This study aimed to develop a convolutional neural network (CNN) model to predict shoulder joint reaction forces from 3D body kinematics. Results showed a good convergence between CNN model prediction and musculoskeletal model estimation for six novel tasks. Therefore, a CNN-based deep learning model can be used as a simple and relatively less time- and labor-intensive method to identify unsafe shoulder exertions in order to prevent the incidence of shoulder injuries or pathologies in occupational settings.
ChowdhuryS. K.NimbarteA. D.HsiaoH.GopalakrishnanB.JaridiM. (2018). A biomechanical shoulder strain index based on stabilizing demand of shoulder joint. Ergonomics, 61(12), 1657-1670.
4.
De VriesW.VeegerH.BatenC.van der HelmF. (2016). Can shoulder joint reaction forces be estimated by neural networks?Journal of biomechanics, 49(1), 73-79.
5.
IoffeS.SzegedyC. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
6.
KshirsagarG.LondheN. (2018). Improving performance of Devanagari script input-based P300 speller using deep learning. IEEE Transactions on Biomedical Engineering, 66(11), 2992-3005.
7.
LiewS. S.Khalil-HaniM.BakhteriR. (2016). Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems. Neurocomputing, 216, 718-734.
8.
SrivastavaN.HintonG.KrizhevskyA.SutskeverI.SalakhutdinovR. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
9.
WangS.-H.PhillipsP.SuiY.LiuB.YangM.ChengH. (2018). Classification of Alzheimer’s disease based on eight-layer convolutional neural network with leaky rectified linear unit and max pooling. Journal of medical systems, 42(5), 85.
10.
WiranataA.WibowoS. A.PatmasariR.RahmaniaR.MayasariR. (2018). Investigation of padding schemes for faster R-CNN on vehicle detection. Paper presented at the 2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC).
