The main goal of the process mining is discovering models from event logs. The usefulness level of these discovered models is directly related to the quality of event logs. Many researchers have observed serious deciencies with regard to the quality of event logs and have proposed various solutions to improve the overall quality of discovered process models. Amongst all, only a few have considered the application of a reliable external source in the improvement of the quality of process event logs. Every activity, in a process, is known to leave some trace in the process event le. Besides, when a process instance is executed, the corresponding operations are applied to the database and their impacts are stored in the database bin log. Therefore, the database bin log can be utilized as a reliable relevant source in improving the quality improvement of an event log. In this paper, we propose a method to repair the event log using the database bin log. We show that database operations can be employed in order to overcome the inadequacies of event logs including incorrect and missing data. To this end, we, rst, extract an ontology from each of the event logs and the bin log. Then, we match the extracted ontologies in order to remove inadequacies from the event log. Model validation and evaluation results show the stability of our proposed model, as well as, its superiority over related works.

Keywords