Fig 1.
The serving position and its corresponding number.
Table 1.
The serving position and its corresponding number.
Table 2.
Names and corresponding numbers of techniques used.
Table 3.
Typical scoring condition dataset.
Fig 2.
Correlation matrix between the parameters of the dataset "input".
(The color of each grid in the figure indicates the magnitude of the correlation coefficient between the two variables, with colors closer to red indicating a higher degree of positive correlation, closer to blue indicating a higher degree of negative correlation, and colors closer to white indicating no or little correlation).
Fig 3.
Results of principal component analysis method.
(Class Cluster 1 and Class Cluster 2 in the figure are separated point distributions after fusing 8 parameters, Principal Component 1 and Principal Component 2 represent the coordinates of the data in the new space, they are the two most important directions in the data, there are better clusters with clearer boundaries, and they are able to capture the maximum data variance).
Table 4.
Prediction results of different machine learning methods.
Fig 4.
Prediction results of different kernel functions for support vector machine.
Fig 5.
Random forest and XGBoost predict the importance of "input" parameters.
Fig 6.
Statistics on the number of strikes in different rounds by An Se-young.
Fig 7.
An So-young’s scoring situation the last 3 shots techniques.
Fig 8.
An So-young’s missing situation the last 3 shots techniques.
Fig 9.
The last 3 shots area of An So-young’s scoring.
Fig 10.
The last 3 shots area of An So-young’s missing.