Automated Workers’ Ergonomic Risk Assessment in Manual Material Handling Using sEMG Wearable Sensors and Machine Learning

Abstract

Manual material handling tasks have the potential to be highly unsafe from an ergonomic viewpoint. Safety inspections to monitor body postures can help mitigate ergonomic risks of material handling. However, the real effect of awkward muscle movements, strains, and excessive forces that may result in an injury may not be identified by external cues. This paper evaluates the ability of surface electromyogram (EMG)-based systems together with machine learning algorithms to automatically detect body movements that may harm muscles in material handling. The analysis utilized a lifting equation developed by the U.S. National Institute for Occupational Safety and Health (NIOSH). This equation determines a Recommended Weight Limit, which suggests the maximum acceptable weight that a healthy worker can lift and carry, as well as a Lifting Index value to assess the risk extent. Four different machine learning models, namely Decision Tree, Support Vector Machine, K-Nearest Neighbor, and Random Forest are developed to classify the risk assessments calculated based on the NIOSH lifting equation. The sensitivity of the models to various parameters is also evaluated to find the best performance using each algorithm. Results indicate that Decision Tree models have the potential to predict the risk level with close to 99.35% accuracy.

Prediction of COVID-19 manipulation by selective ACE inhibitory compounds of Potentilla reptant root: In silico study and ADMET profile

“…The many previous studies have indicated medicinal plants and natural products exert beneficial effects in treatment of COVID-19 ( Din et al, 2020 , Hashem-Dabaghian et al, 2021 , Monfared et al, 2020 ), and also, they demonstrated the hopeful ACE inhibitory activity ( Caballero, 2020 ). In this perspective, a growing body of evidence indicates that Potentilla reptans L. (Rosaceae) can rescue heart dysfunction, oxidative stress, cardiac arrhythmias and apoptosis through inhibiting ROS, glucocorticoid regulated kinase-1 (SGK1), glycogen synthase kinase 3β (GSK-3β), BAX and caspase3 regards to increasing Nrf2, SOD, CAT, NO, BCl-2 and improving cardiac hemodynamic function ( Enayati et al, 2021 , Enayati et al, 2019 , Enayati et al, 2018 , Enayati, xxxx , Wu et al, 2021 , Qi et al, 2022 , Antoine et al, 2022 , Mudiyanselage et al, 2021 ).…”

Nanomagnetic macrocyclic Schiff-base–Mn(ii) complex: an efficient heterogeneous catalyst for click approach synthesis of novel β-substitued-1,2,3-triazoles

“…[43][44][45] Along these lines, designing and nding stable and highly active catalysts are considered as two main targets of the green chemistry objectives. [46][47][48][49][50] Recently, there has been an outstanding attention to chemical processes involving heterogeneous catalysts with extraordinary activity, high surface area to volume and good recyclability. 51,52 Heterogenized catalytic complexes are new organic-inorganic hybrid compounds prepared from metallic ions and organic linkers, bonded to the surface of inorganic insoluble nanomaterials.…”

A Logistic Regression Model for Biomechanical Risk Classification in Lifting Tasks

“…Mudiyanselage et al [ 48 ] used 2 wireless sEMG muscle sensors placed on thoracic and multifidus muscles to acquire sEMG and therefore to extract some features to feed several ML algorithms, reaching an accuracy greater than 98%. In their work [ 48 ], the authors solved the problems of the portability of the system in the workplace while using sEMG—well studied signals in occupational ergonomics but were more prone to noises compared to inertial signals.…”

“…Mudiyanselage et al [ 48 ] used 2 wireless sEMG muscle sensors placed on thoracic and multifidus muscles to acquire sEMG and therefore to extract some features to feed several ML algorithms, reaching an accuracy greater than 98%. In their work [ 48 ], the authors solved the problems of the portability of the system in the workplace while using sEMG—well studied signals in occupational ergonomics but were more prone to noises compared to inertial signals. On the same line of Mudiyanselage et al, Donisi et al [ 49 ] proposed a biomechanical risk classification according to the RNLE using tree-based machine learning algorithms fed with time and frequency domains features extracted from bicep sEMG during lifting activities.…”