Research on the Prediction Technology of Ice Hockey Based on Support Vector Machine

The influencing factors of the ice hockey match result are complex, and there is a nonlinear relationship with the relevant predictive indicators. The input characteristics and parameter selection of the model have important influence on the prediction performance. Based on this, this paper proposes a support vector machine ice hockey situation prediction model based on principal component analysis, hybrid genetic algorithm and particle swarm optimization. This model uses principal component analysis to perform principal component analysis on the original features, this can reduce the dimensions of the original features effectively. Using hybrid genetic algorithm and particle swarm algorithm to optimize the parameters of support vector machine to establish a predictive model. The simulation results show that when principal component analysis is used to reduce the input features, the running time of the SVM prediction model based on principal component analysis, hybrid genetic algorithm and particle swarm optimization is reduced. Compared to a single genetic algorithm optimization parameter or a particle swarm optimization parameter support vector machine prediction model, the prediction accuracy and stability are significantly improved.

[1]  Zhao Zhongwen,et al.  Visualization Study of High-Dimensional Data Classification Based on PCA-SVM , 2017, 2017 IEEE Second International Conference on Data Science in Cyberspace (DSC).

[2]  Zhong Qiang-hui.  Dimensionality reduction method based on PCA and KICA , 2011 .

[3]  Sungzoon Cho,et al.  GA-SVM wrapper approach for feature subset selection in keystroke dynamics identity verification , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[4]  Fatima Ardjani,et al.  Optimization of SVM Multiclass by Particle Swarm (PSO-SVM) , 2010 .

[5]  Enrique Alba,et al.  Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms , 2007, 2007 IEEE Congress on Evolutionary Computation.

[6]  Baojun Zhao,et al.  Face Recognition System Using SVM Classifier and Feature Extraction by PCA and LDA Combination , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[7]  Yi-Ping Hung,et al.  Easy and Deep Media , 2010 .

[8]  Anmin Zhu,et al.  A SVM-based model for NBA playoffs prediction , 2016 .

[9]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.