Postural Classification by Image Embedding and Transfer Learning: An Example of Using the OWAS Method in Motor-Manual Work to Automate the Process and Save Resources
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Sourcing
2.2. Manual Data Classification and Annotation
2.3. Classification by Embedding and Machine Learning
2.3.1. Software and Embedders Used
2.3.2. Workflow Used to Tune the Architecture and Hyperparameters of the Local Classifier
3. Results
3.1. Accuracy of the Models on the Posture Dataset
3.2. Accuracy of the Models on the Action Dataset
3.3. Model Performance on Unseen Data
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lundbäck, M.; Häggström, C.; Nordfjell, T. Worldwide trends in methods for harvesting and extracting industrial roundwood. Int. J. For. Eng. 2021, 32, 202–215. [Google Scholar] [CrossRef]
- Rhee, K.Y.; Choe, S.W.; Kim, Y.S.; Koo, K.H. The trend of occupational injuries in Korea from 2001 to 2010. Saf. Health Work 2013, 4, 63–70. [Google Scholar] [CrossRef] [PubMed]
- Social Security Office. Occupational Accident Statistics and Sicknesses. 2015. Available online: https://www.sso.go.th/wpr/assets/upload/files_storage/sso_th/32ad74534d1c43ed7e322128308ec49f.pdf (accessed on 2 August 2024).
- Noor, J.; Syafinie, M.; Marinah, M.; Najidah, M.; Juliana, Y.; Nasrul, A.A. Occupational accidents in forestry and agricultural sectors in Malaysia. Borneo J. Sci. Technol. 2021, 3, 16–19. [Google Scholar]
- Hălălisan, A.F.; Popa, B.; Borz, S.A.; Abrudan, I.V. Health and Safety Issues in Romanian Forests: Findings from FSC Certification Audits. Forest 2022, 13, 714. [Google Scholar] [CrossRef]
- Lindroos, O.; Burström, L. Accident rates and types amoung self-employed private forest owners. Accid. Anal. Prev. 2010, 42, 1729–1735. [Google Scholar] [CrossRef]
- Tsioras, P.A.; Khooshdonbat, M.; Nikooy, M.; Naghdi, R.; Heidari, M. The impact of body posture on heart rate strain during tree felling. Int. J. Environ. Res. Public Health 2022, 19, 11198. [Google Scholar] [CrossRef]
- Cheţa, M.; Marcu, M.V.; Borz, S.A. Workload, exposure to noise, and risk of musculoskeletal disorders: A case study of motor-manual tree feeling and processing in poplar clear cuts. Forests 2018, 9, 300. [Google Scholar] [CrossRef]
- Robb, W.; Zemánek, T.; Kaakkurivaara, N. An analysis of chainsaw operator safety between Asian and European countries. Croat. J. For. Eng. 2022, 43, 373–389. [Google Scholar] [CrossRef]
- David, G.C. Ergonomic methods for assessing exposure to risk of factors for work-related musculoskeletal disorders. Occup. Med. 2005, 55, 190–199. [Google Scholar] [CrossRef]
- Brandl, C.; Mertens, A.; Schlick, C.M. Effect of sampling interval on the reliability of ergonomic analysis using the Ovako working posture analysis system. Int. J. Ind. Ergon. 2017, 57, 68–73. [Google Scholar] [CrossRef]
- Castro Pérez, S.N.; Borz, S.A. Improving the Event-Based Classification Accuracy in Pit-Drilling Operations: An Application by Neural Networks and Median Filtering of the Acceleration Input Signal Data. Sensors 2021, 21, 6288. [Google Scholar] [CrossRef]
- Mathiassen, S.E. Diversity and variation in biomechanical exposure: What is it, and why would we like to know? Appl. Ergon. 2006, 37, 419–427. [Google Scholar] [CrossRef]
- Forkuo, G.O. A systematic survey of conventional and new postural assessment methods. Rev. Pădurilor 2022, 138, 1–34. [Google Scholar]
- Jiang, X.; Hu, Z.; Wang, S.; Zhang, Y. A survey on artificial intelligence in posture recognition. CMES-Comp. Model. Eng. 2023, 137, 35. [Google Scholar]
- Ma, N.; Wu, Z.; Cheung, Y.M.; Guo, Y.; Gao, Y.; Li, J.; Jiang, B. A survey of human action recognition and posture prediction. Tsinghua Sci. Technol. 2022, 27, 973–1001. [Google Scholar] [CrossRef]
- Zheng, C.; Wu, W.; Chen, C.; Yang, T.; Zhu, S.; Shen, J.; Kehtarnavaz, N.; Shah, M. Deep learning-based human pose estimation: A survey. ACM Comput. Surv. 2023, 56, 1–37. [Google Scholar] [CrossRef]
- Alzubaidi, L.; Zhang, J.; Humaidi, A.J.; Al-Dujaili, A.; Duan, Y.; Al-Shamma, O.; Santamaría, J.; Fadhel, M.A.; Al-Amidie, M.; Farhan, L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data 2021, 8, 53. [Google Scholar] [CrossRef]
- Pak, M.; Kim, S. A review of deep learning in image recognition. In Proceedings of the 2017 4th International Conference on Computer Applications and Information Processing Technology (CAIPT), Kuta Bali, Indonesia, 8–10 August 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 1–3. [Google Scholar]
- Raj, R.; Kos, A. An improved human activity recognition technique based on convolutional neural network. Sci. Rep. 2023, 13, 22581. [Google Scholar] [CrossRef]
- Zhang, J.; Cao, J.; Chang, J.; Li, X.; Liu, H.; Li, Z. Research on the application of computer vision based on deep learning in autonomous driving technology. arXiv 2024. [Google Scholar] [CrossRef]
- Zeiler, M.D.; Fergus, R. Visualizing and understanding convolutional networks. In Proceedings of the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, 6–12 September 2014; Proceedings, Part I 13. Springer International Publishing: Cham, Switzerland, 2014; Volume 8689, pp. 818–833. [Google Scholar]
- Talaat, A.S. Novel deep learning models for yoga pose estimator. SN Appl. Sci. 2023, 5, 341. [Google Scholar] [CrossRef]
- Upadhyay, A.; Basha, N.K.; Ananthakrishnan, B. Deep learning-based yoga posture recognition using the Y_PN-MSSD model for yoga practitioners. Healthcare 2023, 11, 609. [Google Scholar] [CrossRef]
- Acharya, A. 9 Ways to Balance Your Computer Vision Dataset. Encord. 2023. Available online: https://encord.com/blog/balance-computer-vision-datasets/ (accessed on 11 February 2025).
- Ali, A.; Shamsuddin, S.M.; Ralescu, A.L. Classification with class imbalance problem. Int. J. Adv. Soft Comput. Appl. 2013, 5, 176–204. [Google Scholar]
- Leevy, J.L.; Khoshgoftaar, T.M.; Bauder, R.A.; Seliya, N. A survey on addressing high-class imbalance in big data. J. Big Data 2018, 5, 42. [Google Scholar] [CrossRef]
- Shorten, C.; Khoshgoftaar, T.M. A survey on image data augmentation for deep learning. J. Big Data 2019, 6, 60. [Google Scholar] [CrossRef]
- Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–1359. [Google Scholar] [CrossRef]
- Shao, L.; Zhu, F.; Li, X. Transfer learning for visual categorization: A survey. IEEE Trans. Neural Netw. Learn. Syst. 2014, 26, 1019–1034. [Google Scholar] [CrossRef]
- Weiss, K.; Khoshgoftaar, T.M.; Wang, D. A survey of transfer learning. J. Big Data 2016, 3, 9. [Google Scholar] [CrossRef]
- Borz, S.A.; Iordache, E.; Marcu, M.V. Enhancing working posture comparability in forest operations by the use of similarity metrics. Forests 2021, 12, 926. [Google Scholar] [CrossRef]
- Calvo, A. Musculoskeletal disorders (MSD) risks in forestry: A case study to propose an analysis method. Agric. Eng. Int. CIGR J. 2009, 11, 1–9. [Google Scholar]
- Justavino, F.C.; Ramirez, R.J.; Perez, N.M.; Borz, S.A. The use of OWAS in forest operations postural assessment: Advantages and limitations. Bull. Trans. Univ. Bras. Ser. II For. Wood Ind. Agr. Food Eng. 2015, 8, 7–16. [Google Scholar]
- Marogel-Popa, T.; Marcu, M.V.; Borz, S.A. Postural risk in manual planting operations of poplar: Two options compared. Sustainability 2020, 12, 5531. [Google Scholar] [CrossRef]
- Zanuttini, R.; Cielo, P.; Poncino, D. The OWAS Method. Preliminary results for the evaluation of the risk of work-related musculo-skeletrical disorders (WMSD) in the forestry sector in Italy. Forest 2005, 2, 242–255. [Google Scholar] [CrossRef]
- Vallabhaneni, N.; Prabhavathy, P. Segmentation quality assessment network-based object detection and optimized CNN with transfer learning for yoga pose classification for health care. Soft Comput. 2023, 28, 743. [Google Scholar] [CrossRef]
- Godec, P.; Pančur, M.; Ilenič, N.; Čopar, A.; Stražar, M.; Erjavec, A.; Pretnar, A.; Demšar, J.; Starič, A.; Toplak, M.; et al. Democratized image analytics by visual programming through integration of deep models and small-scale machine learning. Nat. Commun. 2019, 10, 4551. [Google Scholar] [CrossRef] [PubMed]
- Cen, F.; Zhao, X.; Li, W.; Wang, G. Deep feature augmentation for occluded image classification. Pattern Recognit. 2021, 111, 107737. [Google Scholar] [CrossRef]
- Kortylewski, A.; Liu, Q.; Wang, H.; Zhang, Z.; Yuille, A. Combining compositional models and deep networks for robust object classification under occlusion. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass, CO, USA, 1–5 March 2020; pp. 1322–1330. [Google Scholar]
- Kaakkurivaara, N.; Kaakkurivaara, T.; Ketkaew, C.; Sakulya, T.; Borz, S.A. Modelling productivity in extraction operations by simulations based on GNSS documented data: An example from skidding teak wood in Thailand. Bull. Trans. Univ. Brasov Series II For. Wood Ind. Agr. Food Eng. 2022, 15, 13–32. [Google Scholar] [CrossRef]
- Karhu, O.; Kansi, P.; Kuorinka, I. Correcting working postures in industry: A practical method for analysis. Appl. Ergon. 1977, 8, 199–201. [Google Scholar] [CrossRef] [PubMed]
- Spinelli, R.; Aminti, G.; De Francesco, F. Postural risk assessment of mechanised firewood processing. Ergonomics 2016, 60, 375–383. [Google Scholar] [CrossRef]
- Kivi, P.; Mattila, M. Analysis and improvement of work postures in the building industry: Application of the computerised OWAS method. Appl. Ergon. 1991, 22, 43–48. [Google Scholar] [CrossRef]
- Mattila, M.; Karwowski, W.; Vilkki, M. Analysis of working postures in hammering tasks on building construction sites using the computerized OWAS method. Appl. Ergon. 1993, 24, 405–412. [Google Scholar] [CrossRef] [PubMed]
- Lins, C.; Fudickar, S.; Hein, A. OWAS inter-rater reliability. Appl. Ergon. 2021, 93, 103357. [Google Scholar] [CrossRef]
- Janowitz, I.L.; Gillen, M.; Ryan, G.; Rempel, D.; Trupin, L.; Swig, L.; Mullen, K.; Rugulies, R.; Blanc, P.D. Measuring the physical demands of work in hospital settings: Design and implementation of an ergonomics assessment. Appl. Ergon. 2006, 37, 641–658. [Google Scholar] [CrossRef] [PubMed]
- Demšar, J.; Curk, T.; Erjavec, A.; Gorup, Č.; Hočevar, T.; Milutinovič, M.; Možina, M.; Polajnar, M.; Toplak, M.; Starič, A.; et al. Orange: Data mining toolbox in Python. J. Mach. Learn. Res. 2013, 14, 2349–2353. [Google Scholar]
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2818–2826. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014. [Google Scholar] [CrossRef]
- Almagro Armenteros, J.J.; Sønderby, C.K.; Sønderby, S.K.; Nielsen, H.; Winther, O. DeepLoc: Prediction of protein subcellular localization using deep learning. Bioinformatics 2017, 33, 3387–3395. [Google Scholar] [CrossRef]
- Baltrušaitis, T.; Robinson, P.; Morency, L.P. Openface: An open source facial behavior analysis toolkit. In Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 7–10 March 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 1–10. [Google Scholar]
- Chen, L.; Li, S.; Bai, Q.; Yang, J.; Jiang, S.; Miao, Y. Review of image classification algorithms based on convolutional neural networks. Remote Sens. 2021, 13, 4712. [Google Scholar] [CrossRef]
- Ogundokun, R.O.; Maskeliūnas, R.; Damaševičius, R. Human posture detection using image augmentation and hyperparameter-optimized transfer learning algorithms. Appl. Sci. 2022, 12, 10156. [Google Scholar] [CrossRef]
- Iandola, F.N.; Han, S.; Moskewicz, M.W.; Ashraf, K.; Dally, W.J.; Keutzer, K. SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size. arXiv, 2016. [Google Scholar] [CrossRef]
- Çalışkan, A. Detecting human activity types from 3D posture data using deep learning models. Biomed. Signal Process. Control 2023, 81, 104479. [Google Scholar]
- Han, S.; Mao, H.; Dally, W.J. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv 2015. [Google Scholar] [CrossRef]
- Maas, A.L.; Hannun, A.Y.; Ng, A.Y. Rectifier nonlinearities improve neural network acoustic models. In Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16–21 June 2013; Volume 30, p. 3. [Google Scholar]
- Nair, V.; Hinton, G.E. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, 21–24 June 2010; pp. 807–814. [Google Scholar]
- Kingma, D.P.; Ba, J.L. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015. [Google Scholar] [CrossRef]
- Varying Regularization in Multi-Layer Perceptrons. 2024. Available online: https://scikit-learn.org/stable/auto_examples/neural_networks/plot_mlp_alpha.html#sphx-glr-auto-examples-neural-networks-plot-mlp-alpha-py (accessed on 13 November 2024).
- Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett. 2006, 27, 861–874. [Google Scholar] [CrossRef]
- Kamilaris, A.; Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90. [Google Scholar] [CrossRef]
- Wang, S.; Liu, W.; Wu, J.; Cao, L.; Meng, Q.; Kennedy, P.J. Training deep neural networks on imbalanced data sets. In Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 24–29 July 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 4368–4374. [Google Scholar]
- Grandini, M.; Bagli, E.; Visani, G. Metrics for multi-class classification: An overview. arXiv 2020. [Google Scholar] [CrossRef]
- Joshi, K.; Tripathi, V.; Bose, C.; Bhardwaj, C. Robust sports image classification using InceptionV3 and neural networks. Procedia Comput. Sci. 2020, 167, 2374–2381. [Google Scholar] [CrossRef]
- Tiwari, R.G.; Misra, A.; Ujjwal, N. Image embedding and classification using pre-trained deep learning architectures. In Proceedings of the 8th International Conference on Signal Processing and Communication (ICSC) Noida, India, 1–3 December 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 125–130. [Google Scholar]
- Brownlee, J. Data Preparation for Machine Learning: Data Cleaning, Feature Selection, and Data Transforms in Python. Machine Learning Mastery. 2020. Available online: https://tinyurl.com/yfznxsdn (accessed on 4 November 2024).
- Buda, M.; Maki, A.; Mazurowski, M.A. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 2018, 106, 249–259. [Google Scholar] [CrossRef]
- Kubat, M.; Holte, R.; Matwin, S. Learning when negative examples abound. In Proceedings of the Machine Learning: ECML-97: 9th European Conference on Machine Learning Prague, Czech Republic, 23–25 April 1997; Proceedings 9. Springer: Berlin/Heidelberg, Germany, 1997; pp. 146–153. [Google Scholar]
- Japkowicz, N.; Stephen, S. The class imbalance problem: A systematic study. Intell. Data Anal. 2002, 6, 429–449. [Google Scholar] [CrossRef]
- Saini, M.; Susan, S. Tackling class imbalance in computer vision: A contemporary review. Artif. Intell. Rev. 2023, 56, 1279–1335. [Google Scholar] [CrossRef]
- Ghosh, K.; Bellinger, C.; Corizzo, R.; Branco, P.; Krawczyk, B.; Japkowicz, N. The class imbalance problem in deep learning. Mach. Learn. 2024, 113, 4845–4901. [Google Scholar] [CrossRef]
- Mera, C.; Orozco-Alzate, M.; Branch, J. Improving representation of the positive class in imbalanced multiple-instance learning. In Proceedings of the Image Analysis and Recognition: 11th International Conference, ICIAR 2014, Vilamoura, Portugal, 22–24 October 2014; Proceedings, Part I 11. Springer International Publishing: Cham, Switzerland, 2014; pp. 266–273. [Google Scholar]
- Napierala, K.; Stefanowski, J. Types of minority class examples and their influence on learning classifiers from imbalanced data. J. Intell. Inf. Syst. 2016, 46, 563–597. [Google Scholar] [CrossRef]
- Ahmed, E.; Saint, A.; Shabayek, A.E.R.; Cherenkova, K.; Das, R.; Gusev, G.; Aouada, D.; Ottersten, B. A survey on deep learning advances on different 3D data representations. arXiv 2018. [Google Scholar] [CrossRef]
- Felzenszwalb, P.F.; Girshick, R.B.; McAllester, D.; Ramanan, D. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 2009, 32, 1627–1645. [Google Scholar] [CrossRef]
- Ghiasi, G.; Yang, Y.; Ramanan, D.; Fowlkes, C.C. Parsing occluded people. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 2401–2408. [Google Scholar]
- Rafi, U.; Gall, J.; Leibe, B. A semantic occlusion model for human pose estimation from a single depth image. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA, 7–12 June 2015; pp. 67–74. [Google Scholar]
- Bulusu, S.; Kailkhura, B.; Li, B.; Varshney, P.K.; Song, D. Anomalous example detection in deep learning: A survey. IEEE Access 2020, 8, 132330–132347. [Google Scholar] [CrossRef]
- Hendrycks, D.; Dietterich, T. Benchmarking neural network robustness to common corruptions and perturbations. arXiv 2019. [Google Scholar] [CrossRef]
- Mehra, A.; Zhang, Y.; Hamm, J. Test-time assessment of a model’s performance on unseen domains via optimal transport. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 173–182. [Google Scholar]
- Polyzotis, N.; Roy, S.; Whang, S.E.; Zinkevich, M. Data management challenges in production machine learning. In Proceedings of the 2017 ACM International Conference on Management of Data, Chicago, IL, USA, 14–19 May 2017; pp. 1723–1726. [Google Scholar]
- Borz, S.A.; Papandrea, S.F.; Marcu, M.V.; Bacenetti, J.; Proto, A.R. Postural assessment of three wood measurement options by the owas method: Digital solutions seem to be better. Forests 2022, 13, 2007. [Google Scholar] [CrossRef]
- Osqueizadeh, R.; Bandpei, M.A.M.; Rahmani, N.; Goudarzi, H.R.; Ebadi, A. Reliability and validity of observational methods for postural load assessment: An updated systematic review. J. Health Scope 2023, 12, e137573. [Google Scholar] [CrossRef]
- Eliasson, K.; Palm, P.; Nyman, T.; Forsman, M. Inter-and intra-observer reliability of risk assessment of repetitive work without an explicit method. Appl. Ergon. 2017, 62, 1–8. [Google Scholar] [CrossRef] [PubMed]
- Rhén, I.M.; Forsman, M. Inter-and intra-rater reliability of the OCRA checklist method in video-recorded manual work tasks. Appl. Ergon. 2020, 84, 103025. [Google Scholar] [CrossRef]
- Chaparro-Rico, B.D.; Cafolla, D. Test-retest, inter-rater and intra-rater reliability for spatiotemporal gait parameters using SANE (an eaSy gAit aNalysis systEm) as measuring instrument. Appl. Sci. 2020, 10, 5781. [Google Scholar] [CrossRef]
- Boland, D.M.; Neufeld, E.V.; Ruddell, J.; Dolezal, B.A.; Cooper, C.B. Inter-and intra-rater agreement of static posture analysis using a mobile application. J. Phys. Ther. Sci. 2016, 28, 3398–3402. [Google Scholar] [CrossRef]
- Chollet, F. Deep Learning with Python; Manning Publication Co.: Shelter Island, NY, USA, 2021. [Google Scholar]
- Staples, M.; Zhu, L.; Grundy, J. Continuous validation for data analytics systems. In Proceedings of the 38th International Conference on Software Engineering Companion, Austin, TX, USA, 14–22 May 2016; pp. 769–772. [Google Scholar]
- Bergstra, J.; Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 2012, 13, 281–305. [Google Scholar]
- Bergstra, J.; Yamins, D.; Cox, D. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In Proceedings of the International Conference on Machine Learning, PMLR, Atlanta GA USA, 16–21 June 2013; pp. 115–123. [Google Scholar]
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Ruder, S. An overview of gradient descent optimization algorithms. arXiv 2016. [Google Scholar] [CrossRef]
Action Category Code | Description | Absolute Frequency (n) | Relative Frequency (n/N × 100) |
---|---|---|---|
1 | No corrective action is needed. | 80 | 1.6 |
2 | Corrective actions are needed in the near future. | 1849 | 36.9 |
3 | Corrective actions are needed as soon as possible. | 125 | 2.5 |
4 | Corrective actions are required immediately. | 2951 | 59.0 |
Total (N) | - | 5001 | 100.0 |
Model | Description and Main Parameters | Posture or Action Category | Number of Instances | Correct Predictions | Classification Accuracy |
---|---|---|---|---|---|
1 | Inception V3, Postural data, 2 hidden layers, 1000 neurons each, and α = 0.0001 | 1131 | 3 | 0 | 0.0 |
2141 | 7 | 2 | 28.6 | ||
2171 | 76 | 4 | 5.3 | ||
2271 | 11 | 0 | 0.0 | ||
3121 | 4 | 0 | 0.0 | ||
3141 | 14 | 0 | 0.0 | ||
3171 | 8 | 0 | 0.0 | ||
4131 | 20 | 0 | 0.0 | ||
4141 | 203 | 174 | 85.7 | ||
4151 | 21 | 0 | 0.0 | ||
4171 | 30 | 15 | 50.0 | ||
Overall | 397 | 195 | 49.1 | ||
2 | SqueezeNet, Postural data, 2 hidden layers, 1000 neurons each, and α = 0.001 | 1131 | 3 | 0 | 0.0 |
2141 | 7 | 0 | 0.0 | ||
2171 | 76 | 19 | 25.0 | ||
2271 | 11 | 0 | 0.0 | ||
3121 | 4 | 0 | 0.0 | ||
3141 | 14 | 0 | 0.0 | ||
3171 | 8 | 0 | 0.0 | ||
4131 | 20 | 0 | 0.0 | ||
4141 | 203 | 161 | 79.3 | ||
4151 | 21 | 6 | 28.6 | ||
4171 | 30 | 21 | 30.0 | ||
Overall | 397 | 207 | 52.1 | ||
3 | Inception V3, Action data, 1 hidden layer, 1000 neurons each, and α = 0.001 | 1 | 24 | 0 | 0.0 |
2 | 137 | 44 | 32.1 | ||
3 | 21 | 0 | 0.0 | ||
4 | 224 | 161 | 71.9 | ||
Overall | 406 | 205 | 50.5 | ||
4 | SqueezeNet, Action data, 3 hidden layers, 1000 neurons each, and α = 0.001 | 1 | 24 | 0 | 0.0 |
2 | 137 | 102 | 74.5 | ||
3 | 21 | 2 | 1.0 | ||
4 | 224 | 139 | 62.1 | ||
Overall | 406 | 243 | 59.9 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Forkuo, G.O.; Borz, S.A.; Kaakkurivaara, T.; Kaakkurivaara, N. Postural Classification by Image Embedding and Transfer Learning: An Example of Using the OWAS Method in Motor-Manual Work to Automate the Process and Save Resources. Forests 2025, 16, 492. https://doi.org/10.3390/f16030492
Forkuo GO, Borz SA, Kaakkurivaara T, Kaakkurivaara N. Postural Classification by Image Embedding and Transfer Learning: An Example of Using the OWAS Method in Motor-Manual Work to Automate the Process and Save Resources. Forests. 2025; 16(3):492. https://doi.org/10.3390/f16030492
Chicago/Turabian StyleForkuo, Gabriel Osei, Stelian Alexandru Borz, Tomi Kaakkurivaara, and Nopparat Kaakkurivaara. 2025. "Postural Classification by Image Embedding and Transfer Learning: An Example of Using the OWAS Method in Motor-Manual Work to Automate the Process and Save Resources" Forests 16, no. 3: 492. https://doi.org/10.3390/f16030492
APA StyleForkuo, G. O., Borz, S. A., Kaakkurivaara, T., & Kaakkurivaara, N. (2025). Postural Classification by Image Embedding and Transfer Learning: An Example of Using the OWAS Method in Motor-Manual Work to Automate the Process and Save Resources. Forests, 16(3), 492. https://doi.org/10.3390/f16030492