Determining motions with an IMU during level walking and slope and stair walking

ABSTRACT This study investigated whether using an inertial measurement unit (IMU) can identify different walking conditions, including level walking (LW), descent (DC) and ascent (AC) slope walking as well as downstairs (DS) and upstairs (US) walking. Thirty healthy participants performed walking under five conditions. The IMU was stabilised on the exterior of the left shoe. The data from IMU were used to establish a customised prediction model by cut point and a prediction model by using deep learning method. The accuracy of both prediction models was evaluated. The customised prediction model combining the angular velocity of dorsi–plantar flexion in the heel-strike (HS) and toe-off (TO) phases can distinctly determine real conditions during DC and AC slope, DS, and LW (accuracy: 86.7–96.7%) except for US walking (accuracy: 60.0%). The prediction model established by deep learning using the data of three-axis acceleration and three-axis gyroscopes can also distinctly identify DS, US, and LW with 90.2–90.7% accuracy and 84.8% and 82.4% accuracy for DC and AC slope walking, respectively. In conclusion, inertial measurement units can be used to identify walking patterns under different conditions such as slopes and stairs with customised prediction model and deep learning prediction model.

[1]  Tzyy-Yuang Shiang,et al.  Assessment of walking, running, and jumping movement features by using the inertial measurement unit. , 2015, Gait & posture.

[2]  B. Hu,et al.  Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking. , 2018, Journal of biomechanics.

[3]  Wan Nurshazwani Wan Zakaria,et al.  Implementation of IMU sensor for elbow movement measurement of Badminton players , 2016, 2016 2nd IEEE International Symposium on Robotics and Manufacturing Automation (ROMA).

[4]  M. Granat,et al.  The validity and reliability of a novel activity monitor as a measure of walking , 2006, British Journal of Sports Medicine.

[5]  Brendan J Burkett,et al.  The use of a single inertial sensor to identify stride, step, and stance durations of running gait. , 2010, Journal of science and medicine in sport.

[6]  T. Hortobágyi,et al.  Multiple gait parameters derived from iPod accelerometry predict age-related gait changes. , 2016, Gait & posture.

[7]  Trevor C. Chen,et al.  Effects of Descending Stair Walking on Health and Fitness of Elderly Obese Women , 2017, Medicine and science in sports and exercise.

[8]  Shuichi Obuchi,et al.  The feasibility of measuring joint angular velocity with a gyro-sensor. , 2008, Archives of physical medicine and rehabilitation.

[9]  Andrea N. Lay,et al.  The effects of sloped surfaces on locomotion: a kinematic and kinetic analysis. , 2006, Journal of biomechanics.

[10]  Kamiar Aminian,et al.  Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes. , 2002, Journal of biomechanics.

[11]  Hafiz Farhan Maqbool,et al.  Heuristic based gait event detection for human lower limb movement , 2017, 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[12]  E. Ambikairajah,et al.  Time-Frequency Based Features for Classification of Walking Patterns , 2007, 2007 15th International Conference on Digital Signal Processing.

[13]  Alex Stacoff,et al.  Ground reaction forces on stairs: effects of stair inclination and age. , 2005, Gait & posture.

[14]  Andrea Ancillao,et al.  Indirect Measurement of Ground Reaction Forces and Moments by Means of Wearable Inertial Sensors: A Systematic Review , 2018, Sensors.

[15]  E. Zehr,et al.  Task-specific modulation of cutaneous reflexes expressed at functionally relevant gait cycle phases during level and incline walking and stair climbing , 2006, Experimental Brain Research.

[16]  Jane Wardle,et al.  Indoor Tracking to Understand Physical Activity and Sedentary Behaviour: Exploratory Study in UK Office Buildings , 2015, PloS one.

[17]  K. Kawamura,et al.  Gait analysis of slope walking: a study on step length, stride width, time factors and deviation in the center of pressure. , 1991, Acta medica Okayama.

[18]  Y Schutz,et al.  High-precision satellite positioning system as a new tool to study the biomechanics of human locomotion. , 2000, Journal of biomechanics.

[19]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[20]  Aleksandar Milenkovic,et al.  Journal of Neuroengineering and Rehabilitation Open Access a Wireless Body Area Network of Intelligent Motion Sensors for Computer Assisted Physical Rehabilitation , 2005 .

[21]  Christoph Kalkbrenner,et al.  Gait Analysis with IMU - Gaining New Orientation Information of the Lower Leg , 2014, BIODEVICES.

[22]  A. Protopapadaki,et al.  Hip, knee, ankle kinematics and kinetics during stair ascent and descent in healthy young individuals. , 2007, Clinical biomechanics.

[23]  David R. Bowden,et al.  Sex differences in whole body gait kinematics at preferred speeds. , 2015, Gait & posture.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Hylton B Menz,et al.  Accelerometry: a technique for quantifying movement patterns during walking. , 2008, Gait & posture.

[26]  H. Inooka,et al.  Non-restricted measurement of walking distance , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[27]  Chen-Chi Wu,et al.  Determine the Foot Strike Pattern Using Inertial Sensors , 2016, J. Sensors.

[28]  Honglak Lee,et al.  Unsupervised feature learning for audio classification using convolutional deep belief networks , 2009, NIPS.

[29]  Yoshiyuki Sankai,et al.  Interactive task generation for humanoid based on human motion strategy , 2004, RO-MAN 2004. 13th IEEE International Workshop on Robot and Human Interactive Communication (IEEE Catalog No.04TH8759).

[30]  Tzyy-Yuang Shiang,et al.  Measuring kinematic changes of the foot using a gyro sensor during intense running , 2014, Journal of sports sciences.

[31]  Wen-Wen Yang,et al.  Acute Effects of Battle Rope Exercise on Performance, Blood Lactate Levels, Perceived Exertion, and Muscle Soreness in Collegiate Basketball Players. , 2020, Journal of strength and conditioning research.

[32]  C. Matthews,et al.  Best practices for using physical activity monitors in population-based research. , 2012, Medicine and science in sports and exercise.

[33]  Melanie Swan,et al.  Sensor Mania! The Internet of Things, Wearable Computing, Objective Metrics, and the Quantified Self 2.0 , 2012, J. Sens. Actuator Networks.

[34]  Omid Dehzangi,et al.  IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion , 2017, Sensors.

[35]  H. Barbeau,et al.  Postural adaptation to walking on inclined surfaces: I. Normal strategies. , 2002, Gait & posture.

[36]  Bram Vanderborght,et al.  ED-FNN: A New Deep Learning Algorithm to Detect Percentage of the Gait Cycle for Powered Prostheses , 2018, Sensors.

[37]  Panagiota Anastasopoulou,et al.  Validation and Comparison of Two Methods to Assess Human Energy Expenditure during Free-Living Activities , 2014, PloS one.

[38]  E. Tomasi,et al.  Calibration of raw accelerometer data to measure physical activity: A systematic review. , 2018, Gait & posture.

[39]  Jeen-Shing Wang,et al.  Walking Pattern Classification and Walking Distance Estimation Algorithms Using Gait Phase Information , 2012, IEEE Transactions on Biomedical Engineering.