### Research Interests
Current research activities are focused on developing methodologies and computational algorithms for early-warning indicators for impending critical transitions or catastrophic failure in engineered and biological systems. The methodologies will employ (neural) network models and uncertainty measures, such as various forms of statistical entropy, and independent signal components to infer the impending onset of critical transitions.
In the case of engineered systems, e.g., power grids, communication networks, etc., the approach would exploit the existence of reliable compact models for its predictive inference. For biological systems, e.g., predicting the impending epileptic seizures from EEG measurements, the approach would adaptively identify a viable model while simultaneously extracting indicators for its prediction. In both domains, the goal is to extract ensembles of the signal’s independent state components and their statistical indicators from measurement profiles to infer the impending catastrophic transition.
