deletions | additions       diff --git a/res_cluster.md b/res_cluster.md  index 854d8eb..7e55be0 100644  --- a/res_cluster.md  +++ b/res_cluster.md 
...
This is achieved using the clustering method DBSCAN \cite{Sander_1998}. The works in the parameter space and finds clusters of arbitrary shape based on the density of events. This is preferable to standard clustering methods which often yield radially symmetric clusters (k-means, etc).   Clustering is performed twice. First in two steps. First,  pixel events are clustered distributed into groups  accoring to their shape i.e., clustering is done on the  matrix \(E^s\). This step distributes pixels into several groups based on solely their shape is possible because, although the function used for fitting various release events  (e.g., groups sparks or waves) is the same, the shape parameters  of elementary events composing a event approximating a  spark and are likely to be more similar to other spark events rather than  wave events). events. This is clearly visible on Figure x where ...  .  In the second clustering step, the \(E^p\) matrix is cluster for each shape group and physically nearby clusters of similar events are obtained. With this two-step approach, release events of various types consisting on elementary events from multiple pixels are obtained.