Title :
ANN-models for jaw-research
Author :
Beddoes, M.P. ; Peck, C.C. ; Hannam, A.G. ; Kitney, R.K. ; Ward, R.K.
Author_Institution :
Dept. of Electr. & Comput. Eng., British Columbia Univ., Canada
Abstract :
ANN models for the opening jaw starting from the closed position are studied here. The models link final tension values in four active jaw muscles to final jaw positions and final tensions in the remaining muscles. The models assume the jaw opens in the midline: thus, right- and left-side muscles have equal tensions, and jaw motion is in two-dimensions. We have examined two ANN jaw models. One gives jaw motion and passive muscle tensions given active muscle tensions. The other, possibly of practical use, gives jaw motion given active muscle tensions; passive muscle tensions appear as signals inside the model.
Keywords :
backpropagation; biomechanics; muscle; neural nets; neurophysiology; physiological models; ANN-models; active muscle tensions; backpropagation method; closed position; equal tensions; final jaw positions; final tension values; four active jaw muscles; jaw motion; jaw-research; left-side muscles; midline; opening jaw; passive muscle tensions; right-side muscles; two dimensions; Actuators; Biological neural networks; Biological system modeling; Biology computing; Circuit simulation; Electric variables measurement; Humans; Muscles; Resists; Steady-state;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020412