TY - JOUR
T1 - Convolutional LSTM
T2 - a deep learning approach to predict shoulder joint reaction forces
AU - Mubarrat, S. T.
AU - Chowdhury, S.
N1 - Publisher Copyright:
© 2022 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2023
Y1 - 2023
N2 - We developed a Convolutional LSTM (ConvLSTM) network to predict shoulder joint reaction forces using 3D shoulder kinematics data containing 30 different shoulder activities from eight human subjects. We considered simulation outcomes from the AnyBody musculoskeletal model as the baseline force dataset to validate ConvLSTM model predictions. Results showed a good correlation (>80% accuracy, r≥0.82) between ConvLSTM predicted and AnyBody estimated force values, the generalization of the developed model for novel task type (p-value=0.07 ∼ 0.33), and a better prediction accuracy for the ConvLSTM model than conventional CNN and LSTM models.
AB - We developed a Convolutional LSTM (ConvLSTM) network to predict shoulder joint reaction forces using 3D shoulder kinematics data containing 30 different shoulder activities from eight human subjects. We considered simulation outcomes from the AnyBody musculoskeletal model as the baseline force dataset to validate ConvLSTM model predictions. Results showed a good correlation (>80% accuracy, r≥0.82) between ConvLSTM predicted and AnyBody estimated force values, the generalization of the developed model for novel task type (p-value=0.07 ∼ 0.33), and a better prediction accuracy for the ConvLSTM model than conventional CNN and LSTM models.
KW - AnyBody musculoskeletal modelling
KW - Deep learning network
KW - convolutional LSTM
KW - shoulder joint reaction forces
KW - shoulder movement
UR - http://www.scopus.com/inward/record.url?scp=85126070545&partnerID=8YFLogxK
U2 - 10.1080/10255842.2022.2045974
DO - 10.1080/10255842.2022.2045974
M3 - Article
C2 - 35234548
AN - SCOPUS:85126070545
SN - 1025-5842
VL - 26
SP - 65
EP - 77
JO - Computer Methods in Biomechanics and Biomedical Engineering
JF - Computer Methods in Biomechanics and Biomedical Engineering
IS - 1
ER -