Sort by
Refine Your Search
-
Listed
-
Employer
-
Field
-
The Rantalainen group is focused on application of machine learning and AI for development and validation of predictive models for cancer precision medicine, with a particular focus computational pathology. Our
-
applications, specifically targeting the prognosis and risk prediction of Heart Failure (HF) in patients. This research integrates AI safety, explainability, and multimodal medical data analysis to enhance
-
of bioadhesives to better predict and optimise the production process and product properties, and thus ultimately expects to enhance the efficiency of the production process in different wood and fibre-based
-
well as contributing to the development of predictive in vitro models for hazard identification. Additional duties include sample collection and characterization of airborne particle emissions at industrial sites
-
to increasing CO2 and climatic change is a large uncertainty for ecosystems, crop productivity and climate predictions. To tackle this uncertainty, we combine: growth chamber experiments, samples from world
-
plants will respond to increasing CO2 and climatic change is a large uncertainty for ecosystems, crop productivity and climate predictions. To tackle this uncertainty, we combine: growth chamber
-
estimates remain highly uncertain because existing approaches often neglect critical lake-specific dynamics and feedback mechanisms that are essential for accurately predicting ecological responses and
-
incorporating machine learning to predict the influence of microstructural features on the structural integrity of metallic materials, e.g., resistance to plastic deformation and crack growth. Responsibilities
-
and climatic change is a large uncertainty for ecosystems, crop productivity and climate predictions. To tackle this uncertainty, we combine: growth chamber experiments, samples from world-unique CO2
-
predictive control under uncertainty for autonomous systems. The research aims to develop improved numerical methods for solving challenging belief-space motion planning problems, where the uncertainty in