A study on human gait analysis

Human gait is one of the most important biometric which has so far been neglected for use in medical diagnostics. In this paper, we make a feasibility study on human gait acquired from a wearable sensor based biometric suit called as Intelligent Gait Oscillation Detector (IGOD). This suit measures simultaneous gait oscillation from eight major joints (two knees, two hips, two elbows and two shoulders) of a human body. Techniques for analyzing and understanding the human gait patterns were developed. Variance in the gait oscillation was studied with respect to gait speed varying from 3km/hr to 5km/hr. Gender variance (male/female) gait oscillation has also been studied. A comprehensive analysis on human gait affected by knee joint movement and hip joint oscillation has been addressed with the arm swing effects. This analysis will provide us with an insight on human bipedal locomotion and its stability. We plan to create a repository of human gait oscillations which could extensively be analyzed for person identification and detecting walking problems in patients, which is detection of disease in the medical field.

[1]  Yangsheng Xu,et al.  Gait Modeling for Human Identification , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[2]  Roozbeh Jafari,et al.  Human identification by gait analysis , 2008, HealthNet '08.

[3]  Gerhard Tröster,et al.  Quantifying Gait Similarity: User Authentication and Real-World Challenge , 2009, ICB.

[4]  Ju-Jang Lee,et al.  Estimation of Walking Behavior Using Accelerometers in Gait Rehabilitation , 2002 .

[5]  Se Jin Park,et al.  Foot Step Based Person Identification Using Histogram Similarity and Wavelet Decomposition , 2008, 2008 International Conference on Information Security and Assurance (isa 2008).

[6]  Damjan Zazula,et al.  Gait identification using cumulants of accelerometer data , 2009 .

[7]  Einar Snekkenes,et al.  Gait Authentication and Identification Using Wearable Accelerometer Sensor , 2007, 2007 IEEE Workshop on Automatic Identification Advanced Technologies.

[8]  Soumik Mondal,et al.  A Framework for Synthesis of Human Gait Oscillation Using Intelligent Gait Oscillation Detector (IGOD) , 2010, IC3.

[9]  Patrick Bours,et al.  Improved Cycle Detection for Accelerometer Based Gait Authentication , 2010, 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[10]  Yasushi Makihara,et al.  Performance evaluation of gait recognition using the largest inertial sensor-based gait database , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[11]  Gora Chand Nandi,et al.  Gait Based Personal Identification System Using Rotation Sensor , 2012 .

[12]  Hiroshi Shimizu,et al.  Self-organized control of bipedal locomotion by neural oscillators in unpredictable environment , 1991, Biological Cybernetics.

[13]  S. Marocco,et al.  Classification of plantar pressure and heel acceleration patterns using neural networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..