Title :
Workflow mining: Extending the αalgorithm to mine duplicate tasks
Author :
Gu, Chun-qin ; Chang, Hui-you ; Yi, Yang
Author_Institution :
Dept. of Inf. Sci. & Technol., Sun Yat-Sen Univ., Guangzhou
Abstract :
Designing a workflow model is a complicated, time-consuming and error-prone process. A possible solution is workflow mining which extracts workflow models from workflow logs. Considerable researches have been done to develop heuristics to mine event-data logs in order to make a workflow model. However, if there are cyclic tasks in workflow traces, the current research in workflow mining still has problems in mining duplicate tasks. Based on the alpha-algorithm, an improved workflow mining algorithm called alpha#-algorithm is presented. The complete experiments have been done to evaluate the proposed algorithm.
Keywords :
data mining; knowledge management; workflow management software; alpha#-algorithm; duplicate tasks mining; event-data logs mining; workflow logs; workflow mining; workflow model design; workflow traces; Computer errors; Cybernetics; Data mining; Electronic mail; Heuristic algorithms; Information science; Knowledge management; Machine learning; Petri nets; Sun; Workflow mining; cyclic tasks; duplicate tasks; workflow model;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620432
