TY - JOUR
T1 - Analysis of Neural Network Based Proportional Myoelectric Hand Prosthesis Control
AU - Wand, Michael
AU - Kristoffersen, Morten B.
AU - Franzke, Andreas W.
AU - Schmidhuber, Jurgen
N1 - KAUST Repository Item: Exported on 2022-09-14
Acknowledgements: This work was supported by the EU H2020 research and innovation programme under Grant 687795 (Acronym: INPUT) . The authors with to thank Sebastian Amsüss for providing the data corpus and valuable advice, and Alessio Murgia and Raoul Bongers for helpful feedback and discussions.
PY - 2022/1/10
Y1 - 2022/1/10
N2 - 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 R2 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.
AB - 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 R2 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.
UR - http://hdl.handle.net/10754/680484
UR - https://ieeexplore.ieee.org/document/9675284/
UR - http://www.scopus.com/inward/record.url?scp=85122880201&partnerID=8YFLogxK
U2 - 10.1109/TBME.2022.3141308
DO - 10.1109/TBME.2022.3141308
M3 - Article
C2 - 35007192
SN - 1558-2531
VL - 69
SP - 2283
EP - 2293
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 7
ER -