deletions | additions       diff --git a/res_cluster.md b/res_cluster.md  index da0bba7..76bac7b 100644  --- a/res_cluster.md  +++ b/res_cluster.md 
...
Having determined the events in each pixel it is possible to reconstruct the image with reduced noise levels using the matrix \(E\). However, this will not tell us anything about the properties of release events (number, dynamics) as these are made up of several events from different pixels. Therefore it is necessary to combine events from various pixels into macroscopic release events.  This is achieved using the clustering method DBSCAN (\cite{Sander_1998}). \cite{Sander_1998}.  The method finds a clusters of arbitrary shape based on the density of events in parameter space. This is preferable to standard clustering methods which often yield radially symmetric clusters (k-means, etc). Clustering is performed twice. First pixel events are clustered accoring to their shape i.e., clustering is done on matrix \(E_s\). This step distributes pixels into several groups based on solely their shape. For example, into spark and wave events. In the second clustering step, each shape group is clustered based on location. This way, release events consisting on events from multiple pixels are obtained.