Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug 7;20(16):4414.
doi: 10.3390/s20164414.

An Evaluation of Posture Recognition Based on Intelligent Rapid Entire Body Assessment System for Determining Musculoskeletal Disorders

Ze Li  1 , Ruiqiu Zhang  1 , Ching-Hung Lee  2 , Yu-Chi Lee  1
Affiliations

An Evaluation of Posture Recognition Based on Intelligent Rapid Entire Body Assessment System for Determining Musculoskeletal Disorders

Ze Li et al. Sensors (Basel). .

Abstract

Determining the potential risks of musculoskeletal disorders through working postures in a workplace is expensive and time-consuming. A novel intelligent rapid entire body assessment (REBA) system based on convolutional pose machines (CPM), entitled the Quick Capture system, was applied to determine the risk levels. The aim of the study was to validate the feasibility and reliability of the CPM-based REBA system through a simulation experiment. The reliability was calculated from the differences of motion angles between the CPM-based REBA and a motion capture system. Results show the data collected by the Quick Capture system were consistent with those of the motion capture system; the average of root mean squared error (RMSE) was 4.77 and the average of Spearman's rho (ρ) correlation coefficient in the different 12 postures was 0.915. For feasibility evaluation, the linear weighted Cohen's kappa between the REBA score obtained by the Quick Capture system and those from the three experts were used. The result shows good agreement, with an average proportion agreement index (P0) of 0.952 and kappa of 0.738. The Quick Capture system does not only accurately analyze working posture, but also accurately determines risk level of musculoskeletal disorders. This study suggested that the Quick Capture system could be applied for a rapid and real-time on-site assessment.

Keywords: convolutional pose machines; ergonomics; musculoskeletal disorders (MSDs); posture analysis; rapid entire body assessment (REBA).

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure A1
Figure A1
The main interface of the Quick Capture system. Data collection and upload (a), and REBA online assessment report (b).
Figure A2
Figure A2
The detailed report of the Quick Capture system.
Figure 1
Figure 1
The system architecture of the Quick Capture system.
Figure 2
Figure 2
Human skeleton model provided by convolutional pose machines (CPM) (a), and the human skeleton model and joint point number required for evaluation (b).
Figure 3
Figure 3
Flow chart of the algorithm for calculating the posture score of upper arm.
Figure 4
Figure 4
Compared with the exposed area of the chest and the face in the reverse state, (a) shows the waist and the head twisted state; (b) shows the normal non-twisted state.
Figure 5
Figure 5
The normal status of the wrist (a) and the wrist flip status (b).
Figure 6
Figure 6
A screenshot of the interface for recording necessary data.
Figure 7
Figure 7
The 12 working posture using in the study.
Figure 8
Figure 8
The experimental setting of this study.
Figure 9
Figure 9
Human skeleton generated by Quick Capture system.
Figure 10
Figure 10
Comparison of REBA scores between experts and Quick Capture system evaluation. REBA grand scores (a), scores A (b), scores B (c). **: significant difference (p < 0.01); *: significant difference (p < 0.05).
See this image and copyright information in PMC

References

    1. Marras W.M., Cutlip R.G., Burt S.E., Waters T.R. National occupational research agenda (NORA) future directions in occupational musculoskeletal disorder health research. Appl. Ergon. 2009;40:15–22. doi: 10.1016/j.apergo.2008.01.018. - DOI - PubMed
    1. Vallati C., Virdis A., Gesi M., Carbonaro N., Tognetti A. ePhysio: A Wearables-Enabled Platform for the Remote Management of Musculoskeletal Diseases. Sensors. 2018;19:2. doi: 10.3390/s19010002. - DOI - PMC - PubMed
    1. Ferguson S.A., Marras W.S., Gary Allread W., Knapik G.G., Vandlen K.A., Splittstoesser R.E., Yang G. Musculoskeletal disorder risk as a function of vehicle rotation angle during assembly tasks. Appl. Ergon. 2011;42:699–709. doi: 10.1016/j.apergo.2010.11.004. - DOI - PubMed
    1. Nath N.D., Akhavian R., Behzadan A.H. Ergonomic analysis of construction worker’s body postures using wearable mobile sensors. Appl. Ergon. 2017;62:107–117. doi: 10.1016/j.apergo.2017.02.007. - DOI - PubMed
    1. Sutari W., Yekti Y.N.D., Astuti M.D., Sari Y.M. Analysis of working posture on muscular skeleton disorders of operator in stamp scraping in ‘batik cap’ industry. Procedia Manuf. 2015;4:133–138. doi: 10.1016/j.promfg.2015.11.023. - DOI