Research

Domain-aware Sensor-Based Modeling for Complex Systems

This research focuses on leveraging domain expertise to enhance sensor-based models for complex systems. By integrating domain-specific knowledge, we aim to improve the accuracy and reliability of data-driven models, making them more adept at predicting system behaviors and outcomes. This approach not only enhances the performance of predictive models but also ensures that they are robust across varied real-world scenarios. 

Smart AI-Based Systems for Predictive and Preventive Analytics

Our research develops intelligent AI systems that predict outcomes and prevent undesirable events before they occur. These systems utilize advanced machine learning algorithms and big data analytics to foresee potential problems and intervene proactively. This dual focus allows for a more comprehensive approach to decision-making and management, significantly enhancing operational efficiency and safety in critical sectors. 

Adaptive Stochastic and Robust Control in predictive Digital Twin

The research focuses on developing advanced control strategies that leverage digital twin technology. This research integrates stochastic modeling to account for uncertainties in system behaviors, and robust control methods to ensure performance stability under diverse operational conditions. We aim to enhance the predictive accuracy and operational efficiency of digital twins, enabling real-time decision-making and optimization in complex environments.