Generating and Analyzing Data Set of Workflow-Nets

Generating and Analyzing Data Set of Workflow-Nets

This paper proposes a machine learning-based method to study workflow-nets (WF-nets for short) and its properties, especially soundness property. We first proposed how to generate a large amount of WF-nets. Next, we generated a data set by using the proposed method and systematically analyzed it on...

Full description

Saved in:
Bibliographic Details
Published in:2020 Eighth International Symposium on Computing and Networking Workshops (CANDARW) pp. 471 - 473
Main Authors: Matsubara, Shohei, Yamaguchi, Shingo, Bin Ahmadon, Mohd Anuaruddin
Format: Conference Proceeding
Language:English
Published: IEEE 01-11-2020
Subjects:
Conferences
Learning systems
machine-learning
Measurement
Petri net
Petri nets
Soundness
verification
Workflow net
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a machine learning-based method to study workflow-nets (WF-nets for short) and its properties, especially soundness property. We first proposed how to generate a large amount of WF-nets. Next, we generated a data set by using the proposed method and systematically analyzed it on some metrics. Finally, we tried to apply a machine learning-based method to verify the soundness problem. The experimental result shows that the accuracy was 78% for the soundness of a subclass of WF-nets called asymmetric choice WF-nets.
DOI:10.1109/CANDARW51189.2020.00097