Classification of body postures using smart workwear
Abstract Background Despite advancing automation, employees in many industrial and service occupations still have to perform physically intensive work that may have negative effects on the health of the musculoskeletal system. For targeted preventive measures, precise knowledge of the work postures...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-10-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-022-05821-9 |
| _version_ | 1797986038927327232 |
|---|---|
| author | Christian Lins Andreas Hein |
| author_facet | Christian Lins Andreas Hein |
| author_sort | Christian Lins |
| collection | DOAJ |
| description | Abstract Background Despite advancing automation, employees in many industrial and service occupations still have to perform physically intensive work that may have negative effects on the health of the musculoskeletal system. For targeted preventive measures, precise knowledge of the work postures and movements performed is necessary. Methods Prototype smart work clothes equipped with 15 inertial sensors were used to record reference body postures of 20 subjects. These reference postures were used to create a software-based posture classifier according to the Ovako Working Posture Analysing System (OWAS) by means of an evolutionary training algorithm. Results A total of 111,275 posture shots were recorded and used for training the classifier. The results show that smart workwear, with the help of evolutionary trained software classifiers, is in principle capable of detecting harmful postures of its wearer. The detection rate of the evolutionary trained classifier ( $$\bar{a}_{ccr} = 0.35$$ a ¯ ccr = 0.35 for the postures of the back, $$\bar{a}_{ccr} = 0.64$$ a ¯ ccr = 0.64 for the arms, and $$\bar{a}_{ccr} = 0.25$$ a ¯ ccr = 0.25 for the legs) outperforms that of a TensorFlow trained classifying neural network. Conclusions In principle, smart workwear – as prototypically shown in this paper – can be a helpful tool for assessing an individual’s risk for work-related musculoskeletal disorders. Numerous potential sources of error have been identified that can affect the detection accuracy of software classifiers required for this purpose. |
| first_indexed | 2024-04-11T07:26:48Z |
| format | Article |
| id | doaj.art-b4bd078237db46f7906d6ea45e2482ff |
| institution | Directory Open Access Journal |
| issn | 1471-2474 |
| language | English |
| last_indexed | 2024-04-11T07:26:48Z |
| publishDate | 2022-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj.art-b4bd078237db46f7906d6ea45e2482ff2022-12-22T04:37:02ZengBMCBMC Musculoskeletal Disorders1471-24742022-10-0123111810.1186/s12891-022-05821-9Classification of body postures using smart workwearChristian Lins0Andreas Hein1Department of Computer Science, Hamburg University of Applied SciencesDepartment of Health Services Research, Carl von Ossietzky University OldenburgAbstract Background Despite advancing automation, employees in many industrial and service occupations still have to perform physically intensive work that may have negative effects on the health of the musculoskeletal system. For targeted preventive measures, precise knowledge of the work postures and movements performed is necessary. Methods Prototype smart work clothes equipped with 15 inertial sensors were used to record reference body postures of 20 subjects. These reference postures were used to create a software-based posture classifier according to the Ovako Working Posture Analysing System (OWAS) by means of an evolutionary training algorithm. Results A total of 111,275 posture shots were recorded and used for training the classifier. The results show that smart workwear, with the help of evolutionary trained software classifiers, is in principle capable of detecting harmful postures of its wearer. The detection rate of the evolutionary trained classifier ( $$\bar{a}_{ccr} = 0.35$$ a ¯ ccr = 0.35 for the postures of the back, $$\bar{a}_{ccr} = 0.64$$ a ¯ ccr = 0.64 for the arms, and $$\bar{a}_{ccr} = 0.25$$ a ¯ ccr = 0.25 for the legs) outperforms that of a TensorFlow trained classifying neural network. Conclusions In principle, smart workwear – as prototypically shown in this paper – can be a helpful tool for assessing an individual’s risk for work-related musculoskeletal disorders. Numerous potential sources of error have been identified that can affect the detection accuracy of software classifiers required for this purpose.https://doi.org/10.1186/s12891-022-05821-9Non-neutral posturesWork-related musculoskeletal disordersInertial sensorsNeuroevolution |
| spellingShingle | Christian Lins Andreas Hein Classification of body postures using smart workwear BMC Musculoskeletal Disorders Non-neutral postures Work-related musculoskeletal disorders Inertial sensors Neuroevolution |
| title | Classification of body postures using smart workwear |
| title_full | Classification of body postures using smart workwear |
| title_fullStr | Classification of body postures using smart workwear |
| title_full_unstemmed | Classification of body postures using smart workwear |
| title_short | Classification of body postures using smart workwear |
| title_sort | classification of body postures using smart workwear |
| topic | Non-neutral postures Work-related musculoskeletal disorders Inertial sensors Neuroevolution |
| url | https://doi.org/10.1186/s12891-022-05821-9 |
| work_keys_str_mv | AT christianlins classificationofbodyposturesusingsmartworkwear AT andreashein classificationofbodyposturesusingsmartworkwear |