Research
Our research interest broadly explores
- How to design a framework for the efficient processing of low-level data allowing to extract process knowledge?
- How can machine learning be used to increase data quality (e.g. noise) and thus accelerate data and process analysis?
- How can synthetic data be efficiently generated that enable privacy-awareness or distributed analysis?
- How can machine learning be used to reduce the involvement of users, but to increase the quality of the data-driven, discovered processes?
The following figure shows our process analytics pipeline that we apply for unstructured data like IoT data, time-series and video-based data. First, the raw data must be pre-processed. Then, aggregation and abstraction techniques must be applied on the pre-processed data to enhance the data with semantics. Next, process mining techniques are applied to discover a process, which gives the data a behavioral structure. Finally, enhanced visualization techniques like AR or VR improve the exploration of processes and data.
We are open to (interdisciplinary) collaborations. Please feel free to contact us.