On the Application of Artificial Intelligence and Feature Selection in Sports Science Education and Research: A Case Study
Article Sidebar
Main Article Content
Abstract
In sports science education and research, the use of artificial intelligence methods along with feature selection algorithms can be of great help for developing prediction models where experimental studies based on measurements are not feasible. In this paper, we present a case study in regards to how sports science can benefit from the use of artificial intelligence methods combined with a feature selection algorithm. More specifically, the purpose of our study is to develop prediction models for upper body power (UBP), which is one of the most important factors affecting the performance of cross-country skiers during races. The dataset, which includes 75 subjects, was obtained from the College of Education, Health and Development of Montana State University. Multilayer Perceptron (MLP) and Single Decision Tree (SDT) along with the minimum-redundancy maximum-relevance (mRMR) feature selection algorithm were used to produce prediction models for predicting the 10-second UBP (UBP10) and 60-second UBP (UBP60). The predictor variables in the dataset are protocol, gender, age, body mass index (BMI), maximum oxygen uptake (VO2max), maximum heart rate (HRmax), time and heart rate at lactate threshold (HRLT) whereas UBP10 and UBP60 are the target variables. Based on the ranking scores of predictor variables assigned by the mRMR, 16 different prediction models have been developed. By using 10-fold cross-validation, the efficiency of the prediction models has been calculated with their multiple correlation coefficients (R’s) and standard error of estimates (SEE’s). The results show that using less amount of predictor variables than the full set of predictor variables can be useful for prediction of UBP10 and UBP60 with comparable error rates. The model consisting of the predictor variables gender, BMI, VO2max, HRLT and time yields the lowest SEE’s for prediction of UBP10, while the model including the predictor variables gender, age, BMI and VO2max gives the lowest SEE’s for prediction of UBP60, whichever regression method is used. Using these two models instead of the full set of predictor variables yields up to 4.95% and 6.83% decrement rates in SEE’s for MLP and SDT based UBP prediction models, respectively.
Keywords: multilayer perceptron; single decision tree; sports science education;
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Akay, M. F., Abut, F., Daneshvar, S. & Heil, D. (2015). Prediction of upper body power of cross-country skiers using support vector machines. Arabian Journal for Science and Engineering, 40 (4), 1045–1055.
Akay, M. F., Abut, F., Ozciloglu, M. & Heil, D. (2015). Identifying the discriminative predictors of upper body power of cross-country skiers using support vector machines combined with feature selection. Neural Computing and Applications, doi: 10.1007/s00521-015-1986-9 .
Akay, M. F., Akgol, D., Turhan, I. & Heil, D. (2014). Prediction of upper body power of cross-country skiers using support vector machines combined with feature selection. Proceedings from: The Second International Symposium on Engineering, Artificial Intelligence & Applications, North Cyprus, 5-7 Nov 2014 (7-9).
Akay, M. F., Daneshvar, S., Isoglu, O. & Heil, D. (2014). Predicting the upper body of cross-country skiers using support vector machines. In Proceedings of The 7th Engineering and Technology Symposium, Ankara, Turkey, 15-16 May 2015 (21-24).
Akgol, D., M. F., Akay, M.F. & Heil, D. (2015). Development of new models for predicting upper body power of cross-country skiers using machine learning methods. In Proceedings of The 1st International Symposium on Sport Science, Engineering and Technology, Istanbul, Turkey, 10-13 May 2015 (34-40).
Alsobrook, N. G. & Heil, D. (2009). Upper body power as a determinant of classical cross-country ski performance. European Journal of Applied Physiology, 105 (4), 633–641.
Delashmit, W. H. & Manry, M. T. (2005). Recent developments in multilayer perceptron neural networks. In Proceedings of the 7th Annual Memphis Area Engineering and Science Conference, Memphis, Tennessee, 11 May 2005 (1-15).
Hamid, K., Ivanovich, E. V. & Hamid, K. (2014). An alternative approach for assessing sediment impact on aquatic ecosystems using Single Decision Tree (SDT). Journal of Water Sustainability, 4 (3), 181-204.
Heil, D. P. & Camenisch, K. (2014). Static flexibility as a correlate of skate roller skiing economy within collegiate cross-country skiers. International Journal of Sports Science, 4 (5), 188–197.
Heil, D. & Willis, S. (2012). In science and skiing V: Determinants of both classic and skate cross country ski performance in competitive junior and collegiate skiers, Germany: Meyer & Meyer Sport.
Lawson, S. K., Reid, D. C. & Wiley, J. P. (1992). Anterior compartment pressures in cross-country skiers. A comparison of classic and skating skis. The American Journal of Sports Medicine, 20 (6), 750–753.
Marsland, F., Lyons, K., Anson, J., Waddington, G., Macintosh, C. & Chapman, D. (2012). Identification of cross-country skiing movement patterns using micro-sensors. Sensors (Basel, Switzerland), 12 (4), 5047–5066.
Ozciloglu, M., Akay, M.F. & Heil, D. (2015). New prediction models for upper body power of cross-country skiers using machine learning methods with minimum-redundancy maximum-relevance feature selection algorithm. In Proceedings of The Third International Symposium on Engineering, Artificial Intelligence & Applications, North Cyprus, 4-6 Nov 2015 (16-17).
Ozciloglu, M., Akay, M. F., Abut, F. & Heil, D. (2015). Feature selection for prediction of upper body power of cross-country skiers using different machine learning methods. In Proceedings of The 1st International Symposium on Sport Science, Engineering and Technology, Istanbul, Turkey, 4-6 Nov 2015 (1-5).
Peng, H. F. & Long, C. D. (2005). Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (8), 1226–1238