Role of machine learning in gait analysis: a review

Abstract Human biomechanics and gait form an integral part of life. The gait analysis involves a large number of interdependent parameters that were difficult to interpret due to a vast amount of data and their inter-relations. To simplify evaluation, the integration of machine learning (ML) with biomechanics is a promising solution. The purpose of this review is to familiarise the readers with key directions of implementation of ML techniques for gait analysis and gait rehabilitation. An extensive literature survey was based on research articles from nine databases published from 1980 to 2019. With over 943 studies identified, finally, 43 studies met the inclusion criteria. The outcome reported illustrates that supervised ML techniques showed accuracies above 90% in the identified gait analysis domain. The statistical results revealed support vector machine (SVM) as the best classifier (mean-score = 0.87 ± 0.07) with remarkable generalisation capability even on small to medium datasets. It has also been analysed that the control strategies for gait rehabilitation are benefitted from reinforcement learning and (deep) neural-networks due to their ability to capture participants’ variability. This review paper shows the success of ML techniques in detecting disorders, predicting rehabilitation length, and control of rehabilitation devices which make them suitable for clinical diagnosis.

[1]  João Paulo,et al.  ISR-AIWALKER: Robotic Walker for Intuitive and Safe Mobility Assistance and Gait Analysis , 2017, IEEE Transactions on Human-Machine Systems.

[2]  A. Paulo Coimbra,et al.  Human knee joint walking pattern generation using computational intelligence techniques , 2018, Neural Computing and Applications.

[3]  Tanvir Anwar,et al.  Extreme learning machine based sEMG for drop-foot after stroke detection , 2016, 2016 Sixth International Conference on Information Science and Technology (ICIST).

[4]  K. X. Khor,et al.  Development of CR2-Haptic: A compact and portable rehabilitation robot for wrist and forearm training , 2014, 2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES).

[5]  L. Schutte,et al.  An index for quantifying deviations from normal gait. , 2000, Gait & posture.

[6]  Andrés Úbeda,et al.  Decoding the Attentional Demands of Gait through EEG Gamma Band Features , 2016, PloS one.

[7]  R. French,et al.  IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING , VOL . ? ? ? , NO . ? ? ? , ? ? ? ? ? ? , 2009 .

[8]  S. M. N. Arosha Senanayake,et al.  Article in Press G Model Applied Soft Computing a Knowledge-based Intelligent Framework for Anterior Cruciate Ligament Rehabilitation Monitoring , 2022 .

[9]  Jiangping Hu,et al.  Learning-based Walking Assistance Control Strategy for a Lower Limb Exoskeleton with Hemiplegia Patients , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[10]  Mohammad Rastgaar,et al.  Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks , 2017, International Journal of Intelligent Robotics and Applications.

[11]  J. Paulo,et al.  Trajectory-based gait pattern shift detection for assistive robotics applications , 2019, Intell. Serv. Robotics.

[12]  Alberto Del Bimbo,et al.  Learning shape variations of motion trajectories for gait analysis , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[13]  Nurhazimah Nazmi,et al.  Generalization of ANN Model in Classifying Stance and Swing Phases of Gait using EMG Signals , 2018, 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[14]  Mark V. Albert,et al.  Activity Recognition for Incomplete Spinal Cord Injury Subjects Using Hidden Markov Models , 2018, IEEE Sensors Journal.

[15]  Kaat Desloovere,et al.  Probabilistic gait classification in children with cerebral palsy: a Bayesian approach. , 2011, Research in developmental disabilities.

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

[17]  Gora Chand Nandi,et al.  Less computationally intensive fuzzy logic (type-1)-based controller for humanoid push recovery , 2015, Robotics Auton. Syst..

[18]  Marcelo Ricardo Stemmer,et al.  Extraction and Classification of Human Body Parameters for Gait Analysis , 2018, Journal of Control, Automation and Electrical Systems.

[19]  D.T.H. Lai,et al.  Identification of patellofemoral pain syndrome using a Support Vector Machine approach , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[20]  Hao Zhou,et al.  Simultaneous Recognition and Assessment of Post-Stroke Hemiparetic Gait by Fusing Kinematic, Kinetic, and Electrophysiological Data , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  Todd C. Pataky,et al.  Automated Nonlinear Feature Generation and Classification of Foot Pressure Lesions , 2010, IEEE Transactions on Information Technology in Biomedicine.

[22]  Edward D Lemaire,et al.  Design, development, and evaluation of a local sensor-based gait phase recognition system using a logistic model decision tree for orthosis-control , 2019, Journal of NeuroEngineering and Rehabilitation.

[23]  Jurandir Nadal,et al.  Principal Component Analysis of Vertical Ground Reaction Force: A Powerful Method to Discriminate Normal and Abnormal Gait and Assess Treatment , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Jun-Young Jung,et al.  A hybrid control method of an exoskeleton robot for intention-driven walking rehabilitation of stroke patients , 2012, 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[25]  J. Hozman,et al.  Prediction of lower extremities movement using characteristics of angle-angle diagrams and artificial intelligence , 2011, 2011 E-Health and Bioengineering Conference (EHB).

[26]  Carlo Menon,et al.  Estimation of Knee Joint Angle Using a Fabric-Based Strain Sensor and Machine Learning: A Preliminary Investigation , 2018, 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob).

[27]  Marimuthu Palaniswami,et al.  Computational Intelligence in Gait Research: A Perspective on Current Applications and Future Challenges , 2009, IEEE Transactions on Information Technology in Biomedicine.

[28]  Yanxin Zhang,et al.  Application of supervised machine learning algorithms in the classification of sagittal gait patterns of cerebral palsy children with spastic diplegia , 2019, Comput. Biol. Medicine.

[29]  Hassan Ghasemzadeh,et al.  A Body Sensor Network With Electromyogram and Inertial Sensors: Multimodal Interpretation of Muscular Activities , 2010, IEEE Transactions on Information Technology in Biomedicine.

[30]  Chang-Soo Han,et al.  Scoliosis Screening through a Machine Learning Based Gait Analysis Test , 2018, International Journal of Precision Engineering and Manufacturing.

[31]  Nitish Thakor,et al.  Spatio–Spectral Representation Learning for Electroencephalographic Gait-Pattern Classification , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[32]  Guodong Guo,et al.  Classification of Normal and Pathological Gait in Young Children Based on Foot Pressure Data , 2016, Neuroinformatics.

[33]  Evangelos Pappas,et al.  Classification of gait patterns in patients with unilateral anterior cruciate ligament deficiency based on phase space reconstruction, Euclidean distance and neural networks , 2020, Soft Comput..

[34]  Xinyu Wu,et al.  Deep rehabilitation gait learning for modeling knee joints of lower-limb exoskeleton , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[35]  D. Moher,et al.  Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement , 2009, BMJ : British Medical Journal.

[36]  Moi Hoon Yap,et al.  Automated Analysis and Quantification of Human Mobility Using a Depth Sensor , 2017, IEEE Journal of Biomedical and Health Informatics.

[37]  J. Kamruzzaman,et al.  Neural networks for detection and classification of walking pattern changes due to ageing , 2006, Australasian Physics & Engineering Sciences in Medicine.

[38]  Alessandro Puiatti,et al.  Activity detection in uncontrolled free-living conditions using a single accelerometer , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[39]  Thompson Sarkodie-Gyan,et al.  Application of wearable sensors for human gait analysis using fuzzy computational algorithm , 2011, Eng. Appl. Artif. Intell..

[40]  Andrés Úbeda,et al.  Using EEG Signals to Detect the Intention of Walking Initiation and Stop , 2015, IWINAC.

[41]  Tatsuo Narikiyo,et al.  A LLE-HMM-based framework for recognizing human gait movement from EMG , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[42]  Aakash Gupta,et al.  Activity recognition in patients with lower limb impairments: Do we need training data from each patient? , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[43]  Hyeon-Min Shim,et al.  Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience , 2015 .

[44]  Albert Pla,et al.  Bag-of-Steps: predicting lower-limb fracture rehabilitation length , 2017, ESANN.

[45]  Tao Liu,et al.  Two New Indices to Assess Gait Disturbances Applied to Anterior Cruciate Ligament Reconstructed Knees , 2018, 2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER).

[46]  Yi Yang,et al.  Gait Recognition Based on Graphene Porous Network Structure Pressure Sensors for Rehabilitation Therapy , 2018, 2018 IEEE International Conference on Electron Devices and Solid State Circuits (EDSSC).

[47]  Xingda Qu,et al.  Subject-specific gait parameters prediction for robotic gait rehabilitation via generalized regression neural network , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[48]  Hongyin Lau,et al.  The reliability of using accelerometer and gyroscope for gait event identification on persons with dropped foot. , 2008, Gait & posture.

[49]  Hailong Zhu,et al.  Support vector machine for classification of walking conditions using miniature kinematic sensors , 2008, Medical & Biological Engineering & Computing.

[50]  Thompson Sarkodie-Gyan,et al.  Automatic classification of pathological gait patterns using ground reaction forces and machine learning algorithms , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[51]  Alex Mihailidis,et al.  An Automated Classification of Pathological Gait Using Unobtrusive Sensing Technology , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[52]  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.

[53]  Meg E. Morris,et al.  Classification of Gait Disorders Following Traumatic Brain Injury , 2015, The Journal of head trauma rehabilitation.

[54]  Akamin Thongsook,et al.  C4.5 Decision Tree against Neural Network on Gait Phase Recognition for Lower Limp Exoskeleton , 2019, 2019 First International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP).

[55]  Sujit Dey,et al.  Human Action Understanding and Movement Error Identification for the Treatment of Patients with Parkinson's Disease , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[56]  Deok Won Kim,et al.  Interpretation of movement during stair ascent for predicting severity and prognosis of knee osteoarthritis in elderly women using support vector machine , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[57]  Hyungmin Kim,et al.  EEG-based Gait State and Gait Intention Recognition Using Spatio-Spectral Convolutional Neural Network , 2019, 2019 7th International Winter Conference on Brain-Computer Interface (BCI).