IEEE

Extraction of an Explanatory Graph to Interpret a CNN

Abstract: This paper introduces an explanatory graph representation to reveal object parts encoded inside convolutional layers of a CNN. Given a pre-trained CNN, each filter 1 in a conv-layer usually ...
Royal Society of Chemistry

Food Authenticity Testing by Nuclear Magnetic Resources

Food authenticity testing using Nuclear Magnetic Resonance (NMR) is a powerful technique to verify the composition and quality of food products. NMR spectroscopy can be applied to analyses the ...
IEEE

EEG-SEEGRAPH: Interpreting Functional Connectivity Disruptions in Dementias via Sparse-Explanatory Dynamic EEG-Graph Learning

Abstract: Robust and interpretable dementia diagnosis from noisy, non-stationary electroencephalography (EEG) is clinically essential yet remains challenging. To this end, we propose SeeGraph, a ...
jech.bmj

Who is the expert? A process guide to incorporate lived/living experience into directed acyclic graphs: an applied example from HIV research

Aim Causal inference relies on correct background knowledge, which epidemiologists generally understand to come from academic experts. Our community-engaged study augments scientific domain knowledge ...