DGMSCL: A dynamic graph mixed supervised contrastive learning approach for class imbalanced multivariate time series classification.

In the Imbalanced Multivariate Time Series Classification (ImMTSC) task, minority-class instances typically correspond to critical events, such as system faults in power grids or abnormal health occurrences in medical monitoring. Despite being rare and random, these events are highly significant. The dynamic spatial-temporal relationships between minority-class instances and other instances make them more prone to interference from neighboring instances during classification.

One GHz linewidth, 33 line per mm, wide angle imaging filter at the potassium resonant line.

This paper presents a narrow linewidth, high resolution, and high quantum efficiency imaging transmission filter based on optical trapping of resonance radiation in potassium vapor. The filter can be used to image radiation over a bandwidth narrow enough to fall within a Fraunhofer dark zone in the solar spectrum, and it can be applied to the imaging of flames, plumes or discharges containing potassium. It may also be applicable to the imaging of Raman scattering from a tunable laser.