Application of machine classification learning models based on factor space mathematical theory in higher vocational education from a biomechanical perspective
Abstract
With the rapid advancement of biomechanical research and educational big data, there is a growing need to integrate sophisticated analytical tools to enhance the understanding of human movement, learning behaviors, and their interactions. Traditional machine learning models often fall short in capturing the complex, multi-dimensional relationships inherent in biomechanical and educational datasets, leading to limited precision, inadequate personalization, and poor generalization capabilities, which restrict their applicability in dynamic teaching environments. To address these challenges, this paper proposes a machine learning model based on Factor Space Mathematical Theory integrated with the extreme gradient boosting (XGBoost) algorithm. By leveraging Factor Space Mathematical Theory, the model effectively captures the multi-dimensional characteristics of biomechanical and educational data, addressing the oversimplification and unidimensional nature of traditional models. Moreover, with the robust classification and prediction performance of XGBoost, the proposed model enhances the ability to generalize and process complex educational data. Experimental results demonstrate that the proposed model achieves an accuracy of 0.92 and an F1 score of 0.90 in predicting students’ biomechanical performance metrics, such as gait analysis and posture stability, which are critical for understanding learning behaviors in physical education and vocational training. The model outperforms the standalone XGBoost model by a significant margin of 0.05 in accuracy. Additionally, MSE analysis across diverse datasets reveals no evidence of overfitting, further validating the model’s strong generalization capabilities. This study highlights the effectiveness of combining Factor Space Theory with XGBoost, offering improved accuracy, operational efficiency, and adaptability in biomechanical data analysis and educational behavior prediction. The findings provide a novel perspective and practical approach to advancing biomechanical research and its application in educational reform, particularly in higher vocational education.
References
1. Mason G. Higher education, initial vocational education and training and continuing education and training: Where should the balance lie. Journal of Education and Work. 2020; 33(7–8): 468–490.
2. Hariri RH, Fredericks EM, Bowers KM. Uncertainty in big data analytics: Survey, opportunities, and challenges. Journal of Big Data. 2019; 6(1): 1–16.
3. Holmes W, Tuomi I. State of the art and practice in AI in education. European Journal of Education. 2022; 57(4): 542–570.
4. Luan H, Tsai CC. A review of using machine learning approaches for precision education. Educational Technology & Society. 2021; 24(1): 250–266.
5. Marques LS, Gresse von Wangenheim C, Hauck JCR. Teaching machine learning in school: A systematic mapping of the state of the art. Informatics in Education. 2020; 19(2): 283–321.
6. James CA, Wheelock KM, Woolliscroft JO. Machine learning: The next paradigm shift in medical education. Academic Medicine. 2021; 96(7): 954–957.
7. Berens J, Schneider K, Gortz S, et al. Early Detection of Students at Risk--Predicting Student Dropouts Using Administrative Student Data from German Universities and Machine Learning Methods. Journal of Educational Data Mining. 2019; 11(3): 1–41.
8. Ikawati Y, Al Rasyid MUH, Winarno I. Student behavior analysis to predict learning styles based felder silverman model using ensemble tree method. EMITTER International Journal of Engineering Technology. 2021; 9(1): 92–106.
9. Ouatik F, Erritali M, Ouatik F, Jourhmane M. Predicting student success using big data and machine learning algorithms. International Journal of Emerging Technologies in Learning (iJET). 2022; 17(12): 236–251.
10. Wu TK, Huang SC, Meng YR. Evaluation of ANN and SVM classifiers as predictors to the diagnosis of students with learning disabilities. Expert Systems with Applications. 2008; 34(3): 1846–1856.
11. Amin S, Uddin MI, Mashwani WK, et al. Developing a personalized E-learning and MOOC recommender system in IoT-enabled smart education. IEEE Access. 2023; 11: 136437–136455.
12. Alshurafat H, Al Shbail MO, Masadeh WM, et al. Factors affecting online accounting education during the COVID-19 pandemic: An integrated perspective of social capital theory, the theory of reasoned action and the technology acceptance model. Education and Information Technologies. 2021; 26(6): 6995–7013.
13. Delen D, Topuz K, Eryarsoy E. Development of a Bayesian Belief Network-based DSS for predicting and understanding freshmen student attrition. European journal of operational research. 2020; 281(3): 575–587.
14. Li R, Du C, Du W, et al. Research on comprehensive evaluation model of physical education teaching quality based on multivariate data. Journal of Sport Psychology. 2022; 31(1): 235–244.
15. Godwin A, Benedict B, Rohde J, et al. New epistemological perspectives on quantitative methods: An example using topological data analysis. Studies in Engineering Education. 2021; 2(1): 16–34.
16. Mubarak AA, Cao H, Hezam IM, Hao F. Modeling students’ performance using graph convolutional networks. Complex & Intelligent Systems. 2022; 8(3): 2183–2201.
17. Yakubu MN, Dasuki SI. Factors affecting the adoption of e-learning technologies among higher education students in Nigeria: A structural equation modelling approach. Information Development. 2019; 35(3): 492–502.
18. Osman AIA, Ahmed AN, Chow MF, et al. Extreme gradient boosting (XGBoost) model to predict the groundwater levels in Selangor Malaysia. Ain Shams Engineering Journal. 2021; 12(2): 1545–1556.
19. Kavzoglu T, Teke A. Predictive Performances of ensemble machine learning algorithms in landslide susceptibility mapping using random forest, extreme gradient boosting (XGBoost) and natural gradient boosting (NGBoost). Arabian Journal for Science and Engineering. 2022; 47(6): 7367–7385.
20. Arabameri E. The Evolution of Motor Behavior: Lessons from Past Research and Future Prospects. Health Nexus. 2024; 2(4): 134–151.
21. Padilla BO. Deep state-space modeling for explainable representation, analysis, and forecasting of professional human body dynamics in dexterity understanding and computational ergonomics [Doctoral dissertation]. Université Paris sciences et lettres; 2023.
22. Ebers MR. Machine learning for dynamical models of human movement [Doctoral dissertation]. University of Washington; 2023.
23. Donmazov S, Saruhan EN, Pekkan K, Piskin S. Review of machine learning techniques in soft tissue biomechanics and biomaterials. Cardiovascular Engineering and Technology. 2024; 15: 1–28.
24. Mishra N, Habal BGM, Garcia PS, Garcia MB. Harnessing an AI-Driven Analytics Model to Optimize Training and Treatment in Physical Education for Sports Injury Prevention. In: Proceedings of the 2024 8th International Conference on Education and Multimedia Technology; 22–24 June 2024; Tokyo, Japan. pp. 309–315.
25. Mishra PK, Fasshauer GE, Sen MK, Ling L. A stabilized radial basis-finite difference (RBF-FD) method with hybrid kernels. Computers & Mathematics with Applications. 2019; 77(9): 2354–2368.
26. Gewers FL, Ferreira GR, De Arruda HF, et al. Principal component analysis: A natural approach to data exploration. ACM Computing Surveys (CSUR). 2021; 54(4): 1–34.
27. Hasan BMS, Abdulazeez AM. A review of principal component analysis algorithm for dimensionality reduction. Journal of Soft Computing and Data Mining. 2021; 2(1): 20–30.
28. Engle RF, Ledoit O, Wolf M. Large dynamic covariance matrices. Journal of Business & Economic Statistics. 2019; 37(2): 363–375.
29. Zhang Z, Jung C. GBDT-MO: Gradient-boosted decision trees for multiple outputs. IEEE transactions on neural networks and learning systems. 2021; 32(7): 3156–3167.
30. Mistry M, Letsios D, Krennrich G, et al. Mixed-integer convex nonlinear optimization with gradient-boosted trees embedded. INFORMS Journal on Computing. 2020; 33(3): 1103–1119.
31. Moradi R, Berangi R, Minaei M. A survey of regularization strategies for deep models. Artificial Intelligence Review. 2020; 53(6): 3947–3986.
32. Bejani MM, Ghatee M. A systematic review on overfitting control in shallow and deep neural networks. Artificial Intelligence Review. 2021; 54(8): 6391–6438.
33. Chen J, Pu Y, Guo L, et al. Second‐order optimization methods for time‐delay autoregressive exogenous models: Nature gradient descent method and its two modified methods. International Journal of Adaptive Control and Signal Processing. 2023; 37(1): 211–223.
34. Guo J, Fu H, Pan B, Kang R. Recent progress of residual stress measurement methods: A review. Chinese Journal of Aeronautics. 2021; 34(2): 54–78.
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
