Mobile App to Streamline the Development of Wearable Sensor-Based Exercise Biofeedback Systems: System Development and Evaluation

Background Biofeedback systems that use inertial measurement units (IMUs) have been shown recently to have the ability to objectively assess exercise technique. However, there are a number of challenges in developing such systems; vast amounts of IMU exercise datasets must be collected and manually labeled for each exercise variation, and naturally occurring technique deviations may not be well detected. One method of combatting these issues is through the development of personalized exercise technique classifiers. Objective We aimed to create a tablet app for physiotherapists and personal trainers that would automate the development of personalized multiple and single IMU-based exercise biofeedback systems for their clients. We also sought to complete a preliminary investigation of the accuracy of such individualized systems in a real-world evaluation. Methods A tablet app was developed that automates the key steps in exercise technique classifier creation through synchronizing video and IMU data collection, automatic signal processing, data segmentation, data labeling of segmented videos by an exercise professional, automatic feature computation, and classifier creation. Using a personalized single IMU-based classification system, 15 volunteers (12 males, 3 females, age: 23.8 [standard deviation, SD 1.8] years, height: 1.79 [SD 0.07] m, body mass: 78.4 [SD 9.6] kg) then completed 4 lower limb compound exercises. The real-world accuracy of the systems was evaluated. Results The tablet app successfully automated the process of creating individualized exercise biofeedback systems. The personalized systems achieved 89.50% (1074/1200) accuracy, with 90.00% (540/600) sensitivity and 89.00% (534/600) specificity for assessing aberrant and acceptable technique with a single IMU positioned on the left thigh. Conclusions A tablet app was developed that automates the process required to create a personalized exercise technique classification system. This tool can be applied to any cyclical, repetitive exercise. The personalized classification model displayed excellent system accuracy even when assessing acute deviations in compound exercises with a single IMU.

[1]  Mike Y. Chen,et al.  Tracking Free-Weight Exercises , 2007, UbiComp.

[2]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[3]  Brian Caulfield,et al.  Evaluating rehabilitation exercise performance using a single inertial measurement unit , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

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

[5]  Sandra Bassett.  Measuring Patient Adherence to Physiotherapy , 2012 .

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

[7]  E. B. George,et al.  Fractals and the analysis of growth paths , 1985, Bulletin of mathematical biology.

[8]  William Johnston,et al.  Objective Classification of Dynamic Balance Using a Single Wearable Sensor , 2016, icSPORTS.

[9]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[10]  M. Matarić,et al.  Evaluation Metrics and Results of Human Arm Movement Imitation , 2000 .

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

[12]  Kristof Van Laerhoven,et al.  myHealthAssistant: a phone-based body sensor network that captures the wearer's exercises throughout the day , 2011, BODYNETS.

[13]  Hagit Shatkay,et al.  Approximate queries and representations for large data sequences , 1996, Proceedings of the Twelfth International Conference on Data Engineering.

[14]  D. Felson,et al.  Effect of therapeutic exercise for hip osteoarthritis pain: results of a meta-analysis. , 2008, Arthritis and rheumatism.

[15]  E. Sugawara,et al.  Properties of AdeABC and AdeIJK Efflux Systems of Acinetobacter baumannii Compared with Those of the AcrAB-TolC System of Escherichia coli , 2014, Antimicrobial Agents and Chemotherapy.

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

[17]  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).

[18]  W J Kraemer,et al.  Effect of resistance training on women's strength/power and occupational performances. , 2001, Medicine and science in sports and exercise.

[19]  Jonathan Feng-Shun Lin,et al.  Online Segmentation of Human Motion for Automated Rehabilitation Exercise Analysis , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[20]  Dana Kulic,et al.  Classification of squat quality with inertial measurement units in the single leg squat mobility test , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[21]  Strength conditioning in older men: skeletal muscle hypertrophy and improved function. , 1988 .

[22]  Oonagh M. Giggins,et al.  Biofeedback in rehabilitation , 2013, Journal of NeuroEngineering and Rehabilitation.

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

[24]  M Friedrich,et al.  The effect of brochure use versus therapist teaching on patients performing therapeutic exercise and on changes in impairment status. , 1996, Physical therapy.

[25]  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.

[26]  Darragh F Whelan,et al.  Technology in Rehabilitation: Evaluating the Single Leg Squat Exercise with Wearable Inertial Measurement Units. , 2016, Methods of information in medicine.

[27]  Medical Advisory Secretariat.  Physiotherapy rehabilitation after total knee or hip replacement: an evidence-based analysis. , 2005, Ontario health technology assessment series.

[28]  Shaul Markovitch,et al.  Feature Generation Using General Constructor Functions , 2002, Machine Learning.

[29]  P Netter,et al.  EULAR evidence based recommendations for gout. Part II: Management. Report of a task force of the EULAR Standing Committee For International Clinical Studies Including Therapeutics (ESCISIT) , 2006, Annals of the rheumatic diseases.

[30]  William J. Kraemer,et al.  Muscle hypertrophy, hormonal adaptations and strength development during strength training in strength-trained and untrained men , 2003, European Journal of Applied Physiology.

[31]  Eamonn Delahunt,et al.  Classification of deadlift biomechanics with wearable inertial measurement units. , 2017, Journal of biomechanics.

[32]  M. Tahar Kechadi,et al.  Leveraging IMU data for accurate exercise performance classification and musculoskeletal injury risk screening , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[33]  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.

[34]  Francisco Herrera,et al.  Study on the Impact of Partition-Induced Dataset Shift on $k$-Fold Cross-Validation , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[35]  W. Frontera,et al.  Strength conditioning in older men: skeletal muscle hypertrophy and improved function. , 1988, Journal of applied physiology.

[36]  Adrian Burns,et al.  SHIMMER™ – A Wireless Sensor Platform for Noninvasive Biomedical Research , 2010, IEEE Sensors Journal.

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