Search

Preventing work-related musculoskeletal disorders (WMSDs) is crucial in reducing their impact on individuals and society. However, the existing mainstream 2D image-based approach is insufficient in capturing the complex 3D movements and postures involved in many occupational tasks. To address this, an improved deep learning-based rapid entire body assessment (REBA) method has been proposed. The method takes working videos as input and automatically outputs the corresponding REBA score through 3D pose reconstruction. The proposed method achieves an average precision of 94.7% on real-world data, which is comparable to that of ergonomic experts. Furthermore, the method has the potential to be applied across a wide range of industries as it has demonstrated good generalisation in multiple scenarios. The proposed method offers a promising solution for automated and accurate risk assessment of WMSDs, with implications for various industries to ensure the safety and well-being of workers. PRACTITIONER SUMMARY: This paper proposes a deep learning-based improved rapid entire body assessment (REBA) method for assessing work-related musculoskeletal disorders (WMSDs) risks using 3D pose reconstruction from videos, achieving 94.7% precision, comparable to ergonomic experts, with potential applications across various industries. [ABSTRACT FROM AUTHOR]

Vacuum dewatering is a highly energy-intensive process that is widely adopted in industrial production such as papermaking and chemical manufacture. A significant portion of the energy consumed by vacuum system is converted into energy that drives airflow passing through the wet fiber web. During the energy conversion process, a part of the energy is wasted due to the redundant capacity of the vacuum pump, which is caused by the deviation of the airflow rate estimation during the design of the vacuum system. To improve the energy conversion rate, a variable porosity model (VPM) is proposed in this study to better simulate the process of airflow passing through a porous medium–wet fiber web. Compared with the existing constant porosity model (CPM), the VPM model takes the effect of wet fiber web compressibility into account to improve the accuracy of airflow rate calculation. Different sets of experimental data demonstrate that the accuracy of airflow calculation of the VPM is about 22 times that of the CPM. In addition, the characteristic parameterization of different fiber structures in this study expands the applicability of the model and can be widely adopted in multitudinous industrial fields, which is of great significance for improving the energy conversion rate of vacuum dewatering process and saving energy. [ABSTRACT FROM AUTHOR]

Analysis linking directly genomics, neuroimaging phenotypes and clinical measurements is crucial for understanding psychiatric disorders, but remains rare. Here, we describe a multi-scale analysis using genome-wide SNPs, gene expression, grey matter volume (GMV), and the positive and negative syndrome scale scores (PANSS) to explore the etiology of schizophrenia. With 72 drug-naive schizophrenic first episode patients (FEPs) and 73 matched heathy controls, we identified 108 genes, from schizophrenia risk genes, that correlated significantly with GMV, which are highly co-expressed in the brain during development. Among these 108 candidates, 19 distinct genes were found associated with 16 brain regions referred to as hot clusters (HCs), primarily in the frontal cortex, sensory-motor regions and temporal and parietal regions. The patients were subtyped into three groups with distinguishable PANSS scores by the GMV of the identified HCs. Furthermore, we found that HCs with common GMV among patient groups are related to genes that mostly mapped to pathways relevant to neural signaling, which are associated with the risk for schizophrenia. Our results provide an integrated view of how genetic variants may affect brain structures that lead to distinct disease phenotypes. The method of multi-scale analysis that was described in this research, may help to advance the understanding of the etiology of schizophrenia. [ABSTRACT FROM AUTHOR]