Development of Physical Fitness Prediction Models for Turkish Secondary School Students Using Machine Learning Methods
Abstract
Physical fitness is a set of attributes that are either health or skill-related which can be measured with specific tests. Maintaining physical fitness is essential for health and wellbeing. However, since measurement of physical fitness requires improved professional equipment, experienced staff and lots of time, researchers need different ways to determine physical fitness. The aim of this study is to develop new prediction models for predicting the physical fitness of Turkish secondary school students by using machine learning methods including Support Vector Machines (SVM), Radial Basis Function Neural Network (RBFNN) and Tree Boost (TB). The dataset comprises data of various number of subjects according to the target variables such as the test scores of the 30m speed, 20m stage run, balance and agility. The predictor variables used to develop the prediction models are gender, age, height, weight, body fat, number of curl-up and push-ups in 30 seconds. Root Mean Square Error (RMSE) has been utilized to assess the performance of the prediction models. Based on the results we can conclude that SVM based prediction models outperform other models based on RBFNN and TB. Also, the predictor variables body fat, push-up and curl-up play a significant role when used all together for physical fitness prediction.
Keywords
Kaynakça
- Abut, F., Akay, M.F., Sow, B. and George, J. 2015. Support Vector Machines for Prediction of Endurance Times Involving Isometric Side Bridge Exercise Test, Third International Symposium on Engineering, Artificial Intelligence & Applications (ISEAIA2015), North Cyprus, pp. 7-9.
- Ahmed, M.U., Loutfi, A., 2013. Pyhsical Activity Identification using Supervised Machine Learning and based on Pulse Rate, International Journal of Computer Science and Applications, Publication 4(7).
- Chuang, C.C., Lee, Z.C., 2011. Hybrid robust support vector machines for regression without liers, Applied Soft Computing.
- Dijkhuis,T.B., Blaauw, F., Ittersum,M. W., Aiello, M. 2018. Personalized Physical Activity Coaching : A Machine Learning Approach, in Sensors, 18(2), p.623.
- Fergus, P., Hussain,A., Hearty, J., Fairclough,S., Boddy, L., Machintoch, K.A., Stratton,G., Ridgers, N.D. and Radi, N. 2015. A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity, Intelligent Computing Theories and Methodologies: 11th International Conference, ICIC 2015, Fuzhou, China, pp. 676-688.
- Hannan, S.A., Manza, R.R., Ramteke, R.J. 2010. Generalized Regression Neural Network and Radial Basis Function for Heart Disease Diagnosis, International Journal of Computer Applications, Volume 13, Issue 2, ISBN: 10.5120/1325-1799.
- Hoffman, J., 2006. Norms for Fitness, Performance and Health, Human Kinetics Publishers, ISBN-13: 9780736054836, 97–104.
- Reichherzer, T., Timm, M., Earley, N., Reyes, N., 2017. Using Machine Learning Techniques to Track Individuals & Their Fitness Activities, In A. Bossard, G. Lee, & L. Miller (Eds.), Proceedings of 32nd International Conference on Computers and Their Applications, Honolulu, Hawaii, USA, pp. 119–124.
- Wang, L., 2005. Support Vector Machines: Theory and Applications, Springer Science & Business Media, Volume 177, 1st Edition: ISBN: 978-3-540-32384-6.