An Assessment of Fitness of Undergraduates in BITZH by Using SMOTE and Machine Learning Algorithms

DOI

10.2991/978-94-6463-058-9_94How to use a DOI?

Keywords

Physical Fitness; Machine Learning; Multiple Classifiers; Voting

ABSTRACT

The physical fitness test is used as a tool to evaluate students' physical health. This paper proposed a assessment of physical fitness test based on machine learning (ML) to improve college students' awareness of physical fitness. In this paper, we collected the number of records of fitness test at about 120 thousands from undergraduates who come from Beijing institute of technology in Zhuhai. Firstly, we first classified students' physical fitness into five categories by using K-Means. Then, we resampled the dataset by using the synthetic minority over-sampling technique (SMOTE) to address the imbalance of dataset. This framework that constructed with ML methods, included DT, RF, GBN, LR, SVM, XGB. In addition, Voting combined with single model which can improve the accuracy of model. The model was evaluated by using these performance metrics, such as Macro-Precision, Kappa, and so on. The result of experiment shows that the precision of SVM is 99.54%, and the recall of this is 99.53%. At the same time, the ensemble model combined SVM with Voting have better performance than others. In conclusion, the model which build based on Voting and SVM can detect and predict the level of health effectively.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shiyi Wang
AU  - Zejian Lin
AU  - Yanhui Huang
AU  - Chuangfeng Ma
AU  - Xindong Zhao
AU  - Xiaoyu Wei
PY  - 2022
DA  - 2022/12/27
TI  - An Assessment of Fitness of Undergraduates in BITZH by Using SMOTE and Machine Learning Algorithms
BT  - Proceedings of the 2nd International Conference on Internet, Education and Information Technology (IEIT 2022)
PB  - Atlantis Press
SP  - 587
EP  - 595
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-058-9_94
DO  - 10.2991/978-94-6463-058-9_94
ID  - Wang2022
ER  -