downloads

Downloads per month over past year