From neuromuscular activation to end-point locomotion: An artificial neural network-based technique for neural prostheses.

Neuroprostheses, implantable or non-invasive ones, are promising techniques to enable paralyzed individuals with conditions, such as spinal cord injury or spina bifida (SB), to control their limbs voluntarily. Direct cortical control of invasive neuroprosthetic devices and robotic arms have recently become feasible for primates. However, little is known about designing non-invasive, closed-loop neuromuscular control strategies for neural prostheses. Our goal was to investigate if an artificial neural network-based (ANN-based) model for closed-loop-controlled neural prostheses could use neuromuscular activation recorded from individuals with impaired spinal cord to predict their end-point gait parameters (such as stride length and step width). We recruited 12 persons with SB (5 females and 7 males) and collected their neuromuscular activation and end-point gait parameters during overground walking. Our results show that the proposed ANN-based technique can achieve a highly accurate prediction (e.g., R-values of 0.92-0.97, ANN (tansig+tansig) for single composition of data sets) for altered end-point locomotion. Compared to traditional robust regression, this technique can provide up to 80% more accurate prediction. Our results suggest that more precise control of complex neural prostheses during locomotion can be achieved by engaging neuromuscular activity as intrinsic feedback to generate end-point leg movement. This ANN-based model allows a seamless incorporation of neuromuscular activity, detected from paralyzed individuals, to adaptively predict their altered gait patterns, which can be employed to provide closed-loop feedback information for neural prostheses.

[1]  B. Bril,et al.  Head Coordination as a Means to Assist Sensory Integration in Learning to Walk , 1998, Neuroscience & Biobehavioral Reviews.

[2]  Dejan Popović,et al.  Automatic vs hand-controlled walking of paraplegics. , 2003, Medical engineering & physics.

[3]  C L Vaughan,et al.  A neural network representation of electromyography and joint dynamics in human gait. , 1993, Journal of biomechanics.

[4]  A. C. Cheng.  Amplifying Embedded System Efficiency via Automatic Instruction Fusion on a Post-Manufacturing Reconfigurable Architecture Platform , 2008, ISQED 2008.

[5]  Gary S. Tyson,et al.  High-quality ISA synthesis for low-power cache designs in embedded microprocessors , 2006, IBM J. Res. Dev..

[6]  Shigeto Furukawa,et al.  Auditory cortical responses in the cat to sounds that produce spatial illusions , 1999, Nature.

[7]  M R Pierrynowski,et al.  Enhancing the ability of gait analyses to differentiate between groups: scaling gait data to body size. , 2001, Gait & posture.

[8]  M. Laubach,et al.  Cortical ensemble activity increasingly predicts behaviour outcomes during learning of a motor task , 2022 .

[9]  F Leurs,et al.  A dynamic recurrent neural network for multiple muscles electromyographic mapping to elevation angles of the lower limb in human locomotion , 2003, Journal of Neuroscience Methods.

[10]  金小刚,et al.  A hybrid neural network model for consciousness , 2004 .

[11]  Guy Cheron,et al.  Recognition of the physiological actions of the triphasic EMG pattern by a dynamic recurrent neural network , 2007, Neuroscience Letters.

[12]  Byron M. Yu,et al.  A high-performance brain–computer interface , 2006, Nature.

[13]  Davide Cattaneo,et al.  Head control: volitional aspects of rehabilitation training in patients with multiple sclerosis compared with healthy subjects. , 2005, Archives of physical medicine and rehabilitation.

[14]  Martin T. Hagan,et al.  Neural network design , 1995 .

[15]  S. Jonic,et al.  Three machine learning techniques for automatic determination of rules to control locomotion , 1999, IEEE Transactions on Biomedical Engineering.

[16]  S. D. Prentice,et al.  Simple artificial neural network models can generate basic muscle activity patterns for human locomotion at different speeds , 1998, Experimental Brain Research.

[17]  A. Krogh.  What are artificial neural networks? , 2008, Nature Biotechnology.

[18]  Dawn M. Taylor,et al.  Direct Cortical Control of 3D Neuroprosthetic Devices , 2002, Science.

[19]  D B Chaffin,et al.  A back-propagation neural network model of lumbar muscle recruitment during moderate static exertions. , 1995, Journal of biomechanics.

[20]  Simon Haykin,et al.  Classification of radar clutter using neural networks , 1991, IEEE Trans. Neural Networks.

[21]  T Laurell,et al.  Classification of motor commands using a modified self-organising feature map. , 2005, Medical engineering & physics.

[22]  Zhanpeng Jin,et al.  Predicting end-point locomotion from neuromuscular activities of people with spina bifida: A self-organizing and adaptive technique for future implantable and non-invasive neural prostheses , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  Gary S. Tyson,et al.  An energy efficient instruction set synthesis framework for low power embedded system designs , 2005, IEEE Transactions on Computers.

[24]  D. Winter,et al.  Quantitative assessment of co-contraction at the ankle joint in walking. , 1985, Electromyography and clinical neurophysiology.

[25]  Monica A. Daley,et al.  A Physiologist's Perspective on Robotic Exoskeletons for Human Locomotion , 2007, Int. J. Humanoid Robotics.

[26]  V. Dietz,et al.  Degradation of neuronal function following a spinal cord injury: mechanisms and countermeasures. , 2004, Brain : a journal of neurology.

[27]  Geoffrey E. Hinton,et al.  Self-organizing neural network that discovers surfaces in random-dot stereograms , 1992, Nature.

[28]  M. Hahn.  Feasibility of estimating isokinetic knee torque using a neural network model. , 2007, Journal of biomechanics.

[29]  P. Hodges,et al.  A comparison of computer-based methods for the determination of onset of muscle contraction using electromyography. , 1996, Electroencephalography and clinical neurophysiology.

[30]  Li-Shan Chou,et al.  Neural network estimation of balance control during locomotion. , 2005, Journal of biomechanics.

[31]  Xing Xu,et al.  A therizinosauroid dinosaur with integumentary structures from China , 1999, Nature.

[32]  Jerald D. Kralik,et al.  Real-time prediction of hand trajectory by ensembles of cortical neurons in primates , 2000, Nature.

[33]  Max Q.-H. Meng,et al.  An efficient neural network approach to dynamic robot motion planning , 2000, Neural Networks.

[34]  Beverly D Ulrich,et al.  Lateral stabilization improves walking in people with myelomeningocele. , 2008, Journal of biomechanics.

[35]  José Carlos Príncipe,et al.  An analysis of the gamma memory in dynamic neural networks , 1994, IEEE Trans. Neural Networks.

[36]  Masayoshi Kubo,et al.  Early changes in muscle activation patterns of toddlers during walking. , 2006, Infant behavior & development.

[37]  G. Gottlieb,et al.  A Computational Model of the Simplest Motor Program. , 1993, Journal of motor behavior.

[38]  Zhanpeng Jin,et al.  ImplantBench: Characterizing and Projecting Representative Benchmarks for Emerging Bioimplantable Computing , 2008, IEEE Micro.

[39]  Masayoshi Kubo,et al.  Emergence of neuromuscular patterns during walking in toddlers with typical development and with Down syndrome. , 2009, Human movement science.

[40]  L D Edmonds,et al.  Prevalence of spina bifida at birth--United States, 1983-1990: a comparison of two surveillance systems. , 1996, MMWR. CDC surveillance summaries : Morbidity and mortality weekly report. CDC surveillance summaries.

[41]  G. Snoek,et al.  Use of the NESS Handmaster to restore handfunction in tetraplegia: clinical experiences in ten patients , 2000, Spinal Cord.

[42]  Hermann Ney,et al.  On the Estimation of 'Small' Probabilities by Leaving-One-Out , 1995, IEEE Trans. Pattern Anal. Mach. Intell..