Classification of lunge biomechanics with multiple and individual inertial measurement units

Abstract Lunges are a common, compound lower limb resistance exercise. If completed with aberrant technique, the increased stress on the joints used may increase risk of injury. This study sought to first investigate the ability of inertial measurement units (IMUs), when used in isolation and combination, to (a) classify acceptable and aberrant lunge technique (b) classify exact deviations in lunge technique. We then sought to investigate the most important features and establish the minimum number of top-ranked features and decision trees that are needed to maintain maximal system classification efficacy. Eighty volunteers performed the lunge with acceptable form and 11 deviations. Five IMUs positioned on the lumbar spine, thighs, and shanks recorded these movements. Time and frequency domain features were extracted from the IMU data and used to train and test a variety of classifiers. A single-IMU system achieved 83% accuracy, 62% sensitivity, and 90% specificity in binary classification and a five-IMU system achieved 90% accuracy, 80% sensitivity, and 92% specificity. A five-IMU set-up can also detect specific deviations with 70% accuracy. System efficiency was improved and classification quality was maintained when using only 20% of the top-ranked features for training and testing classifiers.

[1]  Patria Hume,et al.  Physiotherapist agreement when visually rating movement quality during lower extremity functional screening tests. , 2012, Physical therapy in sport : official journal of the Association of Chartered Physiotherapists in Sports Medicine.

[2]  Dan Morris,et al.  RecoFit: using a wearable sensor to find, recognize, and count repetitive exercises , 2014, CHI.

[3]  Hugo Fuks,et al.  Qualitative activity recognition of weight lifting exercises , 2013, AH.

[4]  T. Ward,et al.  Development of a wearable motion capture suit and virtual reality biofeedback system for the instruction and analysis of sports rehabilitation exercises , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Noel E. O'Connor,et al.  Automatic Activity Classification and Movement Assessment During a Sports Training Session Using Wearable Inertial Sensors , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[6]  Sebastian Madgwick,et al.  Estimation of IMU and MARG orientation using a gradient descent algorithm , 2011, 2011 IEEE International Conference on Rehabilitation Robotics.

[7]  Erik B Simonsen,et al.  Differences in the movement pattern of a forward lunge in two types of anterior cruciate ligament deficient patients: copers and non-copers. , 2002, Clinical biomechanics.

[8]  R. Escamilla.  Knee biomechanics of the dynamic squat exercise. , 2001, Medicine and science in sports and exercise.

[9]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[10]  Lee Burton,et al.  Pre-participation screening: the use of fundamental movements as an assessment of function - part 2. , 2006, North American journal of sports physical therapy : NAJSPT.

[11]  Bryan L Riemann,et al.  Biomechanical analysis of the anterior lunge during 4 external-load conditions. , 2012, Journal of athletic training.

[12]  Brian Caulfield,et al.  Evaluating Performance of the Single Leg Squat Exercise with a Single Inertial Measurement Unit , 2015, REHAB.

[13]  Toshiyo Tamura,et al.  Measurement and Estimation of 3D Orientation using Magnetic and Inertial Sensors , 2015 .

[14]  Brian Caulfield,et al.  Gyroscope-based assessment of temporal gait parameters during treadmill walking and running , 2012 .

[15]  Bryan P Conrad,et al.  Investigation of clinician agreement in evaluating movement quality during unilateral lower extremity functional tasks: a comparison of 2 rating methods. , 2007, The Journal of orthopaedic and sports physical therapy.

[16]  Noel E. O'Connor,et al.  Kinect vs. Low-cost Inertial Sensing for Gesture Recognition , 2014, MMM.

[17]  A. J. Jerri.  The Shannon sampling theorem—Its various extensions and applications: A tutorial review , 1977, Proceedings of the IEEE.

[18]  R. Marshall,et al.  Lunge performance and its determinants , 2003, Journal of sports sciences.

[19]  Takeo Kanade,et al.  Classifying human motion quality for knee osteoarthritis using accelerometers , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[20]  Peter Kokol,et al.  Exercise repetition detection for resistance training based on smartphones , 2012, Personal and Ubiquitous Computing.

[21]  Lee Burton,et al.  Pre-participation screening: the use of fundamental movements as an assessment of function - part 1. , 2006, North American journal of sports physical therapy : NAJSPT.

[22]  Brian Caulfield,et al.  Evaluating performance of the lunge exercise with multiple and individual inertial measurement units , 2016, PervasiveHealth.

[23]  Christopher M Powers,et al.  Trunk position influences the kinematics, kinetics, and muscle activity of the lead lower extremity during the forward lunge exercise. , 2008, The Journal of orthopaedic and sports physical therapy.

[24]  Ruzena Bajcsy,et al.  Recognizing the intensity of strength training exercises with wearable sensors , 2015, J. Biomed. Informatics.

[25]  Matteo Cesana,et al.  The Virtual Trainer: Supervising Movements Through a Wearable Wireless Sensor Network , 2009, 2009 6th IEEE Annual Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks Workshops.

[26]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[27]  J. Hoch,et al.  Reliability and minimal detectable change of the weight-bearing lunge test: A systematic review. , 2015, Manual therapy.

[28]  Takeo Kanade,et al.  Multi-label classification for the analysis of human motion quality , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[29]  Alberto Leardini,et al.  Validation of the angular measurements of a new inertial-measurement-unit based rehabilitation system: comparison with state-of-the-art gait analysis , 2014, Journal of NeuroEngineering and Rehabilitation.

[30]  Vincent Bonnet,et al.  Real-time Estimate of Body Kinematics During a Planar Squat Task Using a Single Inertial Measurement Unit , 2013, IEEE Transactions on Biomedical Engineering.

[31]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[32]  Nasser Kehtarnavaz,et al.  A Real-Time Human Action Recognition System Using Depth and Inertial Sensor Fusion , 2016, IEEE Sensors Journal.

[33]  Dennis Brandborg Nielsen,et al.  Forward lunge knee biomechanics before and after partial meniscectomy. , 2015, The Knee.

[34]  Brian Caulfield,et al.  Evaluating squat performance with a single inertial measurement unit , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[35]  A. J. Jerri.  Correction to "The Shannon sampling theorem—Its various extensions and applications: A tutorial review" , 1979 .

[36]  B Bonnechère,et al.  Validity and reliability of the Kinect within functional assessment activities: comparison with standard stereophotogrammetry. , 2014, Gait & posture.

[37]  Brian Caulfield,et al.  Rehabilitation exercise assessment using inertial sensors: a cross-sectional analytical study , 2014, Journal of NeuroEngineering and Rehabilitation.