Assessing ergonomics and biomechanical risk in manual handling of loads through a wearable system

Conforti, Ilaria; Mileti, Ilaria; Prete, Zaccaria Del; Palermo, Eduardo

doi:10.1109/metroi4.2019.8792843

Cited by 10 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the main effect of weight, we found no significance for the AP and V components of the pl PT trk vector, and we could not quantify a dependency on the weight increase of load. Only for the ML component was a dependency on the weight observed, despite the results of a previous analysis on the kinematic parameters of the trunk [43]. As shown in Table 1, we observed small differences in the CLL and CRL tasks, while we found an increase of the mean value related to the increase of load in the ILL and the IRL tasks.…”

Section: Discussioncontrasting

confidence: 82%

“…Furthermore, interesting results were found for the RoM of the hip joint, as demonstrated by the statistical analysis. According to the previous results on the hip joint [43], we could confirm the effects that were related to the weight increase of the load on this parameters (on both sides) for the two tasks. These results allow us to reaffirm the necessity to include lower limb segments in the ergonomic evaluation of MMH tasks.…”

Section: Discussionsupporting

confidence: 68%

“…These observations underline the need for relying on measurements of posture parameters in the workplace. Our biomechanical model and our wearable setup allowed for a reliable measurement of these parameters, quantifying important movement variables of the two considered postural patterns on the lower limbs, as highlighted in the results of our previous study [43]. By increasing the number of subjects, we obtained significance for all considered kinematic parameters in the main effect of posture.…”

Section: Discussionmentioning

confidence: 64%

“…In fact, in our previous work, a dependency on the weight of kinematic parameters related to the lower limbs during the manual handling of small loads was found. This result highlighted the necessity to assess lower extremity motion despite the use of small setups, especially in the real-time evaluation of postural patterns [43].…”

Section: Introductionmentioning

confidence: 98%

“…Wearable devices, like inertial measurement units (IMUs), represent the most suitable technologic solution for gathering reliable measurements of kinematic parameters and performing motion analysis in a real manufacturing scenario. In clinics, sports, daily life activities, and industrial applications, the adoption of IMUs has enabled promising results [40][41][42][43].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Measuring Biomechanical Risk in Lifting Load Tasks Through Wearable System and Machine-Learning Approach

Conforti

Mileti

Prete

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussioncontrasting

confidence: 82%

Section: Discussionsupporting

confidence: 68%

Section: Discussionmentioning

confidence: 64%

Section: Introductionmentioning

confidence: 98%