4. Pattern Detection

After the Process Models are discovered, the pattern detection aims at subgraph discovery using Frequent Subgraph Mining (FSM). The resulting patterns can be interpreted as patterns and can be clustered in the next step: Pattern Clustering

Start the FSM algorithm

This first step is to configure and start the FSM algorithm. The current used FSM algorithm is gSpan [1]. Therefore, the following parameters must be set:

• Support: The number of occurrences of the subgraph

• Min vertices: Minimum number of vertices in the subgraph

• Max vertices: Maximum number of vertices in the subgraph

^{[1] For details see Xifeng Yan & Jiawei Han. (n.d.). gSpan: Graph-based substructure pattern mining. 2002 IEEE International Conference on Data Mining, 2002. Proceedings., 3, 721–724.}

The input for the FSM algorithm are the process models mined in the previous step. After submitting the form, the FSM starts working.

View the results

After the FSM is finished, the resulting sub graphs (interpreted as patterns) can be viewed. The user has the ability to explore each subgraph through simple zoom and mouse navigation controls.