“…Among the three considered SVM kernel functions, linear and polynomial ones were found to perform classification with high accuracy (92%), similarly to our results. Regarding the Gaussian kernel function, they did not find a high value of accuracy (89%) [52]. Conversely, we obtained a high accuracy with such a kernel, especially in the LL task with the 2 kg load.…”
Section: Discussioncontrasting
confidence: 70%
“…Nevertheless, when considering the level of accuracy and the high values of FP and FN, a small dataset is not an effective choice (see Figures 4 and 5). Furthermore, when considering the TL-l dataset, the processing time result was lower than the result that was obtained in Alwasel et al study [52].…”
Section: Discussioncontrasting
confidence: 70%
“…In the RL task with the 5 kg load, we obtained a 100% TPR value and a 97.4% TNR value (Table 4). In the study of Alwasel et al, a high accuracy was reached in distinguishing between safe and unsafe postures assumed by expert and inexpert masonry workers [52]. They implemented an SVM that was fed with inertial data of the whole kinematic chain.…”
Section: Discussionmentioning
confidence: 99%
“…In industrial environments, SVMs have been applied to classify and recognize the ergonomic posture of movement patterns [40]. In the last few years, activity recognition has usually been based on machine learning algorithms that are fed with inertial sensor data [38,52]. Alwasel et al proposed and validated an SVM algorithm that classified masonry workers' poses as a function of their experience, obtaining a high rate of accuracy 92.11% [52].…”
Section: Introductionmentioning
confidence: 99%
“…In the last few years, activity recognition has usually been based on machine learning algorithms that are fed with inertial sensor data [38,52]. Alwasel et al proposed and validated an SVM algorithm that classified masonry workers' poses as a function of their experience, obtaining a high rate of accuracy 92.11% [52]. In 2016, Ryu and colleagues tested the action recognition of masonry workers by using supervised learning algorithms, such as an SVM, a k-nearest neighbor (kNN) algorithm, and a neural network [53].…”
Ergonomics evaluation through measurements of biomechanical parameters in real time has a great potential in reducing non-fatal occupational injuries, such as work-related musculoskeletal disorders. Assuming a correct posture guarantees the avoidance of high stress on the back and on the lower extremities, while an incorrect posture increases spinal stress. Here, we propose a solution for the recognition of postural patterns through wearable sensors and machine-learning algorithms fed with kinematic data. Twenty-six healthy subjects equipped with eight wireless inertial measurement units (IMUs) performed manual material handling tasks, such as lifting and releasing small loads, with two postural patterns: correctly and incorrectly. Measurements of kinematic parameters, such as the range of motion of lower limb and lumbosacral joints, along with the displacement of the trunk with respect to the pelvis, were estimated from IMU measurements through a biomechanical model. Statistical differences were found for all kinematic parameters between the correct and the incorrect postures (p < 0.01). Moreover, with the weight increase of load in the lifting task, changes in hip and trunk kinematics were observed (p < 0.01). To automatically identify the two postures, a supervised machine-learning algorithm, a support vector machine, was trained, and an accuracy of 99.4% (specificity of 100%) was reached by using the measurements of all kinematic parameters as features. Meanwhile, an accuracy of 76.9% (specificity of 76.9%) was reached by using the measurements of kinematic parameters related to the trunk body segment.
“…Among the three considered SVM kernel functions, linear and polynomial ones were found to perform classification with high accuracy (92%), similarly to our results. Regarding the Gaussian kernel function, they did not find a high value of accuracy (89%) [52]. Conversely, we obtained a high accuracy with such a kernel, especially in the LL task with the 2 kg load.…”
Section: Discussioncontrasting
confidence: 70%
“…Nevertheless, when considering the level of accuracy and the high values of FP and FN, a small dataset is not an effective choice (see Figures 4 and 5). Furthermore, when considering the TL-l dataset, the processing time result was lower than the result that was obtained in Alwasel et al study [52].…”
Section: Discussioncontrasting
confidence: 70%
“…In the RL task with the 5 kg load, we obtained a 100% TPR value and a 97.4% TNR value (Table 4). In the study of Alwasel et al, a high accuracy was reached in distinguishing between safe and unsafe postures assumed by expert and inexpert masonry workers [52]. They implemented an SVM that was fed with inertial data of the whole kinematic chain.…”
Section: Discussionmentioning
confidence: 99%
“…In industrial environments, SVMs have been applied to classify and recognize the ergonomic posture of movement patterns [40]. In the last few years, activity recognition has usually been based on machine learning algorithms that are fed with inertial sensor data [38,52]. Alwasel et al proposed and validated an SVM algorithm that classified masonry workers' poses as a function of their experience, obtaining a high rate of accuracy 92.11% [52].…”
Section: Introductionmentioning
confidence: 99%
“…In the last few years, activity recognition has usually been based on machine learning algorithms that are fed with inertial sensor data [38,52]. Alwasel et al proposed and validated an SVM algorithm that classified masonry workers' poses as a function of their experience, obtaining a high rate of accuracy 92.11% [52]. In 2016, Ryu and colleagues tested the action recognition of masonry workers by using supervised learning algorithms, such as an SVM, a k-nearest neighbor (kNN) algorithm, and a neural network [53].…”
Ergonomics evaluation through measurements of biomechanical parameters in real time has a great potential in reducing non-fatal occupational injuries, such as work-related musculoskeletal disorders. Assuming a correct posture guarantees the avoidance of high stress on the back and on the lower extremities, while an incorrect posture increases spinal stress. Here, we propose a solution for the recognition of postural patterns through wearable sensors and machine-learning algorithms fed with kinematic data. Twenty-six healthy subjects equipped with eight wireless inertial measurement units (IMUs) performed manual material handling tasks, such as lifting and releasing small loads, with two postural patterns: correctly and incorrectly. Measurements of kinematic parameters, such as the range of motion of lower limb and lumbosacral joints, along with the displacement of the trunk with respect to the pelvis, were estimated from IMU measurements through a biomechanical model. Statistical differences were found for all kinematic parameters between the correct and the incorrect postures (p < 0.01). Moreover, with the weight increase of load in the lifting task, changes in hip and trunk kinematics were observed (p < 0.01). To automatically identify the two postures, a supervised machine-learning algorithm, a support vector machine, was trained, and an accuracy of 99.4% (specificity of 100%) was reached by using the measurements of all kinematic parameters as features. Meanwhile, an accuracy of 76.9% (specificity of 76.9%) was reached by using the measurements of kinematic parameters related to the trunk body segment.
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.