Personalized college physical education curriculum generation via hierarchical recommendation algorithm with biomechanics-driven optimization
Abstract
With the rapid development of modern communication technology and multimedia technology, learners can obtain various learning resources in various ways. But the problem that comes with it is to obtain the knowledge needed by learners from many resources efficiently, quickly and effectively, so as to complete the systematic study of college physical education personalized courses. Since 1980s, personalized learning and personalized service in the network learning environment have been studied accordingly. The related research involves many information science fields such as information retrieval, data mining, artificial intelligence, computer communication and network, but the research on the generation of personalized curriculum of college physical education is relatively few. This paper mainly focuses on the research and realization of personalized curriculum generation technology of college physical education, and explores the solution to realize the individualization of college physical education learning content in the process of large-scale online education. A hierarchical recommendation algorithm based on multi-dimensional feature vector is proposed, with a unique emphasis on integrating biomechanics. By analyzing biomechanical indicators like joint mobility, muscle strength, and body coordination of students, the algorithm can accurately assess their physical conditions. This integration can not only help physical education teachers make the overall teaching plan, but also meet the needs of college students’ individual knowledge and ability characteristics for curriculum learning. In addition, the hierarchical implementation of the recommendation algorithm distributes the recommendation of large-scale knowledge base and resource base at different levels, which effectively reduces the dimension, reduces the amount of calculation and improves the efficiency of the implementation of the personalized curriculum generation algorithm of college physical education. Biomechanics-driven optimization ensures that the recommended courses are not only knowledge - based but also safe and effective for students from a biomechanical perspective, enhancing the overall quality of personalized PE curricula.
References
1. Zavesky E, Liu Z, Xu T, et al. Content curation for course generation: US11113472B2. 2021.
2. Hussein N, Dheyab O K. Secure File Storage in Cloud Computing Based on Hybrid Cryptosystem Algorithm. Solid State Technology, 2020, 63 (6): 15.
3. Atchariyachanvanich K, Nalintippayawong S, Julavanich T. Reverse SQL Question Generation Algorithm in the DBLearn Adaptive E-Learning System. IEEE Access, 2019, PP (99): 1-1.
4. Sheng D, Yuan J, Xie Q, et al. ACMF: An Attention Collaborative Extended Matrix Factorization Based Model for MOOC course service via a heterogeneous view. Future Generation Computer Systems, 2021, 126 (12).
5. Wiilams K, Ajinaja M. Automatic Timable Generation Using Genetic Algorithm. International Journal of Applied Information Systems, 2019, 12:1-9. doi:10.5120/ijais2019451779
6. Mallick S, Majumdar D, Mukherjee S, et al. Hybrid Cuckoo Search Approach for Course Time-Table Generation Problem. International Journal of Applied Metaheuristic Computing, 2020, 11 (4): 214-230.
7. Ze-Bing X U, Wang Z. Implementation of Collaborative Filtering Recommendation Algorithm Based on SVD and Hierarchical Clustering. Digital Technology and Application, 2018.
8. Jiang C, Feng J, Sun X, et al. Personalized exercises Recommendation algorithm based on Knowledge Hierarchical Graph, ReKHG. Computer Engineering and Applications, 2018.
9. Dai J, Jia Z, Gao X, et al. A Hierarchical Optimizer for Recommendation System Based on Shortest Path Algorithm. 2019. DOI: 10.48550/arXiv.1911.08994
10. Li W, Zhou X, Shimizu S, et al. Personalization Recommendation Algorithm Based on Trust Correlation Degree and Matrix Factorization. IEEE Access, 2019: 1-1.
11. Sun Y, Gu W, Li B, et al. Electricity-Retail-Market-Reform Oriented Recommendation Method of User’s Hierarchical Clustering and Pricing Packages. Power System Technology, 2018. doi: 10.13335/j.1000-3673.pst.2017.1226
12. Wang H C, Hsu T T, Sari Y. Personal research idea recommendation using research trends and a hierarchical topic model. Scientometrics, 2019, 121.
13. Duan X. Automatic Generation and Evolution of Personalized Curriculum Based on Genetic Algorithm. International Journal of Emerging Technologies in Learning (jJET), 2019, 14(12):15.
14. Das J, Majumder S, Gupta P, et al. Collaborative Recommendations using Hierarchical Clustering based on K-d Trees and Quadtrees. International Journal of Intellectual Fuzzy and Knowledge-Based Systems, 2019, 27(4): 637-668.
15. Zhao D, Zhang L, Zhang B, et al. MaHRL: Multi-goals Abstraction Based Deep Hierarchical Reinforcement Learning for Recommendations //SIGIR ‘20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval. ACM, 2020.
16. Ruan Z. Data analysis of competition pressure source based on the combination of k-means clustering algorithm and hierarchical algorithm. IPPTA: Quarterly Journal of Indian Pulp and Paper Technical Association, 2018, 30 (8): 430-435.
17. Liu Z, Xu Z, Yan Y. Hierarchical Bayesian Personalized Recommendation: A Case Study and Beyond. 2019. arXiv:1908.07371
18. Sharmila A H, Jaisankar N. Edge Intelligent Agent Assisted Hybrid Hierarchical Blockchain for continuous healthcare monitoring & recommendation system in 5G WBAN-IoT. Computer Networks, 2021, 200: 108508.
19. Guangli L I, Zhu T, Hua J, et al. Hybrid recommendation system for tourist spots based on hierarchical sampling statistics and Bayesian personalized ranking. Journal of Central China Normal University (Natural Sciences), 2019.
20. Fariani, R.I., Junus, K. & Santoso, H.B. A Systematic Literature Review on Personalised Learning in the Higher Education Context. Tech Know Learn 28, 449–476 (2023). https://doi.org/10.1007/s10758-022-09628-4
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
