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

Abstract

BackgroundBiofeedback 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.ObjectiveWe 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.MethodsA 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.ResultsThe 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.ConclusionsA 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.

Wearable Inertial Sensor Systems for Lower Limb Exercise Detection and Evaluation: A Systematic Review

“…Eleven studies investigated the utilisation of wearable IMU systems for quantifying exercise technique [3,19,23,64,[69][70][71][72][73][74][75]. Table 10 summarises the sensing set-ups, movement measure which was classified, methodology and performance metrics for each system identified in this area.…”

“…Only one study experimentally evaluated the real-world accuracy of a movement classification system [75], which is recommended for future studies where possible as it negates the limitations of cross-validation techniques in assessing system efficacy. The efficacy scores presented by authors included accuracy, sensitivity/precision/true positive rate and specificity/recall/true negative rate.…”

“…Some recent studies also compare the effectiveness of global and personalised classification systems [73,74], whereby a personalised classification system is one which is trained from data from an individual and developed specifically for this individual and a global classification system is trained with data from many individuals and can be used by individuals not included in the training data. Analysis has shown that the personalised systems are more computationally efficient and accurate than global ones [73][74][75], which has enabled movement classification systems to be developed with single sensing unit rather than multiple sensing units. However, the time required to collect data from and train a classification system for every individual who requires a movement classification system is a significant practical limitation which may hinder the uptake of movement classification systems in clinical practice.…”

“…However, the time required to collect data from and train a classification system for every individual who requires a movement classification system is a significant practical limitation which may hinder the uptake of movement classification systems in clinical practice. Creating tools which streamline this process, as in O'Reilly et al [75], could be an important avenue of research.…”

Smart exercise application to improve leg function and short-term memory through game-like lunge exercises

“…Recently, O'Reilly et al (O'Reilly, Duffin, Ward, & Caulfield, 2017) developed a tablet application which successfully automated the process of creating an individualized exercise biofeedback system. This system seems to be an excellent solution for home-based exercise because it can be carried and still track and provide motion data.…”