Gait Anomaly Detection of Subjects With Parkinson’s Disease Using a Deep Time Series-Based Approach

Parkinson’s disease (PD) is a cognitive degenerative disorder of the central nervous system that mainly affects the motor system. The earliest symptoms evidence a general deficit of coordination and an unsteady gait. Current approaches for the evaluation and assessment of gait disturbances in PD have proved to be expensive, inconvenient and ineffective in the detection of anomalous walking patterns. In this paper, we address these issues by defining a deep time series-based approach for the detection of anomalous walking patterns in the gait dynamics of elderly people by analyzing the acceleration values of their movements. The results show a training accuracy and testing accuracy of over 90% with an accuracy improvement of 4.28% in comparison with related works.

[1]  Diane Podsiadlo,et al.  The Timed “Up & Go”: A Test of Basic Functional Mobility for Frail Elderly Persons , 1991, Journal of the American Geriatrics Society.

[2]  Jeffrey M. Hausdorff,et al.  Is walking a random walk? Evidence for long-range correlations in stride interval of human gait. , 1995, Journal of applied physiology.

[3]  Maciej Krawczak,et al.  An approach to dimensionality reduction in time series , 2014, Inf. Sci..

[4]  Mohammad Reza Daliri,et al.  HMM for Classification of Parkinson’s Disease Based on the Raw Gait Data , 2014, Journal of Medical Systems.

[5]  Huiru Zheng,et al.  Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis , 2009, 2009 3rd International Conference on Pervasive Computing Technologies for Healthcare.

[6]  Karl Johan Åström,et al.  On the choice of sampling rates in parametric identification of time series , 1969, Inf. Sci..

[7]  Daryl Pregibon,et al.  A Statistical Perspective on Knowledge Discovery in Databases , 1996, Advances in Knowledge Discovery and Data Mining.

[8]  Antonio Coronato,et al.  A Deep Learning-Based Approach for the Recognition of Sleep Disorders in Patients with Cognitive Diseases: A Case Study , 2017, FedCSIS.

[9]  Y. S. Rao,et al.  SVM based machine learning approach to identify Parkinson's disease using gait analysis , 2016, 2016 International Conference on Inventive Computation Technologies (ICICT).

[10]  Clu-istos Foutsos,et al.  Fast subsequence matching in time-series databases , 1994, SIGMOD '94.

[11]  R. Manmatha,et al.  Word image matching using dynamic time warping , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[12]  M. Leonardi,et al.  Quality of life in Parkinson`s Disease , 2012, Journal of medicine and life.

[13]  Jeffrey M. Hausdorff,et al.  Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis. , 2000, Journal of applied physiology.

[14]  Jaihyun Park,et al.  SVM based dynamic classifier for sleep disorder monitoring wearable device , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[15]  Giuseppe De Pietro,et al.  A situation-aware system for the detection of motion disorders of patients with Autism Spectrum Disorders , 2014, Expert Syst. Appl..

[16]  Mariana Callil Voos,et al.  Gait, posture and cognition in Parkinson's disease , 2016, Dementia & neuropsychologia.

[17]  Keith M. Kendrick,et al.  Analysis of Gait Rhythm Fluctuations for Neurodegenerative Diseases by Phase Synchronization and Conditional Entropy , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[18]  Chandralika Chakraborty,et al.  Issues and Limitations of HMM in Speech Processing: A Survey , 2016 .

[19]  Antonio Coronato,et al.  Intelligent Monitoring of Stereotyped Motion Disorders in Case of Children with Autism , 2013, 2013 9th International Conference on Intelligent Environments.

[20]  Jeffrey M. Hausdorff.  Gait dynamics in Parkinson's disease: common and distinct behavior among stride length, gait variability, and fractal-like scaling. , 2009, Chaos.

[21]  Eamonn J. Keogh,et al.  The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances , 2016, Data Mining and Knowledge Discovery.

[22]  S. Sveinbjornsdottir.  The clinical symptoms of Parkinson's disease , 2016, Journal of neurochemistry.

[23]  F. Horak,et al.  The Balance Evaluation Systems Test (BESTest) to Differentiate Balance Deficits , 2009, Physical Therapy.

[24]  J. Orbach.  Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. , 1962 .

[25]  Eamonn J. Keogh.  Nearest Neighbor , 2010, Encyclopedia of Machine Learning.

[26]  W. Vernon,et al.  Terminology and forensic gait analysis. , 2015, Science & justice : journal of the Forensic Science Society.

[27]  C. Sathish Kumar,et al.  Parkinsons disease classification using wavelet transform based feature extraction of gait data , 2017, 2017 International Conference on Circuit ,Power and Computing Technologies (ICCPCT).

[28]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[29]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[30]  Deepak Joshi,et al.  An automatic non-invasive method for Parkinson's disease classification , 2017, Comput. Methods Programs Biomed..

[31]  Giorgio Biagetti,et al.  A comparative study of machine learning algorithms for physiological signal classification , 2018, KES.

[32]  D. Wrisley,et al.  Reliability, internal consistency, and validity of data obtained with the functional gait assessment. , 2004, Physical therapy.

[33]  Thomas G. Dietterich.  Machine Learning for Sequential Data: A Review , 2002, SSPR/SPR.

[34]  Yves Chauvin,et al.  Backpropagation: the basic theory , 1995 .