Interoperability and integration testing methods for IoT systems: A systematic mapping study

M Bures, M Klima, V Rechtberger, X Bellekens… - … conference on software …, 2020 - Springer
The recent active development of Internet of Things (IoT) solutions in various domains has
led to an increased demand for security, safety, and reliability of these systems. Security and …

Runtime monitors for Markov decision processes

S Junges, H Torfah, SA Seshia - International Conference on Computer …, 2021 - Springer
We investigate the problem of monitoring partially observable systems with nondeterministic
and probabilistic dynamics. In such systems, every state may be associated with a risk, eg …

Benchmarking Combinations of Learning and Testing Algorithms for Automata Learning

BK Aichernig, M Tappler, F Wallner - Formal Aspects of Computing, 2024 - dl.acm.org
Automata learning enables model-based analysis of black-box systems by automatically
constructing models from system observations, which are often collected via testing. The …

Learning finite state models from recurrent neural networks

E Muškardin, BK Aichernig, I Pill, M Tappler - International Conference on …, 2022 - Springer
Explaining and verifying the behavior of recurrent neural networks (RNNs) is an important
step towards achieving confidence in machine learning. The extraction of finite state models …

A framework for identification and validation of affine hybrid automata from input-output traces

X Yang, OA Beg, M Kenigsberg… - ACM Transactions on …, 2022 - dl.acm.org
Automata-based modeling of hybrid and cyber-physical systems (CPS) is an important
formal abstraction amenable to algorithmic analysis of its dynamic behaviors, such as in …

Safe and secure future AI-driven railway technologies: challenges for formal methods in railway

M Seisenberger, MH ter Beek, X Fan, A Ferrari… - … Applications of Formal …, 2022 - Springer
In 2020, the EU launched its sustainable and smart mobility strategy, outlining how it plans
to have a 90% reduction in transport emission by 2050. Central to achieving this goal will be …

Modalas: Model-driven assurance for learning-enabled autonomous systems

MA Langford, KH Chan, JE Fleck… - 2021 ACM/IEEE 24th …, 2021 - ieeexplore.ieee.org
Increasingly, safety-critical systems include artificial intelligence and machine learning
components (ie, Learning-Enabled Components (LECs)). However, when behavior is …

Learning Environment Models with Continuous Stochastic Dynamics

M Tappler, E Muškardin, BK Aichernig… - arXiv preprint arXiv …, 2023 - arxiv.org
Solving control tasks in complex environments automatically through learning offers great
potential. While contemporary techniques from deep reinforcement learning (DRL) provide …

A roadside decision-making methodology based on deep reinforcement learning to simultaneously improve the safety and efficiency of merging zone

J Hu, X Li, Y Cen, Q Xu, X Zhu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The safety and efficiency of the merging zone is particularly important for traffic networks.
Although autonomous vehicle improves the safety and efficiency from vehicle view, traffic …

MoDALAS: addressing assurance for learning-enabled autonomous systems in the face of uncertainty

MA Langford, KH Chan, JE Fleck, PK McKinley… - Software and Systems …, 2023 - Springer
Increasingly, safety-critical systems include artificial intelligence and machine learning
components (ie, learning-enabled components (LECs)). However, when behavior is learned …