›
To prevent spam users, you can only post on this forum after registration, which is by invitation. If you want to post on the forum, please send me a mail (h DOT m DOT w DOT verbeek AT tue DOT nl) and I'll send you an invitation in return for an account.

interpretation of results

MunaMuna Posts: 23
in ProM 6
Hello community
What are the resources from which we can give an interpretation of the results found by the plugin.
knowing that we are new to this 
Tagged:

Comments

  • hverbeekhverbeek Posts: 428
    Hi,

    I think you first need to be clear on which plug-in we're talking about. Different plug-in shave different results, and, hence, different interpretations.

    Please try to be as specific as possible in your questions. It is very hard to answer very generic questions.

    Kind regards,
    Eric.
  • MunaMuna Posts: 23
    Im talking about inductive visual miner, I have results that I m not able to interpret ,namely  the image joined. I dont know the significations jholded in this process tree
  • MunaMuna Posts: 23
    The plus triangle refers to what ? exactly ? does it mean that the activities were performed in parallel ? or optional?
  • hverbeekhverbeek Posts: 428
    Hi,

    The plus diamonds are AND-splits and AND-joins (cf. BPMN diagrams). As a result, indeed, the three paths between an AND-split and AND-join can indeed be performed in parallel.

    All simple nodes correspond to XOR splits and XOR-joins. As an example, in your model, the activity "Entree park de visite" was skipped 6 times.

    Kind regards,
    Eric.
  • MunaMuna Posts: 23
    what about the deviations 66 times does it mean that the entree park de visite and scanner were skipped 66 times ? In advance I know that it is not true
  • hverbeekhverbeek Posts: 428
    Hi,

    No, for this, you need to look at the numbers as well. It is obvious that there are 342 cases. However, only 276 pass through "Scanner". The remaining 66 follow the red arc.

    It would have been better if the red arc would only have bypassed "Scanner" (like the "Entree park de visite" is bypassed by 6 cases), but for some reason, this was not done.

    Kind regards,
    Eric.
  • MunaMuna Posts: 23
    Thank you, 
    and that red arc represent what ? I really can get it.
    Does it mean that 66 cases surpass the scanner ? am I correct ?
    Another question on 66 in Entree Terminal export (it is called self edge I guess) as well as (4 in sortie SAS) what does this refer to ?
  • MunaMuna Posts: 23
    that is more precise isnt  it ? so we can modify the paths in order to get the best precision ?  
    dd.JPG 39.6K
  • hverbeekhverbeek Posts: 428
    Hi,

    You can create your own model, but I'm not sure you want to go there.

    An alternative would be to lower the noise threshold. The Inductive Visual Miner typically has the noise threshold set to a value like 0.1 or 0.2. Lowering this value would force it to add some deviations into the model proper (showing them as blue arcs instead of red arcs).

    Kind regards,
    Eric.
  • MunaMuna Posts: 23
    Another thing when looking at the traces, as explaination I see the only in log ignored- or only in model ignored) what does it mean 

    Sorry for my multiple question but I really need to understand
  • hverbeekhverbeek Posts: 428
    Hi,

    If you really need to understand, I suggest to read the thesis titled "Robust process mining with guarantees" by Sander Leemans, which can be found on https://research.tue.nl/en/publications/robust-process-mining-with-guarantees. Chapter 9 in this thesis explain the Inductive Visual Miner in detail.

    Kind regards,
    Eric.


  • MunaMuna Posts: 23
    Thank you for you time and patience

    Best regards
    Mouna
Sign In or Register to comment.