Human Gait Modeling and Analysis Using a Semi-Markov Process With Ground Reaction Forces

Modeling and evaluation of patients’ gait patterns is the basis for both gait assessment and gait rehabilitation. This paper presents a convenient and real-time gait modeling, analysis, and evaluation method based on ground reaction forces (GRFs) measured by a pair of smart insoles. Gait states are defined based on the foot–ground contact forms of both legs. From the obtained gait state sequence and the duration of each state, the human gait is modeled as a semi-Markov process (SMP). Four groups of gait features derived from the SMP gait model are used for characterizing individual gait patterns. With this model, both the normal gaits of healthy people and the abnormal gaits of patients with impaired mobility are analyzed. Abnormal evaluation indices (AEI) are further proposed for gait abnormality assessment. Gait analysis experiments are conducted on 23 subjects with different ages and health conditions. The results show that gait patterns are successfully obtained and evaluated for normal, age-related, and pathological gaits. The effectiveness of the proposed AEI for gait assessment is verified through comparison with a video-based gait abnormality rating scale.

[1]  W. Marsden.  I and J , 2012 .

[2]  Yangsheng Xu,et al.  Human Abnormal Gait Modeling via Hidden Markov Model , 2007, 2007 International Conference on Information Acquisition.

[3]  Wei-Hsin Liao,et al.  Design and control of a powered knee orthosis for gait assistance , 2013, 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[4]  M. Hanlon,et al.  Real-time gait event detection using wearable sensors. , 2006, Gait & posture.

[5]  K. M. Gill,et al.  Gait assessment for neurologically impaired patients. Standards for outcome assessment. , 1986, Physical therapy.

[6]  Yasuhisa Hasegawa,et al.  Gait support for complete spinal cord injury patient by synchronized leg-swing with HAL , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Michelle Karg,et al.  Clinical Gait Analysis: Comparing Explicit State Duration HMMs Using a Reference-Based Index , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[8]  Hugh Herr,et al.  Exoskeletons and orthoses: classification, design challenges and future directions , 2009, Journal of NeuroEngineering and Rehabilitation.

[9]  Michael H Schwartz,et al.  The Gait Deviation Index: a new comprehensive index of gait pathology. , 2008, Gait & posture.

[10]  K. M. Gill,et al.  Gait Assessment for Neurologically Impaired Patients , 1986 .

[11]  Jinghui Cao,et al.  Control strategies for effective robot assisted gait rehabilitation: the state of art and future prospects. , 2014, Medical engineering & physics.

[12]  Antonello Maruotti,et al.  ESTIMATION OF THE STATIONARY DISTRIBUTION OF A SEMI-MARKOV CHAIN , 2012 .

[13]  L. Schutte,et al.  An index for quantifying deviations from normal gait. , 2000, Gait & posture.

[14]  Hylton B Menz,et al.  Accelerometry: a technique for quantifying movement patterns during walking. , 2008, Gait & posture.

[15]  R. Riener,et al.  Stair ascent and descent at different inclinations. , 2002, Gait & posture.

[16]  Masayoshi Tomizuka,et al.  Gait phase analysis based on a Hidden Markov Model , 2011 .

[17]  Catherine Dehollain,et al.  Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring , 2004, IEEE Transactions on Biomedical Engineering.

[18]  Hongyin Lau,et al.  The reliability of using accelerometer and gyroscope for gait event identification on persons with dropped foot. , 2008, Gait & posture.

[19]  Valentina Agostini,et al.  Segmentation and Classification of Gait Cycles , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[20]  Giancarlo Ferrigno,et al.  A Novel Adaptive, Real-Time Algorithm to Detect Gait Events From Wearable Sensors , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  M. Grasso,et al.  Rehabilitation of Walking With Electromyographic Biofeedback in Foot‐Drop After Stroke , 1994, Stroke.

[22]  Angelo M. Sabatini,et al.  A hidden Markov model-based technique for gait segmentation using a foot-mounted gyroscope , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[23]  Yosuke Kurihara,et al.  Accelerometry-Based Gait Analysis and Its Application to Parkinson's Disease Assessment— Part 2 : A New Measure for Quantifying Walking Behavior , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  M. Tomizuka,et al.  A Gait Monitoring System Based on Air Pressure Sensors Embedded in a Shoe , 2009, IEEE/ASME Transactions on Mechatronics.

[25]  Robert G. Gallager,et al.  Discrete Stochastic Processes , 1995 .

[26]  Jwu-Sheng Hu,et al.  A Kinematic Human-Walking Model for the Normal-Gait-Speed Estimation Using Tri-Axial Acceleration Signals at Waist Location , 2013, IEEE Transactions on Biomedical Engineering.

[27]  Oscar Cordón,et al.  Human Gait Modeling Using a Genetic Fuzzy Finite State Machine , 2012, IEEE Transactions on Fuzzy Systems.

[28]  J. Gage,et al.  Differentiation of idiopathic toe-walking and cerebral palsy. , 1988, Journal of pediatric orthopedics.

[29]  J. F. Yang,et al.  The modified Gait Abnormality Rating Scale for recognizing the risk of recurrent falls in community-dwelling elderly adults. , 1996, Physical therapy.

[30]  Toshiki Kobayashi,et al.  Kinetic Gait Analysis Using a Low-Cost Insole , 2013, IEEE Transactions on Biomedical Engineering.