Loading [a11y]/accessibility-menu.js
Self-Healing Event Logs | IEEE Journals & Magazine | IEEE Xplore

Abstract:

Event logs of process-aware information systems play an increasingly critical role in today's enterprises because they are the basis for a number of business intelligence...Show More

Abstract:

Event logs of process-aware information systems play an increasingly critical role in today's enterprises because they are the basis for a number of business intelligence applications such as complex event processing, provenance analysis, performance analysis, and process mining. However, due to incorrect manual recording, system errors, and resource constraints, event logs inevitably contain noise in the form of deviating event sequences with redundant, missing, or dislocated events. To repair event logs, existing approaches rely on predefined process models to obtain a minimum recovery for each deviating event sequence. However, process models are typically unavailable in practice, rendering existing approaches inapplicable. In this scenario, can event logs be self-healing? To address this problem, we propose an approach that leverages compliant event sequences to repair deviating sequences. Our approach is effective if the compliant event sequences contain sufficient knowledge for repair. We implement our approach in a prototype and employ the tool to conduct experiments. The experimental results demonstrate that our approach can achieve efficient repairs without the help of process models.
Published in: IEEE Transactions on Knowledge and Data Engineering ( Volume: 33, Issue: 6, 01 June 2021)
Page(s): 2750 - 2763
Date of Publication: 28 November 2019

ISSN Information:

Funding Agency:


References

References is not available for this document.