“…Each participant was instructed to build the first course of a wall using seven CMUs. The first course was selected because it imposes the greatest loading on the lower back [30]. The CMUs were Type 1 blocks weighing 16.6 kg.…”
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.
“…Each participant was instructed to build the first course of a wall using seven CMUs. The first course was selected because it imposes the greatest loading on the lower back [30]. The CMUs were Type 1 blocks weighing 16.6 kg.…”
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.
“…For example, Ray and Teizer [16] used a Kinect range camera to classify work tasks as ergonomic or non-ergonomic. Alwasel et al [11] used an IMU-based sensor suit and 3D Static Strength Prediction Program [17] to estimate joint forces and moments in a bricklaying task. Research efforts in WMSDs in the construction industry utilizing sensing technologies, to date, have been focused on posture detection, posture classification, and comparison of working posture to ergonomic standards.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Previous research efforts reported that less experienced workers showed higher lost-workday claims [1] and significantly lower productivity than experienced workers [11]. Specifically, Alwasel et al [11] investigated the joint force and moments of masons who were grouped based on experience level, during a bricklaying task. The results showed that joint forces and moments were lowest in the group with the highest level of experience compared to the groups with less experience.…”
Construction work involves a number of repetitive and physically demanding tasks. Exposure to these labor intensive tasks with awkward postures result in an increase in biomechanical risk factors that may lead to work-related musculoskeletal disorders (WMSDs). Thus, it is essential to provide training for apprentice-level workers to adopt safe working postures. Recent advancements in sensing technologies have enabled us to automatically collect body motion data and analyze posture. The present work presents an automated posture assessment method using inertial measurement units (IMUs) allowing for in-depth ergonomic analysis via kinematic data. A case study on masonry work was performed and body motion data from masons with varying experience levels were collected. For the posture analysis, we first investigated the risk of working posture between experience groups using observation-based posture assessment methods (RULA and REBA), then compared the assessment scores between experience groups. Finally, a prototype training tool based on working posture was introduced. The experimental results show that the automated collection and analysis of motion data can provide greater understanding of working postures adopted by workers with different experience levels with the potential to be used as a training tool in apprenticeship programs.
“…Na alvenaria, os pedreiros são expostos a longas horas de demandas físicas, fator este que aumenta o risco de lesões musculoesqueléticas. Por dia, esses trabalhadores assentam em média, 1.000 tijolos realizando assim, em média, 1.000 flexões de torção de tronco (MITROPOULOS e MEMARIAN, 2013;BOSCHMAN et al, 2014;ALWASEL et al, 2017).…”
unclassified
“…Esta necessidade de movimentos repetitivos, torções de tronco, o peso dos tijolos que variam em média de 4 a 7kg e outros fatores ambientais indicam uma elevada probabilidade de alteração de força e fadiga muscular, diminuição da capacidade do trabalhador e velocidade do movimento (ALGHADIR e ANWER, 2015;ALWASEL et al, 2017).…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.