Objective Assessment Of Resistance Training Exercises Using A Wrist-worn Tri-axial Accelerometer

Abstract

The 2008 Physical Activity Guidelines for Americans recommend that all adults perform muscle-strengthening exercises to work all of the major muscle groups of the body on at least two days per week, in addition to aerobic activity. Studies using objective methods of monitoring physical activity have focused primarily on the assessment of aerobic activity. To date, a method to objectively classify resistance training exercises has not been developed using a wrist-worn activity monitor. PURPOSE: The purpose of this study was to examine the use of a wrist-worn, tri-axial accelerometer-based activity monitor (ActiGraph GT3X+) for classifying upper- and lower-body dumbbell resistance training exercises. METHODS: Sixty participants performed 12 different dynamic dumbbell exercises. The exercises included: bench press, shoulder press, biceps curls, upright rows, lateral raises, triceps extensions, triceps kickbacks, bent-over row (standing), bent-over row (kneeling), squats, walking lunges, and calf raises. Algorithms for classifying the exercises were developed using two different METHODS: support vector machine (SVM) and cosine similarity (CS). Confusion matrices were developed for each method and inter-method reliability was assessed using Cohen’s kappa. RESULTS: The results indicated that SVM and CS accurately classified the 12 different resistance training exercises 78% and 85% of the time, respectively. Both methods struggled to correctly differentiate bench press vs shoulder press and squat vs walking lunges. If those exercises were excluded, the accuracy of SVM and CS increased to 85% and 93%, respectively. CONCLUSION: This study demonstrated that individual resistance training exercises can be classified using a single activity monitor worn on the wrist. Future studies using larger sample sizes and additional data channels may be able to improve on the precision of the classification of resistance training exercises.