3D free reaching movement prediction of upper-limb based on deep neural networks

Chao Wang; Manoj Sivan; Tianzhe Bao; Guqiang Li; Shengquan Xie

doi:10.1109/NER49283.2021.9441350

3D free reaching movement prediction of upper-limb based on deep neural networks

Chao Wang
, Manoj Sivan
, Tianzhe Bao
, Guqiang Li
, Shengquan Xie

School of Rehabilitation Sciences and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Quantitative assessment of motor disorder is one of the main challenges in the field of stroke rehabilitation. This paper proposes a simplified kinematic model for human upper limb(UL) using seven main joints of both the dominant and non-dominant side. With this model, a deep neural network (DNN) is used to predict the 3D free reaching movement of UL of a healthy participant. The experimental results show that the prediction trajectories can achieve high similarities with trajectories of real movements, indicating the promising accuracy in 3D movement estimation of UL achieved by the DNN. With the capability of identifying specific reaching movements in realtime, the trajectories predicted by this data-driven model can be utilized to inform the rehabilitation assessment and training in the future studies as a personalized therapy approach.

Original language	English
Title of host publication	2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021
Publisher	IEEE Computer Society
Pages	1005-1009
Number of pages	5
ISBN (Electronic)	9781728143378
DOIs	https://doi.org/10.1109/NER49283.2021.9441350
State	Published - 4 May 2021
Event	10th International IEEE/EMBS Conference on Neural Engineering, NER 2021 - Virtual, Online, Italy Duration: 4 May 2021 → 6 May 2021

Publication series

Name	International IEEE/EMBS Conference on Neural Engineering, NER
Volume	2021-May
ISSN (Print)	1948-3546
ISSN (Electronic)	1948-3554

Conference

Conference	10th International IEEE/EMBS Conference on Neural Engineering, NER 2021
Country/Territory	Italy
City	Virtual, Online
Period	4/05/21 → 6/05/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

3D
Data-driven
Movement prediction
Rehabilitation assessment
Upper limb

Access to Document

10.1109/NER49283.2021.9441350

Cite this

Wang, C., Sivan, M., Bao, T., Li, G., & Xie, S. (2021). 3D free reaching movement prediction of upper-limb based on deep neural networks. In 2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021 (pp. 1005-1009). Article 9441350 (International IEEE/EMBS Conference on Neural Engineering, NER; Vol. 2021-May). IEEE Computer Society. https://doi.org/10.1109/NER49283.2021.9441350

@inproceedings{819c2bdab96c447893b64b7ca7a3b0c6,

title = "3D free reaching movement prediction of upper-limb based on deep neural networks",

abstract = "Quantitative assessment of motor disorder is one of the main challenges in the field of stroke rehabilitation. This paper proposes a simplified kinematic model for human upper limb(UL) using seven main joints of both the dominant and non-dominant side. With this model, a deep neural network (DNN) is used to predict the 3D free reaching movement of UL of a healthy participant. The experimental results show that the prediction trajectories can achieve high similarities with trajectories of real movements, indicating the promising accuracy in 3D movement estimation of UL achieved by the DNN. With the capability of identifying specific reaching movements in realtime, the trajectories predicted by this data-driven model can be utilized to inform the rehabilitation assessment and training in the future studies as a personalized therapy approach.",

keywords = "3D, Data-driven, Movement prediction, Rehabilitation assessment, Upper limb",

author = "Chao Wang and Manoj Sivan and Tianzhe Bao and Guqiang Li and Shengquan Xie",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021 ; Conference date: 04-05-2021 Through 06-05-2021",

year = "2021",

month = may,

day = "4",

doi = "10.1109/NER49283.2021.9441350",

language = "英语",

series = "International IEEE/EMBS Conference on Neural Engineering, NER",

publisher = "IEEE Computer Society",

pages = "1005--1009",

booktitle = "2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021",

}

Wang, C, Sivan, M, Bao, T, Li, G & Xie, S 2021, 3D free reaching movement prediction of upper-limb based on deep neural networks. in 2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021., 9441350, International IEEE/EMBS Conference on Neural Engineering, NER, vol. 2021-May, IEEE Computer Society, pp. 1005-1009, 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021, Virtual, Online, Italy, 4/05/21. https://doi.org/10.1109/NER49283.2021.9441350

3D free reaching movement prediction of upper-limb based on deep neural networks. / Wang, Chao; Sivan, Manoj; Bao, Tianzhe et al.
2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021. IEEE Computer Society, 2021. p. 1005-1009 9441350 (International IEEE/EMBS Conference on Neural Engineering, NER; Vol. 2021-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 3D free reaching movement prediction of upper-limb based on deep neural networks

AU - Wang, Chao

AU - Sivan, Manoj

AU - Bao, Tianzhe

AU - Li, Guqiang

AU - Xie, Shengquan

PY - 2021/5/4

Y1 - 2021/5/4

N2 - Quantitative assessment of motor disorder is one of the main challenges in the field of stroke rehabilitation. This paper proposes a simplified kinematic model for human upper limb(UL) using seven main joints of both the dominant and non-dominant side. With this model, a deep neural network (DNN) is used to predict the 3D free reaching movement of UL of a healthy participant. The experimental results show that the prediction trajectories can achieve high similarities with trajectories of real movements, indicating the promising accuracy in 3D movement estimation of UL achieved by the DNN. With the capability of identifying specific reaching movements in realtime, the trajectories predicted by this data-driven model can be utilized to inform the rehabilitation assessment and training in the future studies as a personalized therapy approach.

AB - Quantitative assessment of motor disorder is one of the main challenges in the field of stroke rehabilitation. This paper proposes a simplified kinematic model for human upper limb(UL) using seven main joints of both the dominant and non-dominant side. With this model, a deep neural network (DNN) is used to predict the 3D free reaching movement of UL of a healthy participant. The experimental results show that the prediction trajectories can achieve high similarities with trajectories of real movements, indicating the promising accuracy in 3D movement estimation of UL achieved by the DNN. With the capability of identifying specific reaching movements in realtime, the trajectories predicted by this data-driven model can be utilized to inform the rehabilitation assessment and training in the future studies as a personalized therapy approach.

KW - 3D

KW - Data-driven

KW - Movement prediction

KW - Rehabilitation assessment

KW - Upper limb

UR - https://www.scopus.com/pages/publications/85107485603

U2 - 10.1109/NER49283.2021.9441350

DO - 10.1109/NER49283.2021.9441350

M3 - 会议稿件

AN - SCOPUS:85107485603

T3 - International IEEE/EMBS Conference on Neural Engineering, NER

SP - 1005

EP - 1009

BT - 2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021

PB - IEEE Computer Society

T2 - 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021

Y2 - 4 May 2021 through 6 May 2021

ER -

3D free reaching movement prediction of upper-limb based on deep neural networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this