An individual-specific gait pattern prediction model based on generalized regression neural networks.

Robotics is gaining its popularity in gait rehabilitation. Gait pattern planning is important to ensure that the gait patterns induced by robotic systems are tailored to each individual and varying walking speed. Most research groups planned gait patterns for their robotics systems based on Clinical Gait Analysis (CGA) data. The major problem with the method using the CGA data is that it cannot accommodate inter-subject differences. In addition, CGA data is limited to only one walking speed as per the published data. The objective of this work was to develop an individual-specific gait pattern prediction model for gait pattern planning in the robotic gait rehabilitation systems. The waveforms of lower limb joint angles in the sagittal plane during walking were obtained with a motion capture system. Each waveform was represented and reconstructed by a Fourier coefficient vector which consisted of eleven elements. Generalized regression neural networks (GRNNs) were designed to predict Fourier coefficient vectors from given gait parameters and lower limb anthropometric data. The generated waveforms from the predicted Fourier coefficient vectors were compared to the actual waveforms and CGA waveforms by using the assessment parameters of correlation coefficients, mean absolute deviation (MAD) and threshold absolute deviation (TAD). The results showed that lower limb joint angle waveforms generated by the gait pattern prediction model were closer to the actual waveforms compared to the CGA waveforms.

[1]  T Chau,et al.  A review of analytical techniques for gait data. Part 2: neural network and wavelet methods. , 2001, Gait & posture.

[2]  F. Reynard,et al.  The WalkTrainer—A New Generation of Walking Reeducation Device Combining Orthoses and Muscle Stimulation , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  J. Perry,et al.  Pelvic exercise and gait in hemiplegia. , 1989, Physical therapy.

[4]  M. Hanlon,et al.  Prediction methods to account for the effect of gait speed on lower limb angular kinematics. , 2006, Gait & posture.

[5]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[6]  Seung-Hun Park,et al.  A Gait Rehabilitation and Training System based on Task Specific Repetitive Approach , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[7]  T. Oberg,et al.  Joint angle parameters in gait: reference data for normal subjects, 10-79 years of age. , 1994, Journal of rehabilitation research and development.

[8]  H. Kazerooni,et al.  Biomechanical design of the Berkeley lower extremity exoskeleton (BLEEX) , 2006, IEEE/ASME Transactions on Mechatronics.

[9]  Michael H Schwartz,et al.  The effect of walking speed on the gait of typically developing children. , 2008, Journal of biomechanics.

[10]  Jörg Krüger,et al.  HapticWalker---a novel haptic foot device , 2005, TAP.

[11]  Michael Peshkin,et al.  KineAssist: Design and Development of a Robotic Overground Gait and Balance Therapy Device , 2008, Topics in stroke rehabilitation.

[12]  Robert Riener,et al.  Locomotor training in subjects with sensori-motor deficits: An overview of the robotic gait orthosis lokomat , 2010 .

[13]  S.K. Agrawal,et al.  Robot assisted gait training with active leg exoskeleton (ALEX) , 2009, 2008 2nd IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics.

[14]  J Y Goulermas,et al.  Predicting lower limb joint kinematics using wearable motion sensors. , 2008, Gait & posture.

[15]  JoAnne K. Gronley,et al.  Classification of walking handicap in the stroke population. , 1995, Stroke.

[16]  Christopher L. Vaughan,et al.  Dynamics of human gait , 1992 .

[17]  Luv Rustagi,et al.  Human Gait Recognition Based on Dynamic and Static Features Using Generalized Regression Neural Network , 2009, 2009 Second International Conference on Machine Vision.

[18]  Daniel Vélez Día,et al.  Biomechanics and Motor Control of Human Movement , 2013 .

[19]  R. Riener,et al.  Path Control: A Method for Patient-Cooperative Robot-Aided Gait Rehabilitation , 2010, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[20]  H. Barbeau.  Locomotor Training in Neurorehabilitation: Emerging Rehabilitation Concepts , 2003, Neurorehabilitation and neural repair.

[21]  S. Hesse,et al.  Treadmill Training With Partial Body Weight Support and an Electromechanical Gait Trainer for Restoration of Gait in Subacute Stroke Patients: A Randomized Crossover Study , 2002, Stroke.

[22]  R.B. Davis,et al.  Clinical gait analysis , 1988, IEEE Engineering in Medicine and Biology Magazine.

[23]  Chao Qian,et al.  Population , 1940, State Rankings 2020: A Statistical View of America.

[24]  Xingda Qu,et al.  Subject-specific gait parameters prediction for robotic gait rehabilitation via generalized regression neural network , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[25]  J. Burdick,et al.  Implications of Assist-As-Needed Robotic Step Training after a Complete Spinal Cord Injury on Intrinsic Strategies of Motor Learning , 2006, The Journal of Neuroscience.

[26]  A. Hof.  Scaling gait data to body size , 1996 .

[27]  E K Antonsson,et al.  The frequency content of gait. , 1985, Journal of biomechanics.

[28]  Anirban Misra,et al.  Influence of Walking Speed on Gait Parameters , 2013 .

[29]  Daniel P. Ferris,et al.  Powered lower limb orthoses for gait rehabilitation. , 2005, Topics in spinal cord injury rehabilitation.

[30]  V. Dietz,et al.  Treadmill training of paraplegic patients using a robotic orthosis. , 2000, Journal of rehabilitation research and development.

[31]  D. Kerrigan,et al.  Predicting peak kinematic and kinetic parameters from gait speed. , 2003, Gait & posture.

[32]  Dan Yang,et al.  Application of generalized regression neural network in prediction of cement properties , 2010, 2010 International Conference On Computer Design and Applications.