Abstract
The ability to assess the loads on the spine in industry using biologically-assisted models has been limited by the current capability to obtain accurate muscle activities that could be entered into an EMG-assisted model. One crucial aspect of EMG-assisted models is the capability to capture the antagonistic coactivity in dynamic lifting conditions. However, limitations of electromyography equipment make it difficult to assess the muscle activity in industry. The overall project developed a complex engine using fuzzy average with fuzzy cluster distribution techniques in combination with neural network structure. The objective of the current study was compare the predicted spine loads for the actual and predicted muscle activities during sagittal lifting conditions. The model fidelity of the EMG-assisted spine load model was actually improved with the predicted EMG as compared to the actual EMG with improved r-square and average absolute error values. Furthermore, the three-dimensional spine loads were almost identical for the predicted EMG as compared to the actual EMG (within 35 N in each plane). The compression forces predicted within 1% while shear forces were within 11%. Overall, the new neuro-fuzzy engine provides an accurate estimation of the coactivity pattern during lifting that can now be applied in industrial settings where traditional muscle activity assessment methods are subjected to noise or are difficult to administer.
Get full access to this article
View all access options for this article.