Embedded Files
Developing fully autonomous systems that adapt continuously to changing and uncertain environments
Creating data-driven models to enhance decision making and resilience in complex industrial processes
Supporting process improvement, optimal and safe operation, and fault detection through the use of industrial data
Exploring how emerging artificial intelligence solutions can best support industry and companies to operate efficiently
Main Research Area
Machine Learning Foundations and Model Architectures
Core ML/DL techniques, architectures, and hybrid modeling approaches.
Feedforward, Convolutional, Recurrent Neural Networks (FNN, CNN, RNN)
Graph Neural Networks (GNNs)
Generative Adversarial Networks (GANs)
Physics-Informed Neural Networks (PINNs)
Development of hybrid models (integrating ML with first-principle models)
Learning Strategy, Experimentation, and Lifecycle Management
Designing, training, deploying, and adapting models in real-world systems.
Machine learning lifecycle: from data collection to deployment and model maintenance
Real-time adaptive learning and agile decision making
Design of experiments (DoE)
Stochastic modeling and optimization
Intelligent Systems for Process Control and Optimization
ML/AI applications in dynamic systems, and complex decision-making.
Advanced process monitoring
Advanced Process Control (APC)
Process optimization and intensification
Reinforcement Learning for solving complex problems (e.g., process design, optimization, control, decision support)
Agentic AI
Publication Topics
Design of Experiments
Process Safety
Process Control
Process Optimization and Intensification
Reaction Engineering
Reinforcement Learning
Resilience Engineering
Soft Sensors
Stochastic Systems
Symbolic Regression
Knowledge Discovery
PhD Theses
If you are interested in our work, please contact Alex Kummer!
e-mail: kummer.alex@mk.uni-pannon.hu
Page updated
Google Sites
Report abuse