Turf playability testing
Systems and methods for determining a quantifiable playability of a sports surface are disclosed. Test data is included in a test data matrix. A centroid associated with the test data matrix is determined. Distances of data points to the test data matrix are determined. A playability score is calculated as a function of the determined distances.
1. A method, comprising:
generating, by a computing device, a test data matrix comprising a first dimension and a second dimension, each first dimension entry in a plurality of first dimension entries corresponding to a respective tested attribute of a plurality of tested attributes associated with a playing surface, each second dimension entry in a plurality of second dimension entries corresponding to a respective test location of a plurality of test locations on the playing surface;
determining, based on applying a clustering algorithm to at least a portion of the plurality of first dimension entries, a centroid associated with the test data matrix, wherein the centroid comprises a center of a multi-dimensional shape defined by the at least the portion of the plurality of first dimension entries;
determining a plurality of distances relative to the centroid; and
determining, based on a comparison of the plurality of distances to a reference data set, a playability score for the playing surface.
2. The method of claim 1 , further comprising:
generating, based on the test data matrix, one or more additional second dimension entries; and
adding the one or more additional second dimension entries to the test data matrix.
3. The method of claim 2 , wherein generating the one or more additional second dimension entries comprises generating, based on one or more Cartesian cross products, the one or more additional second dimension entries.
4. The method of claim 2 , further comprising selecting, from the test data matrix, a subset of the plurality of second dimension entries.
5. The method of claim 4 , wherein determining the centroid associated with the test data matrix further comprises determining the centroid relative to the subset of the plurality of second dimension entries.
6. The method of claim 4 , wherein determining the plurality of distances comprises determining, for the subset of the plurality of second dimension entries, a corresponding distance to the centroid.
7. The method of claim 4 , wherein determining the subset of the plurality of second dimension entries comprises performing a random selection of the plurality of second dimension entries.
8. The method of claim 1 , wherein determining, based on applying the clustering algorithm to at least the portion of the plurality of first dimension entries, the centroid comprises determining the centroid based on one or more of: a k-means clustering, a density-based spatial clustering of applications with noise (DBSCAN), or a principal component analysis (PCA) clustering.
9. The method of claim 1 , wherein determining the plurality of distances comprises determining a plurality of Euclidean distances or a plurality of cosine distances.
10. The method of claim 1 , wherein the plurality of tested attributes associated with the playing surface comprise one or more of: a g-max, a head injury criterion (HIC), a vertical deformation, an energy restitution, a shear vane, or a rotational traction.
11. A system, comprising:
at least one computing device configured to at least:
generate a test data matrix comprising a first dimension and a second dimension, each first dimension entry in a plurality of first dimension entries corresponding to a respective tested attribute of a plurality of tested attributes associated with a playing surface, each second dimension entry in a plurality of second dimension entries corresponding to a respective test location of a plurality of test locations on the playing surface;
determine, based on applying a clustering algorithm to at least a portion of the plurality of first dimension entries, a centroid associated with the test data matrix, wherein the centroid comprises a center of a multi-dimensional shape defined by the at least the portion of the plurality of first dimension entries;
determine a plurality of distances relative to the centroid; and
determine, based on a comparison of the plurality of distances to a reference data set, a playability score for the playing surface.
12. The system of claim 11 , wherein the at least one computing device is further configured to at least:
generate, based on the test data matrix, one or more additional second dimension entries; and
add the one or more additional second dimension entries to the test data matrix.
13. The system of claim 12 , wherein generating the one or more additional second dimension entries comprises generating, based on one or more Cartesian cross products, the one or more additional second dimension entries.
14. The system of claim 12 , wherein the at least one computing device is further configured to at least select, from the test data matrix, a subset of the plurality of second dimension entries.
15. The system of claim 14 , wherein determining the centroid associated with the test data matrix further comprises determining the centroid relative to the subset of the plurality of second dimension entries.
16. The system of claim 14 , wherein determining the plurality of distances comprises determining, for the subset of the plurality of second dimension entries, a corresponding distance to the centroid.
17. The system of claim 14 , wherein determining the subset of the plurality of second dimension entries comprises performing a random selection of the plurality of second dimension entries.
18. The system of claim 11 , wherein determining, based on applying the clustering algorithm to at least the portion of the plurality of first dimension entries, the centroid comprises determining the centroid based on one or more of: a k-means clustering, a density-based spatial clustering of applications with noise (DBSCAN), or a principal component analysis (PCA) clustering.
19. The system of claim 11 , wherein determining the plurality of distances comprises determining a plurality of Euclidean distances or a plurality of cosine distances.
20. The system of claim 11 , wherein the plurality of tested attributes associated with the playing surface comprise one or more of: a g-max, a head injury criterion (HIC), a vertical deformation, an energy restitution, a shear vane, or a rotational traction.