Judging where a ball will go: the case of curved free kicks in football

This study examined whether adding spin to a ball in the free kick situation in football affects a professional footballer's perception of the ball's future arrival position. Using a virtual reality set-up, participants observed the flight paths of aerodynamically realistic free kicks with (+/- 600 rpm) and without sidespin. With the viewpoint being fixed in the centre of the goal, participants had to judge whether the ball would have ended up in the goal or not. Results show that trajectories influenced by the Magnus force caused by sidespin gave rise to a significant shift in the percentage of goal responses. The resulting acceleration that causes the ball to continually change its heading direction as the trajectory unfolds does not seem to be taken into account by the participants when making goal judgments. We conclude that the visual system is not attuned to such accelerated motion, which may explain why goalkeepers appear to misjudge the future arrival point of such curved free kicks.

Support vector machine classification for large data sets via minimum enclosing ball clustering

Support vector machine (SVM) is a powerful technique for data classification. Despite of its good theoretic foundations and high classification accuracy, normal SVM is not suitable for classification of large data sets, because the training complexity of SVM is highly dependent on the size of data set. This paper presents a novel SVM classification approach for large data sets by using minimum enclosing ball clustering. After the training data are partitioned by the proposed clustering method, the centers of the clusters are used for the first time SVM classification. Then we use the clusters whose centers are support vectors or those clusters which have different classes to perform the second time SVM classification. In this stage most data are removed. Several experimental results show that the approach proposed in this paper has good classification accuracy compared with classic SVM while the training is significantly faster than several other SVM classifiers.