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.

Require a plugin

Hi,

Can anybody tell me the name of package that implement the token-based conformance checking?

Thanks.

Best regards.

Answers

  • hverbeekhverbeek Posts: 455
    Hi,

    Can you be a bit more specific about the token-based conformance checking? For example, where did you read about this plug-in?

    By heart, I would say that the token-based replay is implemented in ProM 5.2, but not in ProM 6. In ProM 6 it has been superseded by the alignment-based conformance checking (which is implemented in the PNetReplayer package). But I'm not sure this is what you're looking for.

    Kind regards,
    Eric.
  • syjing628syjing628 Posts: 29
    edited April 3
    Dear Eric,

    Many thanks for your reply.

    Recently, I need a solution for activity-level model evaluation, i.e. I want to assign a "score" to each activity in the model. Token-based replay can easily support this idea. On the contrary, it is difficult based on alignment-based replay.

    I wonder is there any methods for this purpose? Or does the token-based replay package can be successfully run in ProM 6. Thanks.

    Best regards.
    Post edited by syjing628 on
  • hverbeekhverbeek Posts: 455
    Hi,

    Why would this be difficult with the alignment-based replay? As a result of that replay, you get an score for every activity how well it fits the data: How many model moves vs how many synchronous moves.

    If the log moves are 'in your way', assign them a very high cost, say 100. The replay will then favor model moves over log moves, so you will only get log moves if really needed.

    As far as I know, the token-based replay does not run in ProM 6. We never ported it to ProM 6 as the alignment-based replay is far better.

    Kind regards,
    Eric.
  • syjing628syjing628 Posts: 29
    Hi Eric,

    I will try the alignment-based replay method and find out whether it can solve my problem or not.

    Again, thanks for your reply.

    Best regards,

    Si-Yuan Jing
Sign In or Register to comment.