Learning EFSM Models with Registers in Guards

TL;DR

This paper introduces an active inference approach for learning EFSM models with registers in guards, enabling modeling of systems with parametrized inputs and internal variables without resets, from a single trace.

Contribution

It proposes a novel active inference method for EFSMs that incorporates registers in guards, allowing modeling of complex systems from a single execution trace.

Findings

Successfully models systems with internal registers and parametrized inputs.

Learns EFSM models from a single trace without system resets.

Enhances the expressiveness of EFSMs for software system modeling.

Abstract

This paper presents an active inference method for Extended Finite State Machines, where inputs and outputs are parametrized, and transitions can be conditioned by guards involving input parameters and internal variables called registers. The method applies to (software) systems that cannot be reset, so it learns an EFSM model of the system on a single trace.