Table of Content

Open Access iconOpen Access

ARTICLE

crossmark

Prediction of College Students’ Physical Fitness Based on K-Means Clustering and SVR

Peng Tang, Yu Wang, Ning Shen

Department of Physical Education, Hohai University, Nanjing 210098, China

* Corresponding Author: Email: email

Computer Systems Science and Engineering 2020, 35(4), 237-246. https://doi.org/10.32604/csse.2020.35.237

Abstract

In today’s modern society, the physical fitness of college students is gradually declining. In this paper, a prediction model for college students’ physical fitness is established, in which support vector regression (SVR) and k-means clustering are combined together for the prediction of college students’ fitness. Firstly, the physical measurement data of college students are classified according to gender and class characteristics. Then, the k-means clustering method is used to classify the physical measurement data of college students. Next, the physical characteristics of college students are extracted by SVR to establish the prediction model of physical indicators, and the model for predicting college students’ fitness can be obtained after scoring their physical fitness levels. Finally, based on college physical test data of students at a university in China, the prediction results show that the method has high predictive accuracy compared to other methods.

Keywords


Cite This Article

APA Style
Tang, P., Wang, Y., Shen, N. (2020). Prediction of college students’ physical fitness based on k-means clustering and SVR. Computer Systems Science and Engineering, 35(4), 237-246. https://doi.org/10.32604/csse.2020.35.237
Vancouver Style
Tang P, Wang Y, Shen N. Prediction of college students’ physical fitness based on k-means clustering and SVR. Comput Syst Sci Eng. 2020;35(4):237-246 https://doi.org/10.32604/csse.2020.35.237
IEEE Style
P. Tang, Y. Wang, and N. Shen "Prediction of College Students’ Physical Fitness Based on K-Means Clustering and SVR," Comput. Syst. Sci. Eng., vol. 35, no. 4, pp. 237-246. 2020. https://doi.org/10.32604/csse.2020.35.237

Citations




cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 2872

    View

  • 1972

    Download

  • 1

    Like

Share Link