Fuzzy Logic Based Gait Classification for Hemiplegic Patients

In this study a fuzzy logic classification system was used first to discriminate healthy subjects from patients rather than classifying those using Brunnstrom stages. Decision making was performed in two stages: feature extraction of gait signals and the fuzzy logic classification system which is used Tsukamato-type inference method. According to our signal feature extraction studies, we focused on temporal events and symetrical features of gait signal. Developed system has six inputs while four of them for temporal features evaluation rule block and two of them symmetrical features evaluation rule block. Our simulation test results showed that proposed system classify correctly 100% of subjects as patient and healthy elderly. The correlation coefficient was found 0.85 for classification to subjects to correct Brunnstrom stages. The results show that classifying patients becomes increasingly difficult linearly according to hemiplegia's severity.

[1]  F. Prince,et al.  Symmetry and limb dominance in able-bodied gait: a review. , 2000, Gait & posture.

[2]  J R Morris,et al.  Accelerometry--a technique for the measurement of human body movements. , 1973, Journal of biomechanics.

[3]  Rudolf Kruse,et al.  Obtaining interpretable fuzzy classification rules from medical data , 1999, Artif. Intell. Medicine.

[4]  J. Bussmann,et al.  Analysis and decomposition of signals obtained by thigh-fixed uni-axial accelerometry during normal walking , 2000, Medical and Biological Engineering and Computing.

[5]  K. Aminian,et al.  Temporal feature estimation during walking using miniature accelerometers: an analysis of gait improvement after hip arthroplasty , 1999, Medical & Biological Engineering & Computing.

[6]  Elif Derya Übeyli,et al.  Application of adaptive neuro-fuzzy inference system for detection of electrocardiographic changes in patients with partial epilepsy using feature extraction , 2004, Expert Syst. Appl..

[7]  A. L. Evans,et al.  Recording accelerations in body movements , 2006, Medical and Biological Engineering and Computing.

[8]  David Roden,et al.  Automatic detection of distorted plethysmogram pulses in neonates and paediatric patients using an adaptive-network-based fuzzy inference system , 2002, Artif. Intell. Medicine.

[9]  A. Leardini,et al.  Data management in gait analysis for clinical applications. , 1998, Clinical biomechanics.

[10]  B. Nigg,et al.  Use of force platform variables to quantify the effects of chiropractic manipulation on gait symmetry. , 1987, Journal of manipulative and physiological therapeutics.

[11]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[12]  T. P. Andriacchi,et al.  Clinical applications of gait analysis , 1993 .

[13]  Jodie Usher,et al.  A Fuzzy Logic‐Controlled Classifier for Use in Implantable Cardioverter Defibrillators , 1999, Pacing and clinical electrophysiology : PACE.

[14]  M. Akay,et al.  Discrimination of walking patterns using wavelet-based fractal analysis , 2002, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  S. Morita,et al.  Gait analysis of hemiplegic patients by measurement of ground reaction force. , 1995, Scandinavian journal of rehabilitation medicine.

[16]  H M Baum,et al.  The National Survey of Stroke. Survival and prevalence. , 1981, Stroke.

[17]  H Prade,et al.  An introduction to fuzzy systems. , 1998, Clinica chimica acta; international journal of clinical chemistry.

[18]  Elif Derya Übeyli,et al.  Adaptive neuro-fuzzy inference systems for analysis of internal carotid arterial Doppler signals , 2005, Comput. Biol. Medicine.

[19]  Elif Derya Übeyli,et al.  Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems , 2004, Comput. Biol. Medicine.