Skip to content
BY-NC-ND 3.0 license Open Access Published by De Gruyter Open Access July 28, 2013

The use of artificial neural networks to predict the muscle behavior

  • Patrik Kutilek EMAIL logo , Slavka Viteckova , Zdenĕk Svoboda and Pavel Smrcka
From the journal Open Engineering


The aim of this article is to introduce methods of prediction of muscle behavior of the lower extremities based on artificial neural networks, which can be used for medical purposes. Our work focuses on predicting muscletendon forces and moments during human gait with the use of angle-time diagram. A group of healthy children and children with cerebral palsy were measured using a Vicon MoCap system. The kinematic data was recorded and the OpenSim software system was used to identify the joint angles, muscle-tendon forces and joint muscle moment, which are presented graphically with time diagrams. The musculus gastrocnemius medialis that is often studied in the context of cerebral palsy have been chosen to study the method of prediction. The diagrams of mean muscle-tendon force and mean moment are plotted and the data about the force-time and moment-time dependencies are used for training neural networks. The new way of prediction of muscle-tendon forces and moments based on neural networks was tested. Neural networks predicted the muscle forces and moments of healthy children and children with cerebral palsy. The designed method of prediction by neural networks could help to identify the difference between muscle behavior of healthy subjects and diseased subjects.

[1] Buford W. L., Thompson D. E., A system for three-dimensional interactive simulation of hand biomechanics, IEEE TRANS BIOMED ENG., 1987, 34, 444–453 in Google Scholar

[2] Delp S. L., Arnold A. S., Piazza S. J., Graphicsbased modeling and analysis of gait abnormalities, BIOMED MATER ENG., 1998, 8, 227–240 Search in Google Scholar

[3] Schutte L. M., Rodgers M. M., Zajac F. E., Glaser R. M., Improving the efficacy of electrical stimulationinduced leg cycle ergometry: an analysis based on a dynamic musculoskeletal model, IEEE TRANS REHABIL ENG., 1993, 1, 109–125 in Google Scholar

[4] Yamaguchi G. T., Zajac F. E., Restoring unassisted natural gait to paraplegics via functional neuromuscular simulation: a computer simulation study, IEEE TRANS BIOMED ENG., 1990, 37, 886–902 in Google Scholar

[5] Krogt M. M., Delp S. L., Schwartz M. H., How robust is human gait to muscle weakness?, GAIT POSTURE, 2012, 36, 113–119 in Google Scholar

[6] Hollerbach M. J., Flash T., Dynamic interactions between limb segments during planar arm movement, BIOL CYBERN., 1982, 44, 67–77 in Google Scholar

[7] Zajac F. E., Gordon M. E., Determining muscle’s force and action in multi-articular movement, EXERC SPORT SCI REV., 1989, 17, 187–230 10.1249/00003677-198900170-00009Search in Google Scholar

[8] Liu M. M., Herzog W., Savelberg H. H., Dynamic muscle force predictions from EMG: An artificial neural network approach, J ELECTROMYOGR KINESIOL., 1999, 9, 391–400 in Google Scholar

[9] Gage R. J., Hicks R., Gait Analysis in Prosthetics, CLIN PROSTHET ORTHOT., 1989, 9, 17–21 Search in Google Scholar

[10] Janura M., Cabell L., Svoboda Z., Kozáková J., et al., Kinematic analysis of gait in patients with juvenile hallux valgus deformity, J BIOMECH SCI ENG., 2008, 3, 390–398 in Google Scholar

[11] Gioftsos G., Grieve D. W., The use of neural networks to recognize patterns of human movement: gait patterns, CLIN BIOMECH., 1995, 10, 179–183 in Google Scholar

[12] Koktas N. S., Yalabik N., Yavuzer G., Combining neural networks for gait classification, In: Martmnez-Trinidad J. (Ed.), Proceedings of 11th Iberoamerican Congress on Pattern (November 14–17, 2006 Cancun Mexico), Springer, 2006, 381–388 10.1007/11892755_39Search in Google Scholar

[13] Jaraba J., Orrite-Uruñuela C., Pérez J., Roy-Yarza A., Human Recognition by Gait Analysis Using Neural Networks, In: Dorronsoro J. (Ed.), Proceedings of International Conference on Artificial Neural Networks (August 28–30, 2002 Madrid Spain), Springer, 2002, 364–369 in Google Scholar

[14] Lai D. T. H., Begg R. K., Palaniswami M., Computational Intelligence in Gait Research: A Perspective on Current Applications and Future Challenges, IEEE TRANS INF TECHNOL BIOMED., 2009, 13, 687–702 in Google Scholar

[15] Wang L., Tan T., Ning H., Hu W., Automatic gait recognition based on statistical shape analysis, IEEE TRANS IMAGE PROCESS., 2003, 12, 1120–1131 in Google Scholar

[16] Mijailovic N., Gavrilovic M., Rafajlovic S., Gait Phases Recognition from Accelerations and Ground Reaction Forces: Application of Neural Networks, TELFOR J., 2009, 1, 34–36 Search in Google Scholar

[17] Kutilek P., Farkasova B., Prediction of Lower Extremities Movement by Angle-Angle Diagrams and Neural Networks, ACTA BIOENG BIOMECH., 2011, 13, 57–65 Search in Google Scholar

[18] Sepulveda F., Wells D., Vaughan C., A neural network representation of electromyography and joint dynamics in human gait, J BIOMECH., 1993, 26, 101–109 in Google Scholar

[19] Kutilek P., Viteckova S., Svoboda Z., Smrcka P., Prediction of muscle length during walking by neural networks, In: Maga D., Stefek A., Brezina T. (Ed.), Proceedings of 15th International Symposium Mechatronika (December 5–7, 2012 Prague Czech Republic), CTU in Prague, 308–312 Search in Google Scholar

[20] Ounpuu S., Gage J. R., Davis R. B., Threedimensional lower extremity joint kinetics in normal paediatric gait, J PEDIATR ORTHOP., 1991, 11, 341–349 10.1097/01241398-199105000-00012Search in Google Scholar

[21] Yeow C.H., Hamstrings and quadriceps muscle contributions to energy generation and dissipation at the knee joint during stance, swing and flight phases of level running, KNEE, 2013, 20, 100–105 in Google Scholar

[22] Stansfield B. W., Hillman S. J., Hazlewood M. E., Robb J. E., Regression analysis of gait parameters with speed in normal children walking at self-selected speeds, GAIT POSTURE., 2006, 23, 288–294 in Google Scholar

[23] Orendurff M. S., Aiona M. D., Dorociak R. D., Pierce R. A., Length and force of the gastrocnemius and soleus during gait following tendo Achilles lengthenings in children with equinus, GAIT POSTURE., 2002, 15, 130–135 in Google Scholar

[24] Mademli L., Arampatzis A., Morey-Klapsing G., Brüggemann G. P., Effect of ankle joint position and electrode placement on the estimation of the antagonistic moment during maximal plantarflexion, J ELECTROMYOGR KINESIOL., 2004, 14, 591–597 in Google Scholar PubMed

[25] Beale M., Demuth H., Neural Network Toolbox for Use with MatLab, The MathWorks, Natick, 2002 Search in Google Scholar

[26] Hajny O., Farkasova B., A Study of Gait and Posture with the Use of Cyclograms, ACTA POLYTECH., 2010, 50, 48–51 10.14311/1231Search in Google Scholar

[27] Agre P., Computation and Human Experience, Cambridge University Press, New York, 1997 in Google Scholar

[28] Dayan P., Abbott L., Computational and Mathematical Modeling of Neural Systems, MIT Press, Cambridge, 2001 Search in Google Scholar

[29] Wasserman D., Neural computing theory and practice, Van Nostrand Reinhold, New York, 1989 Search in Google Scholar

[30] MacKay D., Information Theory, Inference, and Learning Algorithms, Cambridge University Press, New York, 2003 Search in Google Scholar

[31] Anderson F. C., Pandy M. G, Individual muscle contributions to support in normal walking, GAIT POSTURE, 2003, 17, 159–169 in Google Scholar

[32] Shelburne K. B., Pandy M. G., Anderson F. C., Torry M. R., Pattern of anterior cruciate ligament force in normal walking, J BIOMECH., 2004, 37, 797–805 in Google Scholar PubMed

[33] Wit A., Czaplicki A., Inverse dynamics and artificial neural network applications in gait analysis of the disabled subjects, HUM MOVEMENT., 2008, 9, 93–102 in Google Scholar

[34] Gordona K. E., Sawickia G. S., Ferrisa D. P., Mechanical performance of artificial pneumatic muscles to power an ankle-foot orthosis, J BIOMECH., 2006, 39, 1832–1841 in Google Scholar PubMed

[35] Kao P. C., Lewis C. L., Ferris D. P., Invariant ankle moment patterns when walking with and without a robotic ankle exoskeleton, J BIOMECH., 2010, 43, 203–209 in Google Scholar PubMed PubMed Central

[36] Sutton R., Barto A., Reinforcement Learning: An Introduction, MIT Press, Cambridge, 1998 10.1109/TNN.1998.712192Search in Google Scholar

Published Online: 2013-7-28
Published in Print: 2013-9-1

© 2013 Versita Warsaw

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Downloaded on 21.2.2024 from
Scroll to top button