Convolutional neural networks (CNNs) are notoriously data-intensive, requiring significantly large datasets for training accurately in an appropriate runtime. Recent approaches aiming to reduce this requirement focus ...

Palladium (Pd) and silver (Ag) are known fission products of TRISO particle nuclear fuels [1]. Pd is known to corrode the silicon carbide (SiC) layer of a TRISO particle, which can compromise the overall fuel performance ...

Additive Manufacturing is 3D printing which requires a set of repeating steps throughout the process. STL, or Standard Triangle Language, is the most important step in the printing process that allows the model to be ...

Additive Manufacturing (AM) is the process of building physical objects by layering materials. It is controlled by G code and a myriad of other codes. CAD models are sliced and converted into a layer by layer code (G Code). ...

As growing efforts take place to enhance the operational safety of nuclear reactors, fuel composites have been explored as replacement to the traditionally used Uranium dioxide (UO2). One potential candidate that has been ...

Probe beam deflection technique (PBDT) was evaluated as a potential method of characterization for both radioactive and non radioactive materials. This method was chosen for its non destructive nature. The analyte of ...

Collected data using a radiation detector to identify anomalies in the presence of naturally occurring radioactive material. Samples of the anomaly signals were put into a Hopfield neural network to train the network ...

Semantic segmentation, the task of classifying objects in an image at a pixel level, has been done since 2012. While our method is not new, our application is. Unlike most tasks which are on clearly-defined objects, the ...