Self-Organising Maps: An Objective Method for Clustering Complex Human Movement

In this study self-organising maps (SOM) were used to classify the coordination patterns of four participants performing three different types of basketball shot from different distances. The shots were the free throw, the three-point and the hook shot. The free throw and three-point shot were hypothesised to be more similar to one another than to the hook shot. The first analysis involved an analysis of trial trajectories visualised on a U-matrix. Two of the participants, unexpectedly, showed more similarity between the three-point shot and the hook shot, instead of the free throw. Where the first analysis was useful in showing aspects of the movement that were not obvious from viewing the computer animation of the original movement, a second SOM was trained on the appearance of the original trajectories and used to produce an output that shows the variability in coordination between all trials in the study. The second SOM showed groupings of the three shooting conditions which were unexpected. The second SOM technique may provide a more objective method than visual technique analysis for explaining movement patterning and structuring practice routines.