Observing behavioural anomalies
Deadline

Challenge
Manufacturers of cyber-physical systems are often unsure of the behaviour of their system once it is installed at the customer's premises.
Once their customers complain about unwanted behaviour, it often takes a lot of effort to get information about this behaviour via logging or tracing. But even then, it is still not easy to reproduce and analyse this erroneous behaviour.
Therefore, manufacturers need more efficient ways to detect anomalies in their systems, and preferably before their customers do.
Project goal
Based on results of a previous research project, we want to apply the possibilities of Complex Event Processing in a tracing analysis pipeline to detect the behaviour of the system based on defined patterns.
These patterns can be created manually in a test phase of the development of the system or generated by mining existing traces for behavioural patterns.
The goal of the project is to understand an application of Complex Event Processing for behavioural pattern matching and to show the use of automatic learning of behavioural patterns.
Would you also like to participate in this project?
BEHAVE_IRVA is an industrial research project. We are looking for companies that want to be part of the user group and work with us to valorise the project.
Interested? Fill in the form below and we will contact you as soon as possible.