deletions | additions       diff --git a/section_Conclusion_begin_itemize_item__.tex b/section_Conclusion_begin_itemize_item__.tex  index 6df4a0c..e8dfac4 100644  --- a/section_Conclusion_begin_itemize_item__.tex  +++ b/section_Conclusion_begin_itemize_item__.tex 
...
\section{Conclusion}  \begin{itemize}  \item application for biomedical image analysis  \item try to use position and acceleration at the same time with an APC  \item find a way to measure how well are our cluster  \end{itemize}  Mutual Information of players position based metric has shown to give very encouraging results for automatic analysis of soccer players.  Indeed with a few tests only it has been possible to give concrete interpretations to the clusters provided by the algorithm.   Some further tests should be driven to understand why it works and why the mutual information of players acceleration based metric doesn't work.