this is for holding javascript data
Lucas Fidon edited subsubsection_Position_based_metric_Goal__.tex
almost 8 years ago
Commit id: 9aa201dc9a3cdf70b537e280a12dab814de4088a
deletions | additions
diff --git a/subsubsection_Position_based_metric_Goal__.tex b/subsubsection_Position_based_metric_Goal__.tex
index ae367a6..8c5d4e3 100644
--- a/subsubsection_Position_based_metric_Goal__.tex
+++ b/subsubsection_Position_based_metric_Goal__.tex
...
\subsubsection{Position-based metric}
When $C_{penalty}$ is low $(C_{penalty}=1.3)$ almost 75\% of the clusters contain only one player.
Goal keepers appear almost always isolated in two different clusters excepting during an action embedding or close to a shot. They are the last players to join the last cluster when $C_{penalty}$ is increased.
During the first minutes of the play we get less clusters embedding more players (2 clusters with 6 players) which might be due, in part, to the disorganization of the team at the beginning.
Those results are encouraging. It seems MI-based metric with position is relevant for the cues about a match we were looking
for. for adjusting accurately $C_{penalty}$.