One symbolic (rule-based inductive learning) and one connectionist (neural network) machine learning technique were used to reconstruct muscle activation patterns from kinematic data measured during normal human walking at several speeds. The activation patterns (or desired outputs) consisted of surface electromyographic (EMG) signals from the semitendinosus and vastus medialis muscles. The inputs consisted of flexion and extension angles measured at the hip and knee of the ipsilateral leg, their first and second derivatives, and bilateral foot contact information. The training set consisted of data from six trials, at two different speeds. The testing set consisted of data from two additional trials (one at each speed), which were not in the training set. It was possible to reconstruct the muscular activation at both speeds using both techniques. Timing of the reconstructed signals was accurate. The integrated value of the activation bursts was less accurate. The neural network gave a continuous output, whereas the rule-based inductive learning rule tree gave a quantised activation level. The advantage of rule-based inductive learning was that the rules used were both explicit and comprehensible, whilst the rules used by the neural network were implicit within its structure and not easily comprehended. The neural network was able to reconstruct the activation patterns of both muscles from one network, whereas two separate rule sets were needed for the rule-based technique. It is concluded that machine learning techniques, in comparison to explicit inverse muscular skeletal models, show good promise in modelling nearly cyclic movements such as locomotion at varying walking speeds. However, they do not provide insight into the biomechanics of the system, because they are not based on the biomechanical structure of the system.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Anderson JR (1980) Cognitive psychology and its implications. Freeman, San Francisco.
Arendt-Nielsen L, Sinkjær T, Nielsen J, Kallesoe K (1991) Electromyographic patterns and knee joint kinematics during walking at various speeds. J Electromyogr Kinesiol 1:89–95
Bussel B, Roby-Brami A, Azouvi PH, Biraben A, Yakovleff A, Held JP (1988) Myoclonus in a patient with spinal cord transection: possible involvement of the spinal stepping generator. Brain 111:1235–1245
Clark P (1990) Machine learning: techniques and recent developments. Research memorandum TIRM-90–041, Turing Institute, Glasgow
Craig JJ (1986) Introduction to robotics. Addison-Wesley, Reading, Mass
Crowninshield RD, Brand RA (1981) A physiologically based criterion of muscle force prediction in locomotion. J Biomech 14:793–801
Davids K, Myers C (1990) The role of tacit knowledge in human skill performance. J Hum Movement Stud 19:273–288
Davy DT, Audu ML (1987) A dynamic optimization technique for predicting muscle forces in the swing phase of gait. J Biomech 20:187–201
Grillner S (1975) Locomotion in vertebrates: central mechanisms and reflex intervention. Physiol Rev 55:247–304
Hatze H (1984) Quantitative analysis, synthesis and optimization of human locomotion. Hum Movement Sci 3:5–25
Kirkwood CA, Andrews BJ, Mowforth P (1989) Automatic detection of gait events: a case study using inductive learning techniques. J Biomed Eng 11:511–516
Koopman HFJM (1989) The three-dimensional analysis and prediction of human walking. Ph. D. thesis, University of Twente, The Netherlands
Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4–22
Michalski RS, Chilausky RL (1980) Knowledge acquisition by encoding expert rules versus computer induction from examples. Int J Man Mach Stud 12:63–87
Mingers J (1989) An empirical comparison of pruning methods for decision tree induction. Mach Learning 4:227–243
Mooney RJ (1990) Backpropagation versus learning decision trees. Neural Network Rev 4:84–85
Patriarco AG, Mann RW, Simons SR, Mansour JM (1981) An evaluation of the approaches of optimization models in the prediction of muscle forces during human gait. J Biomech 14:513–525
Rumelhart DE, McClelland JL (1986) Explorations in the microstructure of cognition, vol 1. Cambridge, Mass
Sethi IK, Sarvarayudu GPR (1982) Hierarchical classifier design using mutual information. IEEE Trans Pattern Anal Mach Intell 4:441–445
Shavlik JW, Mooney RJ, Towell G (1991) Symbolic and neural learning algorithms — an experimental comparison. Mach Learning 6:111–143
Weiss SM, Kapouleas I (1989) An empirical comparison of pattern recognition, neural nets and machine learning classification methods. Proceedings of the 11th International Joint Conference on Artificial Intelligence, Detroit, Mich, pp 688–693
Willis MJ, De Massimo C, Montague GA, Tham MT, Morris AJ (1990) Solving process engineering problems using artificial neural networks. In: McGhee J, Grimble MJ, Mowforth P (eds) Knowledge-based systems for industrial control. (IEE control engineering series 44). Peregrinus, London pp 34–46
Yamaguchi GT, Zajac FE (1990) Restoring unassisted natural gait to paraplegics via functional neuromuscular stimulation: a computer simulation study. IEEE Trans Biomed Eng 37:886–902
Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353
About this article
Cite this article
Heller, B.W., Veltink, P.H., Rijkhoff, N.J.M. et al. Reconstructing muscle activation during normal walking: a comparison of symbolic and connectionist machine learning techniques. Biol. Cybern. 69, 327–335 (1993). https://doi.org/10.1007/BF00203129
- Activation Pattern
- Machine Learning Technique
- Vastus Medialis
- Cyclic Movement
- Muscle Activation Pattern