The sports performance based on variable weight and support vector machine

DOI

10.2991/icence-16.2016.160How to use a DOI?

Keywords

sports; 1000m running; prediction; screen; weight

Abstract

as sports performance is affected by many factors, it's crucial to choose effective divisors. A sports performance prediction model based on weight-SVM is proposed for factor selection and evaluation. Firstly, support vector machine is used to eliminate some invalid factors by use of cross validation MSE minimization principle; then mandatory screening is adopted to weight retention factor and quantize importance degree of retention factor; finally, SVM sports performance prediction model is constructed and applied to 1000m running performance prediction. Simulation result shows, compared with reference model, weight-SVM prediction has higher precision and it can screen and weight factor precisely and provide a new research idea for sports performance prediction.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qingbin Wang
AU  - Ling Jia
PY  - 2016/09
DA  - 2016/09
TI  - The sports performance based on variable weight and support vector machine
BT  - Proceedings of the 2nd International Conference on Electronics, Network and Computer Engineering (ICENCE 2016)
PB  - Atlantis Press
SP  - 872
EP  - 876
SN  - 2352-538X
UR  - https://doi.org/10.2991/icence-16.2016.160
DO  - 10.2991/icence-16.2016.160
ID  - Wang2016/09
ER  -