Towards Detecting Biceps Muscle Fatigue in Gym Activity Using Wearables.

Mohamed Elshafei,Emad Shihab

doi:10.3390/s21030759

Abstract

Fatigue is a naturally occurring phenomenon during human activities, but it poses a bigger risk for injuries during physically demanding activities, such as gym activities and athletics. Several studies show that bicep muscle fatigue can lead to various injuries that may require up to 22 weeks of treatment. In this work, we adopt a wearable approach to detect biceps muscle fatigue during a bicep concentration curl exercise as an example of a gym activity. Our dataset consists of 3000 bicep curls from twenty middle-aged volunteers at ages between 27 to 30 and Body Mass Index (BMI) ranging between 18 to 28. All volunteers have been gym-goers for at least 1 year with no records of chronic diseases, muscle, or bone surgeries. We encountered two main challenges while collecting our dataset. The first challenge was the dumbbell’s suitability, where we found that a dumbbell weight (4.5 kg) provides the best tradeoff between longer recording sessions and the occurrence of fatigue on exercises. The second challenge is the subjectivity of RPE, where we average the reported RPE with the measured heart rate converted to RPE. We observed from our data that fatigue reduces the biceps’ angular velocity; therefore, it increases the completion time for later sets. We extracted a total of 33 features from our dataset, which have been reduced to 16 features. These features are the most overall representative and correlated with bicep curl movement, yet they are fatigue-specific features. We utilized these features in five machine learning models, which are Generalized Linear Models (GLM), Logistic Regression (LR), Random Forests (RF), Decision Trees (DT), and Feedforward Neural Networks (FNN). We found that using a two-layer FNN achieves an accuracy of 98% and 88% for subject-specific and cross-subject models, respectively. The results presented in this work are useful and represent a solid start for moving into a real-world application for detecting the fatigue level in bicep muscles using wearable sensors as we advise athletes to take fatigue into consideration to avoid fatigue-induced injuries.

Highlights

Fatigue is a natural outcome of prolonged activities
In the rare cases of dissimilarity between the Borg scale and the measured heart rates, we average the reported rate of perceived exertion (RPE) with the measured heart rate converted to RPE, as done in previous work [44]
RQ3 Conclusion: Our findings show that our approach achieves high performance for cross-specific in terms of precision (87%), recall (89%), accuracy (88%), and F1-measure

Summary

Introduction

Fatigue is a natural outcome of prolonged activities. A previous work [1] classifies fatigue into two types, objective and subjective fatigue. The objective fatigue is generated from performing physical activities, leading to a decrease in the capability to exert mechanical work [2]. Previous works [5,6,7] about gym over-training in athletes indicate that fatigue often occurs prior to muscle injuries, where muscles are at their most vulnerable state. These injuries are referred to as fatigue-induced injuries, which can lead to a series of complications, such as substantial loss in muscle strength and flexibility [8]. Our work aims to detect fatigue during gym activity to reduce the risk of fatigue-induced injuries.

Methods

Results

Discussion

Conclusion