Extraction and Classification of Human Body Parameters for Gait Analysis

Human gait analysis is considered a new biometric tool for the ability to obtain metrics from the body at a distance. Biometric identifiers have properties that can technologically measure and analyze the characteristics of the human body and can be used as a form of identification and access control for security applications. Recognition through proper interpretation of gait parameters has become a relevant pattern classification problem. This work aims to develop an image processing system, with the use of the Microsoft Kinect sensor, which is capable to extract movement patterns for gait analysis and to present a comparative study of different pattern recognition methods for human identification. The image processing system, developed in C#, allowed the acquisition of three-dimensional data from several volunteers and made it possible to identify the human skeleton and automatically extract the kinetic and kinematic parameters of the body. For data analysis, different classification methods were compared. Among them, the algorithms that presented better performance were probabilistic neural networks, deep neural networks and k-nearest neighbors, with nearly 99% correct recognition rate. The obtained results demonstrate the efficiency of gait analysis as a biometric method. They also show the viability of gait parameter extraction using the Kinect sensor and the good performance of pattern recognition methods applied to the acquired gait kinetic and kinematic parameters.

[1]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  Ricardo J. G. B. Campello,et al.  Comparing Correlation Coefficients as Dissimilarity Measures for Cancer Classification in Gene Expression Data , 2011 .

[4]  Anders Krogh,et al.  Neural Network Ensembles, Cross Validation, and Active Learning , 1994, NIPS.

[5]  R. Prathiba,et al.  Multiple Output Radial Basis Function Neural Network with Reduced Input Features for On-line Estimation of Available Transfer Capability , 2016 .

[6]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[7]  Richard Baker,et al.  The history of gait analysis before the advent of modern computers. , 2007, Gait & posture.

[8]  Daniel Graupe DEEP LEARNING NEURAL NETWORKS: DESIGN AND CASE STUDIES , 2016 .

[9]  Cheng-Yuan Liou,et al.  Autoencoder for words , 2014, Neurocomputing.

[10]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[11]  Alexandre C. Moreira,et al.  Evaluation of Pattern Recognition Algorithms for Applications on Power Factor Compensation , 2017, Journal of Control, Automation and Electrical Systems.

[12]  Ana Carolina Lorena Investigação de estratégias para a geração de máquinas de vetores de suporte multiclasses , 2006 .

[13]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[15]  David A. Winter,et al.  Biomechanics and Motor Control of Human Movement , 1990 .

[16]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[17]  Carlos Zerpa,et al.  The Use of Microsoft Kinect for Human Movement Analysis , 2015 .

[18]  Marco Grangetto,et al.  Human Classification Using Gait Features , 2014, BIOMET.

[19]  B. Nigg,et al.  Calculation of vertical ground reaction force estimates during running from positional data. , 1991, Journal of biomechanics.

[20]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[21]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[22]  C. Oatis,et al.  Kinesiology: The Mechanics and Pathomechanics of Human Movement , 2003 .

[23]  Guilherme A. S. Pereira,et al.  A Probabilistic Approach for Fusing People Detectors , 2015 .

[24]  Thomas Villmann,et al.  Optimization of Statistical Evaluation Measures for Classification by Median Learning Vector Quantization , 2016, WSOM.

[25]  Moataz Eltoukhy,et al.  Improved kinect-based spatiotemporal and kinematic treadmill gait assessment. , 2017, Gait & posture.

[26]  D. Gordon E. Robertson,et al.  Research Methods in Biomechanics , 2004 .

[27]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[28]  Michael W. Whittle,et al.  Gait Analysis: An Introduction , 1986 .

[29]  James J. Little,et al.  Biometric Gait Recognition , 2003, Advanced Studies in Biometrics.

[30]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[31]  Harpreet Kaur,et al.  Gene selection for tumor classification using resilient backpropagation neural network , 2016, 2016 2nd International Conference on Advances in Computing, Communication, & Automation (ICACCA) (Fall).

[32]  Melvyn Roerdink,et al.  Kinematic Validation of a Multi-Kinect v2 Instrumented 10-Meter Walkway for Quantitative Gait Assessments , 2015, PloS one.

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  Ana L. N. Fred,et al.  Pattern Recognition Applications and Methods - International Conference, ICPRAM 2013 Barcelona, Spain, February 15-18, 2013 Revised Selected Papers , 2015, ICPRAM.

[35]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[36]  Stephen Grossberg,et al.  Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks , 1973 .

[37]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[38]  Kuo-Yan Wang,et al.  Applying Back Propagation Neural Networks in the Prediction of Management Associate Work Retention for Small and Medium Enterprises , 2016 .

[39]  Mahmut Ozer,et al.  EEG signals classification using the K-means clustering and a multilayer perceptron neural network model , 2011, Expert Syst. Appl..

[40]  Claudia Linnhoff-Popien,et al.  Gait Recognition with Kinect , 2012 .

[41]  Audun Jøsang Generalising Bayes' theorem in subjective logic , 2016, 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[42]  Geoffrey E. Hinton,et al.  Neighbourhood Components Analysis , 2004, NIPS.

[43]  Ricardo Matsumura de Araújo,et al.  Towards skeleton biometric identification using the microsoft kinect sensor , 2013, SAC '13.

[44]  Shuo Xu,et al.  Bayesian Naïve Bayes classifiers to text classification , 2018, J. Inf. Sci..

[45]  Leif E. Peterson K-nearest neighbor , 2009, Scholarpedia.

[47]  Ming Yang,et al.  Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine , 2016, Simul..

[48]  Carl Heneghan,et al.  Overdiagnosis: what it is and what it isn’t , 2018, BMJ Evidence-Based Medicine.

[49]  Sandhya Samarasinghe,et al.  Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition , 2006 .

[50]  Francisco Javier Ferrández Pastor,et al.  A vision based proposal for classification of normal and abnormal gait using RGB camera , 2016, J. Biomed. Informatics.

[51]  Honghai Liu,et al.  Fusion hand gesture segmentation and extraction based on CMOS sensor and 3D sensor , 2017 .

[52]  Marco Grangetto,et al.  Kinect-Based Gait Analysis for People Recognition Over Time , 2017, ICIAP.

[53]  Thomas Villmann,et al.  Learning vector quantization classifiers for ROC-optimization , 2016, Computational Statistics.

[54]  Jean-Pierre Demailly Analyse numérique et équations différentielles , 2016 .

[55]  David D. Lewis,et al.  Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval , 1998, ECML.

[56]  Ana L. N. Fred,et al.  Towards View-point Invariant Person Re-identification via Fusion of Anthropometric and Gait Features from Kinect Measurements , 2017, VISIGRAPP.

[57]  Dimitris N. Metaxas,et al.  Human Gait Recognition , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[58]  Fabio Tozeto Ramos,et al.  Unsupervised clustering of people from ‘skeleton’ data , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[59]  D. Altman,et al.  Statistics Notes: Diagnostic tests 1: sensitivity and specificity , 1994 .

[60]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[61]  Shuihua Wang,et al.  Tea category identification based on optimal wavelet entropy and weighted k-Nearest Neighbors algorithm , 2018, Multimedia Tools and Applications.

[62]  Rezaul Begg,et al.  Overview of movement analysis and gait features , 2006 .

[63]  Fabio Martínez,et al.  ANÁLISE DO VÍDEO PARA O ESTIMATION DO MOVIMENTO HUMANO: UMA REVISÃO , 2009 .

[64]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[65]  Joseph Hamill,et al.  Biomechanical Basis of Human Movement , 1995 .

[66]  Oscar Castillo,et al.  A Neural Network with a Learning Vector Quantization Algorithm for Multiclass Classification Using a Modular Approach , 2014, WCSC.

[67]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[68]  Fabio Martínez,et al.  VIDEO ANALYSIS FOR ESTIMATION OF THE HUMAN MOVEMENT: A REVISION , 2009 .

[69]  C. V. D. Malsburg,et al.  Frank Rosenblatt: Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms , 1986 .

[70]  Eric Lengyel,et al.  Mathematics for 3D Game Programming and Computer Graphics, Second Edition , 2001 .

[71]  Panu Somervuo,et al.  Self-organizing maps of symbol strings , 1998, Neurocomputing.

[72]  Anthony J. Blazevich,et al.  Sports Biomechanics: The Basics: Optimising Human Performance , 2007 .

[73]  J. Tavares,et al.  Análise da marcha baseada numa correlação multifactorial , 2009 .

[74]  Buse Melis Ozyildirim,et al.  One pass learning for generalized classifier neural network , 2016, Neural Networks.

[75]  E Knutsson,et al.  An analysis of Parkinsonian gait. , 1972, Brain : a journal of neurology.

[76]  F. Cajori,et al.  Mathematical Principles of Natural Philosophy and his System of the World , 1935 .

[77]  Ikhlas Abdel-Qader,et al.  A PNN- Jensen-Bregman Divergence symmetrization for a WLAN Indoor Positioning System , 2016, 2016 IEEE International Conference on Electro Information Technology (EIT).

[78]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .

[79]  Marimuthu Palaniswami,et al.  Computational intelligence for movement sciences : neural networks and other emerging techniques , 2006 .

[80]  Marcos André Gonçalves,et al.  BROOF: Exploiting Out-of-Bag Errors, Boosting and Random Forests for Effective Automated Classification , 2015, SIGIR.

[81]  D. Haro Laboratorio de análisis de marcha y movimiento , 2014 .

[82]  Joseph Hamill,et al.  Comprar Research Methods In Biomechanics | Robertson, G. | 9780736093408 | Human Kinetics , 2013 .

[83]  Kfir Y. Levy,et al.  k*-Nearest Neighbors: From Global to Local , 2017, NIPS.

[84]  Michael Biehl,et al.  Learning vector quantization: The dynamics of winner-takes-all algorithms , 2006, Neurocomputing.

[85]  Fevzullah Temurtas,et al.  A comparative study on thyroid disease diagnosis using neural networks , 2009, Expert Syst. Appl..