Abstract
Pattern recognition techniques are a class of method used to categorize observations across multiple classes. The structure and learning method of a model are selected so as to maximize the classification accuracy obtained over a certain data set. Methods also exist to improve accuracy by suitably structuring the training data [1]. Ensemble learning [2,3,4,5] can be seen as one such method.
In this talk, we discuss a new method that improves the structure of data in order to improve the accuracy of a classifier. In contrast to AdaBoost, a conventional boosting method that increases the weight for misclassified data and adds data over learning iterations, we propose Bagging/Boosting methods that generate virtual data using fuzzy membership functions [6] centered on misclassified data. We call this the pdi-Bagging/Boosting method (Possibilistic Data Interpolation Bagging/Boosting method) [1, 7,8,9,10]. The newly generated virtual data around the misclassified data is used exclusively for training – not for validation or testing. Model accuracy is improved by adding virtual data to the original training data because the pattern recognition model is identified by the training data. On the other hand, the accuracy of the identified model is evaluated on the original test data which is not augmented with virtual data. In other words, the virtual data is not involved in the evaluation of the model at all.
We apply the pdi-Bagging/Boosting method to Trapezoidal fuzzy inference. Trapezoidal fuzzy inference is a general form of triangular fuzzy reasoning, that has proven to be effective at solving various types of inference problems [11, 12]. When used as a clustering method of bagging/boosting algorithm, fuzzy inference allows efficiently for adjusting cluster boundaries with each new data [13, 14]. In trapezoidal fuzzy inference, both the membership function for the antecedent part and the singleton real value of the consequent part need to be learned [15,16,17,18,19,20]. In this talk, we frame the problem of parameter adjustment for fuzzy rules not as a tuning problem but rather, as a design problem [21]. We focus in particular on how to learn coefficients both for the membership functions of the antecedent part and the singletons of the consequent part, how to set initial values, and how to determine the learning sequence of consequent and antecedent parts.
We are developing a system for automatically extracting rules of table tennis strategy from video using a clustering method [22, 23]. We analyzed videos from women’s table tennis singles tournament at the 2016 Rio de Janeiro Olympics, including 16 matches from the third round to the final. This video corpus contains a total of 407 plays, and 7,434 separate ball trajectories. In addition, we are collaborating with OMRON Corporation which has been developing a table tennis robot, “FORPHEUS” [24]. In this talk, the possibility of strategy extraction from video or images using ensemble learning algorithm in the near future is discussed, as well as the possibility to characterize players’ strategies based on the learned relationship between player characteristics and ball position in image-based coordinates [25]. Through future work, we hope to integrate this new capability into an “AI strategy coach” that can help improve player strategies [26,27,28].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hayashi, I.: Data science of “Shinayakana” decision on advanced computational intelligence. In: Proceedings of the 5th International Workshop on Frontier of Science and Technology (FST 2017) and the 5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII 2017) (2017)
Freund, Y.: Boosting a weak learning algorithm by majority. Inf. Comput. 121(2), 256–285 (1995)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)
Dietterich, T.G.: Ensemble methods in machine learning. In: The First International Workshop on Multiple Classifier System (MCS 2000), pp. 1-15 (2000)
Schapire, R.E.: The boosting approach to machine learning: an overview. In: Denison, D.D., Hansen, M.H., Holmes, C., Mallick, B., Yu, B. (eds.) Nonlinear Estimation and Classification. Springer, Berlin (2003)
Zadeh, L.A.: Fuzzy Sets, Fuzzy Logic, Fuzzy Systems. World Scientific Press (1996)
Hayashi, I., Tsuruse, S.: A proposal of boosting algorithm by probabilistic data interpolation for brain-computer interface. In: Proceedings of the 26th Fuzzy System Symposium, pp. 288-291 (2010). (in Japanese)
Hayashi, I., Tsuruse, S.: A proposal of boosting algorithm by possibilistic data interpolation and its application to brain-computer interface. J. Jpn. Soc. Fuzzy Theory Intell. Inform. 28(1), 501–510 (2016). (in Japanese)
Hayashi, I., Tsuruse, S., Suzuki, J., Kozma, R.T.: A proposal for applying PDI-boosting to brain-computer interfaces. In: Proceedings of 2012 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2012) in 2012 IEEE World Congress on Computational Intelligence (WCCI 2012) (2012)
Irie, H., Hayashi, I.: Performance evaluation of PDI-bagging by generation of correct-error virtual data. In: Proceedings of the 29th Symposium on Fuzzy, Artificial Intelligence, Neural Networks and Computational Intelligence, Paper ID:No. A3-3 (2019). (in Japanese)
Mamdani, E.H.: Application of fuzzy algorithms for control of simple dynamic plant. Proc. Inst. Electr. Eng. 121(12), 1585–1588 (1974)
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Approach to Machine Intelligence. Prentice Hall International Inc., Singapore (1992)
Ishibuchi, H., Nozaki, K., Tanaka, H.: Pattern classification by fuzzy rules. J. Jpn. Soc. Fuzzy Theory Syst. 5(1), 74–84 (1993). (in Japanese)
Nakashima, T., Shoji, Y.: The effect of data partition in constructing fuzzy ensemble classifiers. In: Proceedings of the 25th Fuzzy System Symposium, No. 3E2-01 (2009). (in Japanese)
Ichihashi, H., Watanabe, T.: Learning controlby fuzzy model using a simplified fuzzy reasoning. J. Jpn. Soc. Fuzzy Theory Syst. 2(3), 429–437 (1990). (in Japanese)
Nomura, H., Hayashi, I., Wakami, N.: A self-turning method of fuzzy reasoning by delta rule and its application to a moving obstacle avoidance. J. Jpn. Soc. Fuzzy Theory Syst. 4(2), 379–388 (1992). (in Japanese)
Juang, C.F., Wang, C.Y.: A self-Generating fuzzy system with ant and particle swarm cooperative optimization. Expert Syst. Appl. 36(3), 5362–5370 (2009)
Habbi, H., Kidouche, M., Zelmat, M.: Data-driven fuzzy models for nonlinear identification of a complex heat exchanger. Appl. Math. Model. 35, 1470–1482 (2011)
Habbi, H., Boudouaoui, Y., Karaboga, D., Ozturk, C.: Self-generated fuzzy systems design using artificial Bee colony optimization. Inf. Sci. 295, 145–159 (2015)
Gorzalczany, M.B., Rudzinski, F.: Interpretable and accurate medical data classification - a multi-objective genetic-fuzzy optimization approach. Expert Syst. Appl. 71, 26–39 (2017)
Irie, H., Hayashi, I.: Characterization of hyperparameter of learning type trapezoidal fuzzy inference. In: Proceedings of the 34th Fuzzy System Symposium, pp. 259-264 (2018). (in Japanese)
Hayashi, I., Maeda, T., Fujii, M., Wang, S., Tasaka, T.: Acquisition of embodied knowledge on sport skill using TAM network. In: 2009 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2009), pp. 1038-1043 (2009)
Hayashi, I., Fujii, M., Maeda, T., Leveille, J., Tasaka, T.: Extraction of knowledge from the topographic attentive mapping network and its application in skill analysis of Table Tennis. J. Hum. Kinet. 55, 39–54 (2017). https://doi.org/10.1515/hukin-2017-0005
OMRON Corporation: FORPHEUS. https://www.omron.com/innovation/forpheus.html. Accessed 11 Oct 2019
Hayashi, I., Ogino, M., Irie, H., Tamaki, S., Yoshida, K., Kondric, M.: Development of image processing system to realize Table Tennis strategy board. In: Proceedings of Japan Table Tennis Association Sports Science and Medicine Committee International Meeting 2018 (JTTA-SSMC 2018), p. 21 (2018)
Mochizuki, Y., Himeno, R., Omura, K.: Artificial skill and a new principle in sports. Syst. Control Inf. 46(8), 498–505 (2002)
Perl, J., Baca, A.: Application of neural networks to analyze performance in sports. In: The 8th Annual Congress of the European College of Sport Science (2003)
Hayashi, I., Ogino, M., Irie, H., Tamaki, S., Yoshida, K., Kondric, M.: AI coach: learning table tennis strategy rules from video. In: Proceedings of the 16th International Table Tennis Federation (ITTF) Sports Science Congress (ITTF-SSC 2019), p. 76 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hayashi, I., Irie, H. (2020). Ensemble Learning to Generate Virtual Data for Pattern Recognition and Its Possibility of Application to Strategy Inference in Table Tennis. In: Sato, H., Iwanaga, S., Ishii, A. (eds) Proceedings of the 23rd Asia Pacific Symposium on Intelligent and Evolutionary Systems. IES 2019. Proceedings in Adaptation, Learning and Optimization, vol 12. Springer, Cham. https://doi.org/10.1007/978-3-030-37442-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-37442-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37441-9
Online ISBN: 978-3-030-37442-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)