No abstract

No abstract

Workers’ fatigue is a significant problem in physically demanding occupations. Physical fatigue is known to result in the inability to maintain proper posture and working technique. Consequently, workers lose their ability to safely and effectively perform their duties. Thus, understanding the physical demands of labor-intensive work is of great importance in protecting workers’ safety, and maintaining productivity. Current fatigue assessments methods, including surveys and questionnaires, are subjective and lack reliability. Objective fatigue assessments based on physiological data are more reliable, however they are cumbersome to implement in real work conditions. There is a need for an objective fatigue assessment method that can monitor physical fatigue with minimal intrusion. The goal of this study was to investigate whether jerk, the time-derivative of acceleration, can be used to objectively detect physical fatigue. A pilot study on masons was conducted to determine if physical fatigue can be detected by changes in jerk values. Ten participants performed a bricklaying task using forty-five concrete masonry units (CMU). Seven body segments, namely the hands, forearms, upper arms, and pelvis, were selected for placement of IMU sensors to measure the segment accelerations. Jerk was calculated from the measured acceleration via numerical differentiation. Characteristic values of the jerk at the beginning and end of the bricklaying task were obtained to represent the rested and fatigued states. They were then compared for significant differences. Jerk values calculated from the IMU sensors located on the upper arms and pelvis showed significant differences between rested and fatigued states. The results of this pilot study indicate that the characteristic jerk can be used to detect physical fatigue, however caution must be taken in selecting sensor locations to reduce the influence of spurious signals.

Inertial Motion Capture (IMC) systems enable in situ studies of human motion free of the severe constraints imposed by Optical Motion Capture systems. Inverse dynamics can use those motions to estimate forces and moments developing within muscles and joints. We developed an inverse dynamic whole-body model that eliminates the usage of force plates (FPs) and uses motion patterns captured by an IMC system to predict the net forces and moments in 14 major joints. We validated the model by comparing its estimates of Ground Reaction Forces (GRFs) to the ground truth obtained from FPs and comparing predictions of the static model’s net joint moments to those predicted by 3D Static Strength Prediction Program (3DSSPP). The relative root-mean-square error (rRMSE) in the predicted GRF was 6% and the intraclass correlation of the peak values was 0.95, where both values were averaged over the subject population. The rRMSE of the differences between our model’s and 3DSSPP predictions of net L5/S1 and right and left shoulder joints moments were 9.5%, 3.3%, and 5.2%, respectively. We also compared the static and dynamic versions of the model and found that failing to account for body motions can underestimate net joint moments by 90% to 560% of the static estimates.

Construction workers are commonly subjected to ergonomic risks due to manual material handling that requires high levels of energy input over long work hours. Fatigue in musculature is associated with decline in postural stability, motor performance, and altered normal motion patterns, leading to heightened risks of work-related musculoskeletal disorders. Physical fatigue has been previously demonstrated to be a good indicator of injury risks, thus, monitoring and detecting muscle fatigue during strenuous work may be advantageous in mitigating these risks. Currently, few researchers have investigated how physical fatigue and exertion can be continuously monitored for practical use outside laboratory settings. Exercise-induced fatigue has been shown to impact motor control; thus, it can be measured using jerk, the time derivative of acceleration. This paper investigates the application of a machine learning approach, Support Vector Machine (SVM), to automatically recognize jerk changes due to physical exertion. We hypothesized that physical exertion and fatigue will influence motions and thus, can be classified based on jerk values. The motion data of six expert masons were collected using IMU sensors during two bricklaying tasks. The pelvis, upper arms, and thighs jerk values were used to classify inter-and intra-subject rested and exerted states. Our results show that on average, intra-subject classification achieved an accuracy of 94% for a five-course wall building experiment and 80% for a first-course experiment, leading us to conclude that jerk changes due to physical exertion can be detected using wearable sensors and SVMs.