A SPATIOTEMPORAL MODEL PREDICTS THE DYNAMICS OF A BASKETBALL GAME
DOI:
https://doi.org/10.61841/ak6x8397Keywords:
Basketball game decision-making, Temporal point process, Markov decision process (MDP), LSTM-based architectureAbstract
Abstract—Our work as a spatiotemporal model predictive dynamic (STMPD) on a basketball game capable of high-level decision making . Our motivated and skilled experts solve complex decision-making problems at every time point during a game. The conditional intensity of a temporal point process can be learned based on a network, and the likelihood is maximised during training. A Fine-grained player locations started with the simplest case of modelling, where certain players tend to shoot the ball. They discretize the court into cells fine enough to capture all significant spatial variations in model for predicting dynamics in-game, e.g., shooting policy, passing, and who relies on Markov transition probabilities to propagate action through a possession. We propose a method for learning factored Markov decision problems . We use a method that captures the multi-modal behaviour of the players' truth ground and estimation trajectory Prediction is a method for predicting multimodal trajectory by learning a model that assigns probabilities through conducting temporal classification (resolution) (CTC) architectures by generalising away from actual time stamps to recreate the predicted trajectory. Our proposed method of contribution is as follows : i) The method is built on an LSTM-based architecture predicting multiple trajectories and our probabilities, and then we use training with a multimodal loss function when updating the best trajectories . ii) a discriminative learning method for automatically training models to predict near-term game events based on current game conditions . iii) learning factored Markov decision processes (FMDP) problems from domain exploration and expert assistance, ensuring convergence to near-optimal behaviour even after the agent has started to learn critical success factors. IV) An algorithm 1,2, detects changes in possession, pass, and shot players that have been incrementally learned for all components of FMDP, and algorithm 3, which guarantees convergence to near-optimal behaviour even when the agent begins unaware of factors critical to success. A group of players shooting probability to enhance a probabilistic matrix
References
Y. Yue, P. Lucey, P. Carr, A. Bialkowski and I. Matthews, “Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction, ” in procc: IEEE International Conference on Data Mining, 2014,pp.670-679.
B.Skinner and M. Goldman, Optimal strategy in basketball In Handbook of Statistical Methods and Analyses in Sports,2019 . [E-book]
M. Horton, J. Gudmundsson, S. Chawla and J. Estephan , “Automated classification of passing in football, ”in proc Intern Conference on Knowledge Discovery and Data Mining, Ho Chi Minh,Vietnam , 2015; pp.319–330.
D.Cervone, A.DAmour, L.Bornn,. and K.Goldsberry ,A multiresolution stochastic process model for predicting basketball possession outcomes, Journal of the American Statistical Association , vol .111, pp.585-599 , 2016.
A. Miller, L. Bornn, R. Adams, and K. Goldsberry, “Factorized point process intensities: A spatial analysis of professional basketball,” in International Conference on Machine Learning , vol 32, 2014.pp. 22-24.
V. Guralnik and J. Srivastava, “Event detection from time series data,” in Proc: fifth ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NY, USA:ACM Press, 1999, pp. 33–42.
M. Salmenkivi and H. Mannila, “Using Markov Chain Monte Carlo and dynamic programming for event sequence data,” Knowledge and Information Systems, vol. 7, no. 3, pp. 267–288, 2005.
S. L. Scott and P. Smyth, “The Markov modulated Poisson process and Markov Poisson cascade with applications to web traffic data,” Bayesian Statistics, vol. 7, 2003, pp. 671–680.
A.Alahi, K.Goel, V.Ramanathan, A.Robicquet, L.Fei and S.Savarese, “Social lstm: Human trajectory prediction in crowded spaces, ” in proc: IEEE conference on computer vision and pattern recognition, 2016,pp. 961–971.
S.Haddad and S.Lam, “ Self-growing spatial graph networks for pedestrian trajectory prediction" in Proc. The IEEE Winter Conference on Applications of Computer Vision, 2020, pp. 1151–1159.
A. Graves, S. Fern´andez, F. Gomez, and J. Schmidhuber, “Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,”in ICML, Garching, Munich:Germany ,2006.
L.Lamas, J.Barrera, G.Otranto, and C.Ugrinowitsch, invasion team sports: strategy and match modeling
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Journal of Advance Research in Applied Science (ISSN 2208-2352)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
