An Automated Classification of Pathological Gait Using Unobtrusive Sensing Technology

This paper integrates an unobtrusive and affordable sensing technology with machine learning methods to discriminate between healthy and pathological gait patterns as a result of stroke or acquired brain injury. A feature analysis is used to identify the role of each body part in separating pathological patterns from healthy patterns. Gait features, including the orientations of the hips and spine (trunk), shoulders and neck (upper limb), knees and ankles (lower limb), are calculated during walking based on Kinect skeletal tracking sequences. Sequences of these features during three types of walking conditions were examined: 1) walking at self-pace (WSP); 2) walking at distracted (WD); and 3) walking at fast pace (WFP). Two machine learning approaches, an instance-based discriminative classifier ( $k$ -nearest neighbor) and a dynamical generative classifier (using Gaussian Process Latent Variable Model), are examined to distinguish between healthy and pathological gaits. Nested cross validation is implemented to evaluate the performance of the two classifiers using three metrics: F1-score, macro-averaged error, and micro-averaged error. The discriminative model outperforms the generative model in terms of the F1-score (discriminative: WSP > 0.95, WD > 0.96, and WFP > 0.95 and generative: WSP > 0.87, WD > 0.85, and WFP > 0.68) and macro-averaged error (discriminative: WSP < 0.08, WD < 0.1, and WFP < 0.09 and generative: WSP < 0.11, WD < 0.12, and WFP < 0.14). The dynamical generative model on the other hand obtains better micro-averaged error (discriminative: WSP < 0.37, WD < 0.3, and WFP < 0.35 and generative: WSP < 0.15, WD < 0.2, and WFP < 0.2). The high-dimensional gait features are divided into five subsets: lower limb, upper limb, trunk, velocity, and acceleration. An instance-based feature analysis method (ReliefF) is used to assign weights to each subset of features according to its discriminatory power. The feature analysis establishes the most informative features (upper limb, lower limb, and trunk) for identifying pathological gait.

[1]  Marimuthu Palaniswami,et al.  Support vector machines for automated gait classification , 2005, IEEE Transactions on Biomedical Engineering.

[2]  Alex Mihailidis,et al.  Vision-based approach for long-term mobility monitoring: Single case study following total hip replacement. , 2014, Journal of rehabilitation research and development.

[3]  Rachid Aissaoui,et al.  New Accelerometric Method to Discriminate Between Asymptomatic Subjects and Patients With Medial Knee Osteoarthritis During 3-D Gait , 2008, IEEE Transactions on Biomedical Engineering.

[4]  C. Marsden,et al.  Human walking and higher‐level gait disorders, particularly in the elderly , 1993, Neurology.

[5]  L. Snyder-Mackler,et al.  Interrater reliability of videotaped observational gait-analysis assessments. , 1991, Physical therapy.

[6]  Hossein Mousavi Hondori,et al.  A Review on Technical and Clinical Impact of Microsoft Kinect on Physical Therapy and Rehabilitation , 2014, Journal of medical engineering.

[7]  Vladimir Pavlovic,et al.  Learning Switching Linear Models of Human Motion , 2000, NIPS.

[8]  Lawrence Carin,et al.  Infinite Hidden Markov Models for Unusual-Event Detection in Video , 2008, IEEE Transactions on Image Processing.

[9]  Yiming Yang,et al.  An Evaluation of Statistical Approaches to Text Categorization , 1999, Information Retrieval.

[10]  W. Kearns,et al.  Path tortuosity in everyday movements of elderly persons increases fall prediction beyond knowledge of fall history, medication use, and standardized gait and balance assessments. , 2012, Journal of the American Medical Directors Association.

[11]  Vinay Saraph,et al.  Determination of gait patterns in children with cerebral palsy using cluster analysis , 1999 .

[12]  B. Bloem,et al.  Neurological gait disorders in elderly people: clinical approach and classification , 2007, The Lancet Neurology.

[13]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, ACM Trans. Graph..

[14]  Jesse Hoey,et al.  Automated Detection of Unusual Events on Stairs , 2006, The 3rd Canadian Conference on Computer and Robot Vision (CRV'06).

[15]  B. Salzman.  Gait and balance disorders in older adults. , 2010, American family physician.

[16]  Shaogang Gong,et al.  Video behaviour profiling and abnormality detection without manual labelling , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[17]  J R Davids,et al.  Common gait abnormalities of the knee in cerebral palsy. , 1993, Clinical orthopaedics and related research.

[18]  Neil D. Lawrence,et al.  Learning for Larger Datasets with the Gaussian Process Latent Variable Model , 2007, AISTATS.

[19]  Kade Paterson,et al.  Quantifying Individual Components of the Timed Up and Go Using the Kinect in People Living With Stroke , 2015, Neurorehabilitation and neural repair.

[20]  Alex Mihailidis,et al.  Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters. , 2016, Medical engineering & physics.

[21]  M. P. Murray.  Gait as a total pattern of movement. , 1967, American journal of physical medicine.

[22]  Mitja Lustrek,et al.  Fall Detection and Activity Recognition with Machine Learning , 2009, Informatica.

[23]  Alex Mihailidis,et al.  3D Human Motion Analysis to Detect Abnormal Events on Stairs , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.

[24]  Marimuthu Palaniswami,et al.  Automatic Recognition of Gait Patterns Exhibiting Patellofemoral Pain Syndrome Using a Support Vector Machine Approach , 2009, IEEE Transactions on Information Technology in Biomedicine.

[25]  P. Bonato,et al.  Wearable sensors/systems and their impact on biomedical engineering , 2003, IEEE Engineering in Medicine and Biology Magazine.

[26]  Songbo Tan,et al.  Neighbor-weighted K-nearest neighbor for unbalanced text corpus , 2005, Expert Syst. Appl..

[27]  Chek Tien Tan,et al.  Assessing the Kinect's Capabilities to Perform a Time-Based Clinical Test for Fall Risk Assessment in Older People , 2014, ICEC.

[28]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..

[29]  Ennio Gambi,et al.  Kinect as a Tool for Gait Analysis: Validation of a Real-Time Joint Extraction Algorithm Working in Side View , 2015, Sensors.

[30]  David J. Fleet,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Gaussian Process Dynamical Model , 2007 .

[31]  Prajakta S. Kalekar.  Time series Forecasting using Holt-Winters Exponential Smoothing , 2004 .

[32]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[33]  Marjorie Skubic,et al.  Evaluation of an inexpensive depth camera for in-home gait assessment , 2011, J. Ambient Intell. Smart Environ..

[34]  K. Webster,et al.  The application of support vector machines for detecting recovery from knee replacement surgery using spatio-temporal gait parameters. , 2009, Gait & posture.

[35]  Herbert Witte,et al.  Classification of equinus in ambulatory children with cerebral palsy-discrimination between dynamic tightness and fixed contracture. , 2004, Gait & posture.

[36]  D E Krebs,et al.  Reliability of observational kinematic gait analysis. , 1985, Physical therapy.

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

[38]  David J. Fleet,et al.  3D People Tracking with Gaussian Process Dynamical Models , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[39]  Misha Pavel,et al.  Unobtrusive and Ubiquitous In-Home Monitoring: A Methodology for Continuous Assessment of Gait Velocity in Elders , 2010, IEEE Transactions on Biomedical Engineering.

[40]  Richard Simon,et al.  Bias in error estimation when using cross-validation for model selection , 2006, BMC Bioinformatics.

[41]  Mark S. Nixon,et al.  Automated Markerless Analysis of Human Gait Motion for Recognition and Classification , 2011 .

[42]  Tae-Seong Kim,et al.  Depth video-based gait recognition for smart home using local directional pattern features and hidden Markov model , 2014 .

[43]  Jasper Snoek,et al.  Lower body motion analysis to detect falls and near falls on stairs , 2015 .

[44]  R. Nevatia,et al.  Online, Real-time Tracking and Recognition of Human Actions , 2008, 2008 IEEE Workshop on Motion and video Computing.

[45]  Subashan Perera,et al.  Improvements in Speed-Based Gait Classifications Are Meaningful , 2007, Stroke.

[46]  Nooritawati Md Tahir,et al.  Parkinson Disease gait classification based on machine learning approach , 2012 .

[47]  Tao Liu,et al.  Gait Analysis Using Wearable Sensors , 2012, Sensors.

[48]  Alex Mihailidis,et al.  Automated classification of pathological gait after stroke using ubiquitous sensing technology , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[49]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data , 2003, NIPS.

[50]  Oded Maron,et al.  Multiple-Instance Learning for Natural Scene Classification , 1998, ICML.

[51]  Shehroz S. Khan,et al.  Towards the detection of unusual temporal events during activities using HMMs , 2012, UbiComp '12.

[52]  Antonio Arauzo-Azofra,et al.  A feature set measure based on Relief , 2004 .

[53]  Yang Yang,et al.  Reliability and Validity of Kinect RGB-D Sensor for Assessing Standing Balance , 2014, IEEE Sensors Journal.

[54]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[55]  Trevor Darrell,et al.  Discriminative Gaussian process latent variable model for classification , 2007, ICML '07.

[56]  G K Rose.  Clinical gait assessment: a personal view. , 1983, Journal of medical engineering & technology.

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

[58]  A.J. Salazar,et al.  Novel approach for spastic hemiplegia classification through the use of support vector machines , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[59]  Alex Mihailidis,et al.  Mixture-Model Clustering of Pathological Gait Patterns , 2017, IEEE Journal of Biomedical and Health Informatics.

[60]  Vladimir Pavlovic,et al.  Impact of Dynamics on Subspace Embedding and Tracking of Sequences , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[61]  Joaquin Quiñonero Candela,et al.  Local distance preservation in the GP-LVM through back constraints , 2006, ICML.

[62]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[63]  Danijela Ristic-Durrant,et al.  A robust markerless vision-based human gait analysis system , 2011, 2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI).

[64]  Linda Denehy,et al.  Validity of the Microsoft Kinect for assessment of postural control. , 2012, Gait & posture.

[65]  D. Sharma,et al.  Senior health monitoring using Kinect , 2012, 2012 Fourth International Conference on Communications and Electronics (ICCE).

[66]  Thomas G. Dietterich,et al.  A study of distance-based machine learning algorithms , 1994 .

[67]  Ramakant Nevatia,et al.  Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost , 2006, ECCV.

[68]  Ran Gilad-Bachrach,et al.  Full body gait analysis with Kinect , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.