Application of machine classification learning models based on factor space mathematical theory in higher vocational education from a biomechanical perspective
Year: 2025
Type: article
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.
DOI: 10.62617/mcb1150
Authors: Wei Luo, Guo-qing Liu, Zi-jian Wu, Zhi-yan Sa
Institution: Aba Vocational College
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W4407712873