Related papers: Using Multiple Instance Learning for Explainable S…
Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited. Stellar flare forecasting can provide additional flare event samples to support research efforts. Despite this…
In this study we determine scaling relationships of observed solar flares that can be used to predict upper limits of the GOES-class magnitude of solar flares. The flare prediction scheme is based on the scaling of the slowly-varying…
Dynamics of hot chromospheric plasma of solar flares is a key to understanding of mechanisms of flare energy release and particle acceleration. A moderate M1.0 class flare of 12 June, 2014 (SOL2014-06-12T21:12) was simultaneously observed…
Red-shifted components of chromospheric emission lines in the hard X-ray impulsive phase of solar flares have recently been studied through their 30 s evolution with the high resolution of IRIS. Radiative-hydrodynamic flare models show that…
Multiple Instance Learning (MIL) methods have succeeded remarkably in histopathology whole slide image (WSI) analysis. However, most MIL models only offer attention-based explanations that do not faithfully capture the model's decision…
We propose a novel framework to classify large-scale time series data with long duration. Long time seriesclassification (L-TSC) is a challenging problem because the dataoften contains a large amount of irrelevant information to…
We present the study of the X2-class flare which occurred on the 27 October 2014 and was observed with the Interface Region Imaging Spectrograph (IRIS) and the EUV Imaging Spectrometer (EIS) on board the Hinode satellite. Thanks to the high…
Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation…
Introducing thresholds to analyze time series of emission from the Sun enables a new and simple definition of solar flare events, and their interoccurrence times. Rescaling time by the rate of events, the waiting and quiet time…
We study the M1.9 class solar flare SOL2015-09-27T10:40 UT using high-resolution full-Stokes imaging spectropolarimetry of the Ca ii 8542 {\AA} line obtained with the CRISP imaging spectropolarimeter at the Swedish 1-m Solar Telescope.…
We introduce a hybrid approach to solar flare prediction, whereby a supervised regularization method is used to realize feature importance and an unsupervised clustering method is used to realize the binary flare/no-flare decision. The…
Traditional supervised learning tasks require a label for every instance in the training set, but in many real-world applications, labels are only available for collections (bags) of instances. This problem setting, known as multiple…
We propose a new formulation of Multiple-Instance Learning (MIL), in which a unit of data consists of a set of instances called a bag. The goal is to find a good classifier of bags based on the similarity with a "shapelet" (or pattern),…
Studies on the dynamics of solar filaments have significant implications for understanding their formation, evolution, and eruption, which are of great importance for space weather warning and forecasting. The H$\alpha$ Imaging Spectrograph…
Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…
Theoretical stellar spectra rely on model stellar atmospheres computed based on our understanding of the physical laws at play in the stellar interiors. These models, coupled with atomic and molecular line databases, are used to generate…
Weakly supervised whole slide image classification is usually formulated as a multiple instance learning (MIL) problem, where each slide is treated as a bag, and the patches cut out of it are treated as instances. Existing methods either…
The flare activity of the Sun has been studied for decades, using both space- and ground-based telescopes. In particular, the Interface Region Imaging Spectrograph (IRIS) provides unique diagnostics to investigate the thermodynamics of…
Multiple instance learning (MIL) models have achieved remarkable success in analyzing whole slide images (WSIs) for disease classification problems. However, with regard to gigapixel WSI classification problems, current MIL models are often…
The Interface Region Imaging Spectrograph (IRIS) has routinely observed the flaring Mg II NUV spectrum, offering excellent diagnostic potential and a window into the location of energy deposition. A number of studies have forward modelled…