한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제12권8호
  • /
  • Pages.279-286
  • /
  • 2021
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

배깅과 부스팅 알고리즘을 이용한 핸드볼 결과 예측 비교

Comparison of Handball Result Predictions Using Bagging and Boosting Algorithms

  • 김지응 (상명대학교 스포츠산업학과) ;
  • 박종철 (부경대학교 해양스포츠학과) ;
  • 김태규 (부경대학교 해양스포츠학과) ;
  • 이희화 (상명대학교 스포츠산업학과) ;
  • 안지환 (성균관대학교 스포츠과학과)
  • Kim, Ji-eung (Department of Sport management, Sangmyung University) ;
  • Park, Jong-chul (Department of Marine Sports, Pukyong National University) ;
  • Kim, Tae-gyu (Department of Marine Sports, Pukyong National University) ;
  • Lee, Hee-hwa (Department of Sport management, Sangmyung University) ;
  • Ahn, Jee-Hwan (College of Sport Science, Sungkyunkwan University)
  • 투고 : 2021.05.10
  • 심사 : 2021.08.20
  • 발행 : 2021.08.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구는 여자핸드볼 경기에서 발생되는 움직임 정보를 바탕으로 앙상블 기법의 배깅과 부스팅 알고리즘의 예측력을 비교하고, 움직임 정보의 활용가능성을 분석하는데 목적이 있다. 연구의 목적을 달성하기 위하여 15번의 연습경기에서 관성센서를 활용해 수집한 움직임 정보를 활용한 경기 결과예측을 랜덤포레스트와 Adaboost 알고리즘을 활용해 비교·분석하였다. 연구결과 첫째, 랜덤포레스트 알고리즘의 예측률은 66.9 ± 0.1%로 나타났으며, Adaboost 알고리즘의 예측률은 65.6 ± 1.6%로 나타났다. 둘째, 랜덤포레스트는 승리 결과는 모두 예측하였고, 패배의 결과는 하나도 예측하지 못하였다. 반면, Adaboost 알고리즘은 승리 예측 91.4%, 패배예측 10.4%라고 나타났다. 셋째, 알고리즘의 적합성 여부에서 랜덤포레스트는 과적합의 오류가 없었지만, Adaboost는 과적합의 오류가 나타났다. 본 연구결과를 바탕으로 스포츠경기를 예측할 때 움직임 정보도 활용 가능성을 확인하였으며, 랜덤포레스트 알고리즘이 보다 우수함을 확인하였다.

The purpose of this study is to compare the predictive power of the Bagging and Boosting algorithm of ensemble method based on the motion information that occurs in woman handball matches and to analyze the availability of motion information. To this end, this study analyzed the predictive power of the result of 15 practice matches based on inertial motion by analyzing the predictive power of Random Forest and Adaboost algorithms. The results of the study are as follows. First, the prediction rate of the Random Forest algorithm was 66.9 ± 0.1%, and the prediction rate of the Adaboost algorithm was 65.6 ± 1.6%. Second, Random Forest predicted all of the winning results, but none of the losing results. On the other hand, the Adaboost algorithm shows 91.4% prediction of winning and 10.4% prediction of losing. Third, in the verification of the suitability of the algorithm, the Random Forest had no overfitting error, but Adaboost showed an overfitting error. Based on the results of this study, the availability of motion information is high when predicting sports events, and it was confirmed that the Random Forest algorithm was superior to the Adaboost algorithm.

키워드

참고문헌

  1. K. B. Goo & S. B. Kim. (2018). Issues of Sports Circle in the Era of 4th Industrial Revolution. The Korean Society for the Philosophy of Sport, Dance & Martial Arts, 26(2), 7-17.
  2. W. J. Kim, Y. S. Choi & D. H. Yoo. (2018). Development of Win-Loss Prediction Models and Strategies for Improving Winning Rate of the Korean Professional Baseball Teams Using Data Mining Techniques. Korean Journal of Sport Management, 23(3), 88-104. DOI : 10.31308/KSSM.23.3.6
  3. J. H. Cho. (2012). Utilization and Prospect of Sport Big Data. The Korean Journal of Measurement and Evaluation in Physical Education and Sports Science, 14(3), 1-11. DOI : 10.21797/ksme.2012.14.3.001
  4. J. W. Lim & H. J. Kim. (2008). Setting Sprint Zone for performance analysis in Field-Hockey: Using Global Positioning System (GPS). The Korean Journal of Measurement and Evaluation in Physical Education and Sports Science, 10(1), 69-79. DOI : 10.21797/ksme.2008.10.1.006
  5. I. S. Yeo & C. H. Park. (1998). Ethics of competition and victory in sport: The Korean Society for the Philosophy of Sport, Dance & Martial Arts, 6(1), 67-88. UCI(KEPA) : I410-ECN-0101-2018-069-001973573
  6. D. Jennings, S. Cormack, A. J. Coutts, L. Boyd & R. J. Aughey. (2010). The validity and reliability of GPS units for measuring distance in team sport specific running patterns. International journal of sports physiology and performance, 5(3), 328-341. DOI:10.1123/ijspp.5.3.328
  7. D. W. Wundersitz, P. B. Gastin, S. Robertson, P. C. Davey & K. J. Netto. (2015). Validation of a trunk-mounted accelerometer to measure peak impacts during team sport movements. International journal of sports medicine, 36(09), 742-746. DOI: 10.1055/s-0035-1547265
  8. S. K. Min. (2014). Sports Science: On-site support using the Global Positioning System (GPS) in field hockey competitions compared to the Asian Games. Sports science, 128, 48-53.
  9. Y. H. Jung, S. H. Eo, H. S. Moon & H. J. Cho. (2010). A Study for Improving the Performance of Data Mining Using Ensemble Techniques. Communications for Statistical Applications and Methods, 17(4), 561-S74. UCI : G704-000420.2010.17.4.006 https://doi.org/10.5351/CKSS.2010.17.4.561
  10. W. H. Lee. (2006). development of soccer ranking prediction model using neural network analysis. Unpublished doctoral dissertation, Myongji University, Seoul.
  11. Y. H. Oh, H. Kim, J. S. Yun & J. S. Lee. (2014). Using Data Mining Techniques to Predict Win-Loss in Korean Professional Baseball Games. Journal of the Korean Institute of Industrial Engineers, 40(1), 8-17. DOI : 10.7232/JKIIE.2014.40.1.008
  12. Y. C. Kim. (2018). E-sports game prediction using machine learning : focusing on League of Legends. Unpublished master's thesis, Chung-Ang University, Seoul.
  13. D. Miljkovic, L. Gajic, A. Kovacevic & Z. Konjovic. (2010, September). The use of data mining for basketball matches outcomes prediction. In IEEE 8th International Symposium on Intelligent Systems and Informatics. (pp. 309-312). IEEE. DOI: 10.1109/SISY.2010.5647440
  14. N. Razali, A. Mustapha, F. A. Yatim & R. Ab Aziz. (2017, August). Predicting football matches results using Bayesian networks for English Premier League (EPL). In Iop conference series: Materials science and engineering, 226(1), p.012099. DOI: 10.1088/1757-899X/226/1/012099
  15. J. H. Yi & S. W. Lee. (2020). Prediction of English Premier League Game Using an Ensemble Technique. KIPS Transactions on Software and Data Engineering, 9(5), 161-168. https://doi.org/10.3745/KTSDE.2020.9.5.161
  16. W. Cai, D. Yu, Z. Wu, X. Du & T. Zhou. (2019). A hybrid ensemble learning framework for basketball outcomes prediction. Physical A: Statistical Mechanics and its Applications, 528, 121461. DOI: 10.1016/j.physa.2019.121461
  17. A. Groll, C. Ley, G. Schauberger & H. Van Eetvelde. (2019). A hybrid random forest to predict soccer matches in international tournaments. Journal of Quantitative Analysis in Sports, 15(4), 271-287. DOI: 10.1515/jqas-2018-0060
  18. J. C. Park, K. S. Yoon & J. E. Kim. (2015). Movement Analysis of Women's Handball Players by Position using Inertial Measurement Units. Journal of the Korea Convergence Society, 11(4), 343-350. DOI : 10.15207/JKCS.2020.11.4.343
  19. D. R. Jang & M. J. Park. (2020). A Study on the Art Price Prediction Model Using the Random Forests. Journal of Applied Reliability, 20(1), 34-42. DOI : 10.33162/JAR.2020.3.20.1.34
  20. S. J. Kim & H. C. Ahn. (2016). Application of Random Forests to Corporate Credit Rating Prediction. Kyungsung University Institute for Industrial Development, 32(1), 187-211. DOI : 10.22793/indinn.2016.32.1.006
  21. Y. S. Lee, H. J. Oh & M. K. Kim. (2005). An Empirical Comparison of Bagging, Boosting and Support Vector Machine Classifiers in Data Mining. The Korean Journal of applied Statistics, 18(2), 343-354. UCI : G704-000408.2005.18.2.003 https://doi.org/10.5351/KJAS.2005.18.2.343
  22. J. C. W. Chan & D. Paelinckx. (2008). Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment, 112(6), 2999-3011. DOI: 10.1016/j.rse.2008.02.011
  23. H. H. Lee & J. E. Kim. (2019). Application of Electronic Performance Tracking System (EPTS) for Dance Evaluation of Dancers and Prediction Model of Injury Prevention. The Korean Journal of Sport, 17(4), 1597-1607.
  24. S. J. Kang. (2019). Preliminary Study on the Prediction of Human Kinematic Motion Analysis Using Artificial Intelligence. Korean Society for Precision Engineering, 19-19. DOI:10.1007/978-981-13-9129-3_1
  25. H. Y. Jung, Y. J. Na, C. W. Wang & S. D. Min. (2014). Multi-objective system using EMG and accelerometer. Journal of Electrical Engineering & Technology. Summer Academic Conference, 1,502 - 1,503. UCI(KEPA) : I410-ECN-0101-2016-560-001853938