Hybrid heuristics miner based on time series prediction for streaming process mining

To cope with time-attribute and variations of event distribution in dynamic evolving process, an streaming process mining based on time series prediction and hybrid heuristic miner is proposed. A heuristic miner is improved based on post-task of activity in event logs to optimize the initial particl...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD) pp. 251 - 256
Main Authors Wenan Tan, Li Huang, Tengteng Shen, Anqiong Tang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2016
Subjects
Aging
Algorithm design and analysis
Data mining
Heuristic algorithms
Heuristics Miner
Optimization
Particle swarm optimization
Process Mining
Process Prediction
PSO
Time series analysis
Online AccessGet full text

Cover

More Information
Summary:To cope with time-attribute and variations of event distribution in dynamic evolving process, an streaming process mining based on time series prediction and hybrid heuristic miner is proposed. A heuristic miner is improved based on post-task of activity in event logs to optimize the initial particle distribution for Particle Swarm Optimization. Furthermore, "aging factor" based on time series attribute is also designed for adaptive global optimization. Besides, time-related Process Decision Indicator(PDI) is defined as a pattern observable to identify domain-independent evolution indicators in process model. The experimental results show that our algorithm is more effective and scalable for streaming process mining.
DOI:10.1109/CSCWD.2016.7565997