Search: onr:"swepub:oai:gup.ub.gu.se/319177" >
Analysis of Neural ...
Analysis of Neural Network Based Proportional Myoelectric Hand Prosthesis Control
- Article/chapterEnglish2022
Publisher, publication year, extent ...
-
Institute of Electrical and Electronics Engineers (IEEE),2022
Numbers
-
LIBRIS-ID:oai:gup.ub.gu.se/319177
-
https://gup.ub.gu.se/publication/319177URI
-
https://doi.org/10.1109/tbme.2022.3141308DOI
Supplementary language notes
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:art swepub-publicationtype
Notes
-
Objective: We show that state-of-the-art deep neural networks achieve superior results in regression-based multi-class proportional myoelectric hand prosthesis control than two common baseline approaches, and we analyze the neural network mapping to explain why this is the case. Methods: Feedforward neural networks and baseline systems are trained on an offline corpus of 11 able-bodied subjects and 4 prosthesis wearers, using the R-2 score as metric. Analysis is performed using diverse qualitative and quantitative approaches, followed by a rigorous evaluation. Results: Our best neural networks have at least three hidden layers with at least 128 neurons per layer; smaller architectures, as used by many prior studies, perform substantially worse. The key to good performance is to both optimally regress the target movement, and to suppress spurious movements. Due to the properties of the underlying data, this is impossible to achieve with linear methods, but can be attained with high exactness using sufficiently large neural networks. Conclusion: Neural networks perform significantly better than common linear approaches in the given task, in particular when sufficiently large architectures are used. This can be explained by salient properties of the underlying data, and by theoretical and experimental analysis of the neural network mapping. Significance: To the best of our knowledge, this work is the first one in the field which not only reports that large and deep neural networks are superior to existing architectures, but also explains this result.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Kristoffersen, Morten BGothenburg University,Göteborgs universitet,Institutionen för kliniska vetenskaper, Avdelningen för ortopedi,Institute of Clinical Sciences, Department of Orthopaedics
(author)
-
Franzke, A. W.
(author)
-
Schmidhuber, J.
(author)
-
Göteborgs universitetInstitutionen för kliniska vetenskaper, Avdelningen för ortopedi
(creator_code:org_t)
Related titles
-
In:Ieee Transactions on Biomedical Engineering: Institute of Electrical and Electronics Engineers (IEEE)69:7, s. 2283-22930018-92941558-2531
Internet link
Find in a library
To the university's database