A Data-Driven Approach to Predict Fatigue in Exercise Based on Motion Data from Wearable Sensors or Force Plate

Abstract

Fatigue increases the risk of injury during sports training and rehabilitation. Early detection of fatigue during exercises would help adapt the training in order to prevent over-training and injury. This study lays the foundation for a data-driven model to automatically predict the onset of fatigue and quantify consequent fatigue changes using a force plate (FP) or inertial measurement units (IMUs). The force plate and body-worn IMUs were used to capture movements associated with exercises (squats, high knee jacks, and corkscrew toe-touch) to estimate participant-specific fatigue levels in a continuous fashion using random forest (RF) regression and convolutional neural network (CNN) based regression models. Analysis of unseen data showed high correlation (up to 89%, 93%, and 94% for the squat, jack, and corkscrew exercises, respectively) between the predicted fatigue levels and self-reported fatigue levels. Predictions using force plate data achieved similar performance as those with IMU data; the best results in both cases were achieved with a convolutional neural network. The displacement of the center of pressure (COP) was found to be correlated with fatigue compared to other commonly used features of the force plate. Bland–Altman analysis also confirmed that the predicted fatigue levels were close to the true values. These results contribute to the field of human motion recognition by proposing a deep neural network model that can detect fairly small changes of motion data in a continuous process and quantify the movement. Based on the successful findings with three different exercises, the general nature of the methodology is potentially applicable to a variety of other forms of exercises, thereby contributing to the future adaptation of exercise programs and prevention of over-training and injury as a result of excessive fatigue.

Detection of Horse Locomotion Modifications Due to Training with Inertial Measurement Units: A Proof-of-Concept

“…This requires the detection on-line of the strides, to save the corresponding stride kinematics, and to compute the CC and RMSD on consecutive kinematic strides and regularly between non-consecutive strides. Approaches based on artificial intelligence could be developed to identify and compare gait cycles during a training session [40].…”

Interoceptive and metacognitive facets of fatigue in multiple sclerosis

“…While numerous studies exist which, in a variety of contexts and disorders, used machine learning to predict individual fatigue levels from behavioural or physiological data (Baykaner et al, 2015;Mun & Geng, 2019;Luo et al, 2020;Bafna et al, 2021;Jiang et al, 2021;Pinto-Bernal et al, 2021;Yao et al, 2021;Zeng et al, 2021), only two of these studies have concerned MS (Ibrahim et al, 2020;.…”

“…While numerous studies exist which, in a variety of contexts and disorders, used machine learning to predict individual fatigue levels from behavioural or physiological data (Baykaner et al ., 2015; Mun & Geng, 2019; Luo et al ., 2020; Bafna et al ., 2021; Jiang et al ., 2021; Pinto-Bernal et al ., 2021; Yao et al ., 2021; Zeng et al ., 2021), only two of these studies have concerned MS (Ibrahim et al ., 2020; 2022). Additionally, like the vast majority of studies, these two MS-specific studies did not actually predict fatigue (the subjective experience) but predict fatiguability (the observable decrease in performance during physiologically or cognitively demanding tasks) (Kluger et al, 2013) (sometimes, fatigue and fatiguability are also referred to as “trait fatigue” and “state fatigue”, respectively (Cehelyk et al ., 2019)).…”

Upper-Limb Kinematic Behavior and Performance Fatigability of Elderly Participants Performing an Isometric Task: A Quasi-Experimental Study

“…Since performance fatigability may also be revealed as decreased movement accuracy [18][19][20], impaired proprioception acuity [21], and decreased cocontraction during precision movements [18,22,23], the biomechanical approach can be used to identify alterations that occur in motion patterns all the time [24], namely those which are fatigue related.…”

“…According to recent studies, IMU sensor systems accurately measure motor function and supply useful data concerning motor elements that promote assignment performance such as movement precision, smoothness, and accuracy [31], even in single IMU systems [32], showing encouraging results with respect to their reliability and intersystem agreement [33,34], especially in temporal parameters during activity [24] with higher validity for simple tasks [35].…”