1 - 10 of 15 Results
ORNL researchers have developed a deep learning-based approach to rapidly perform high-quality reconstructions from sparse X-ray computed tomography measurements.
We have been working to adapt background oriented schlieren (BOS) imaging to directly visualize building leakage, which is fast and easy.
The invention introduces a novel, customizable method to create, manipulate, and erase polar topological structures in ferroelectric materials using atomic force microscopy.
High coercive fields prevalent in wurtzite ferroelectrics present a significant challenge, as they hinder efficient polarization switching, which is essential for microelectronic applications.
Fusion reactors need efficient systems to create tritium fuel and handle intense heat and radiation. Traditional liquid metal systems face challenges like high pressure losses and material breakdown in strong magnetic fields.
The traditional window installation process involves many steps. These are becoming even more complex with newer construction requirements such as installation of windows over exterior continuous insulation walls.
This invention utilizes new techniques in machine learning to accelerate the training of ML-based communication receivers.
Current technology for heating, ventilation, and air conditioning (HVAC) and other uses such as vending machines rely on refrigerants that have high global warming potential (GWP).
This invention presents technologies for characterizing physical properties of a sample's surface by combining image processing with machine learning techniques.