A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms.

The conventional methods to assess human gait are either expensive or complex to be applied regularly in clinical practice. To reduce the cost and simplify the evaluation, inertial sensors and adaptive algorithms have been utilized, respectively. This paper aims to summarize studies that applied adaptive also called artificial intelligence (AI) algorithms to gait analysis based on inertial sensor data, verifying if they can support the clinical evaluation. Articles were identified through searches of the main databases, which were encompassed from 1968 to October 2016. We have identified 22 studies that met the inclusion criteria. The included papers were analyzed due to their data acquisition and processing methods with specific questionnaires. Concerning the data acquisition, the mean score is 6.1±1.62, what implies that 13 of 22 papers failed to report relevant outcomes. The quality assessment of AI algorithms presents an above-average rating (8.2±1.84). Therefore, AI algorithms seem to be able to support gait analysis based on inertial sensor data. Further research, however, is necessary to enhance and standardize the application in patients, since most of the studies used distinct methods to evaluate healthy subjects.

[1]  Yong Hu,et al.  Systematic literature review of machine learning based software development effort estimation models , 2012, Inf. Softw. Technol..

[2]  Rafael C González,et al.  Real-time gait event detection for normal subjects from lower trunk accelerations. , 2010, Gait & posture.

[3]  Jan Rueterbories,et al.  Gait event detection for use in FES rehabilitation by radial and tangential foot accelerations. , 2014, Medical engineering & physics.

[4]  Angelo M. Sabatini,et al.  A Machine Learning Framework for Gait Classification Using Inertial Sensors: Application to Elderly, Post-Stroke and Huntington’s Disease Patients , 2016, Sensors.

[5]  Kara K. Patterson,et al.  Changes in Gait Symmetry and Velocity After Stroke: A Cross-Sectional Study From Weeks to Years After Stroke , 2010, Neurorehabilitation and neural repair.

[6]  D Kotiadis,et al.  Inertial Gait Phase Detection for control of a drop foot stimulator Inertial sensing for gait phase detection. , 2010, Medical engineering & physics.

[7]  R Williamson,et al.  Gait event detection for FES using accelerometers and supervised machine learning. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[8]  Ruud W. Selles,et al.  Automated Detection of Instantaneous Gait Events Using Time Frequency Analysis and Manifold Embedding , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Angelo M. Sabatini,et al.  Online Decoding of Hidden Markov Models for Gait Event Detection Using Foot-Mounted Gyroscopes , 2014, IEEE Journal of Biomedical and Health Informatics.

[10]  Sally McClean,et al.  A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome. , 2012, Medical engineering & physics.

[11]  Nicola Vitiello,et al.  Automated detection of gait initiation and termination using wearable sensors. , 2013, Medical engineering & physics.

[12]  Jan Rueterbories,et al.  Methods for gait event detection and analysis in ambulatory systems. , 2010, Medical engineering & physics.

[13]  Alpha Agape Gopalai,et al.  A robust real-time gait event detection using wireless gyroscope and its application on normal and altered gaits. , 2015, Medical engineering & physics.

[14]  Hassan Ghasemzadeh,et al.  A Method for Extracting Temporal Parameters Based on Hidden Markov Models in Body Sensor Networks With Inertial Sensors , 2009, IEEE Transactions on Information Technology in Biomedicine.

[15]  Giancarlo Ferrigno,et al.  A Novel Adaptive, Real-Time Algorithm to Detect Gait Events From Wearable Sensors , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[16]  Jian Zhang,et al.  Classifying Lower Extremity Muscle Fatigue During Walking Using Machine Learning and Inertial Sensors , 2013, Annals of Biomedical Engineering.

[17]  Bernd Markert,et al.  Self-Organizing Maps and Fuzzy C-Means Algorithms on Gait Analysis Based on Inertial Sensors Data , 2016, ISDA.

[18]  Eduardo Palermo,et al.  A Novel HMM Distributed Classifier for the Detection of Gait Phases by Means of a Wearable Inertial Sensor Network , 2014, Sensors.

[19]  Irvin Hussein Lopez-Nava,et al.  Estimation of temporal gait parameters using Bayesian models on acceleration signals , 2016, Computer methods in biomechanics and biomedical engineering.

[20]  J Y Goulermas,et al.  Predicting lower limb joint kinematics using wearable motion sensors. , 2008, Gait & posture.

[21]  J. Perry,et al.  Gait Analysis , 2024 .

[22]  M H Granat,et al.  A practical gait analysis system using gyroscopes. , 1999, Medical engineering & physics.

[23]  Andreu Català,et al.  Analyzing human gait and posture by combining feature selection and kernel methods , 2011, Neurocomputing.

[24]  Andrea Mannini,et al.  Gait phase detection and discrimination between walking-jogging activities using hidden Markov models applied to foot motion data from a gyroscope. , 2012, Gait & posture.

[25]  Eric Chalmers,et al.  Inertial sensing algorithms for long-term foot angle monitoring for assessment of idiopathic toe-walking. , 2014, Gait & posture.

[26]  G. Lyons,et al.  The use of accelerometry to detect heel contact events for use as a sensor in FES assisted walking. , 2003, Medical engineering & physics.

[27]  Daniel T H Lai,et al.  A machine learning approach to estimate Minimum Toe Clearance using Inertial Measurement Units. , 2015, Journal of biomechanics.

[28]  M. Stokes,et al.  Assessing changes in subjective and objective function from pre- to post-knee arthroplasty using the Cardiff Dempster–Shafer theory classifier , 2016, Computer methods in biomechanics and biomedical engineering.

[29]  W. Potthast,et al.  Motion analysis of patients after knee arthroplasty during activities of daily living--a systematic review. , 2015, Gait & posture.

[30]  J. Verly,et al.  Development and validation of an accelerometer-based method for quantifying gait events. , 2015, Medical engineering & physics.

[31]  Xiao-Jun Zeng,et al.  An Instance-Based Algorithm With Auxiliary Similarity Information for the Estimation of Gait Kinematics From Wearable Sensors , 2008, IEEE Transactions on Neural Networks.

[32]  Andrea Mannini,et al.  Walking speed estimation using foot-mounted inertial sensors: comparing machine learning and strap-down integration methods. , 2014, Medical engineering & physics.

[33]  Antonio I Cuesta-Vargas,et al.  The use of inertial sensors system for human motion analysis , 2010, Physical therapy reviews : PTR.

[34]  Hung T. Nguyen,et al.  Unsupervised nonparametric method for gait analysis using a waist-worn inertial sensor , 2014, Appl. Soft Comput..

[35]  B. Dobkin,et al.  Reliability and Validity of Bilateral Ankle Accelerometer Algorithms for Activity Recognition and Walking Speed After Stroke , 2011, Stroke.

[36]  Swades De,et al.  RF energy harvester-based wake-up receiver , 2015, 2015 IEEE SENSORS.