Related papers: Meteoroid stream identification with HDBSCAN unsup…
A limitation of many clustering algorithms is the requirement to tune adjustable parameters for each application or even for each dataset. Some techniques require an \emph{a priori} estimate of the number of clusters while density-based…
Molecular electronics studies have advanced from early, simple single-molecule experiments at cryogenic temperatures to complex and multifunctional molecules under ambient conditions. However, room-temperature environments increase the risk…
Clustering techniques have been the key drivers of data mining, machine learning and pattern recognition for decades. One of the most popular clustering algorithms is DBSCAN due to its high accuracy and noise tolerance. Many superior…
Fast radio transient search algorithms identify signals of interest by iterating and applying a threshold on a set of matched filters. These filters are defined by properties of the transient such as time and dispersion. A real transient…
Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks…
Dormant comets in the near-Earth object (NEO) population are thought to be involved in the terrestrial accretion of water and organic materials. Identification of dormant comets is difficult as they are observationally indistinguishable…
In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and…
Clustering, as an unsupervised technique, plays a pivotal role in various data analysis applications. Among clustering algorithms, Spectral Clustering on Euclidean Spaces has been extensively studied. However, with the rapid evolution of…
Gridded satellite precipitation datasets are useful in hydrological applications as they cover large regions with high density. However, they are not accurate in the sense that they do not agree with ground-based measurements. An…
By using an array of high-sensitivity CCD video devices and spectrographs, the activity of meteor events from the poorly-known $\rho$-Geminid meteoroid stream has been monitored during January 2012 and 2013. As a result of this research,…
One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image. This bottleneck is further exacerbated in aerial…
We study the mass spectrum of sub-structures in the Perseus Molecular Cloud Complex traced by 13CO (1-0), finding that $dN/dM\propto M^{-2.4}$ for the standard Clumpfind parameters. This result does not agree with the classical…
In the present work we carry out a study of the high energy cosmic rays mass identification capabilities of a hybrid detector employing both fluorescence telescopes and particle detectors at ground using simulated data. It involves the…
A direct approach to studying the galaxy-halo connection is to analyze groups and clusters of galaxies that trace the underlying dark matter halos, emphasizing the importance of identifying galaxy clusters and their associated brightest…
Meteoroids are pieces of asteroids and comets. They serve as unique probes to the physical and chemical properties of their parent bodies. We can derive some of these properties when meteoroids collide with the atmosphere of Earth and…
A clustering algorithm is applied to Cassini Imaging Science Subsystem continuum and methane band images of Saturns northern hemisphere to objectively classify regional albedo features and aid in their dynamical interpretation. The…
We use a novel cluster identification tool StarGO to explore the metal poor ([Fe/H] $<$ -1.5) outer stellar halo (d $>$ 15 kpc) of the Milky Way using data from Gaia, LAMOST and SDSS. Our method is built using an unsupervised learning…
An Atmospheric Monitoring System (AMS) is a mandatory and key device of a space-based mission which aims to detect Ultra-High Energy Cosmic Rays (UHECR) and Extremely-High Energy Cosmic Rays (EHECR) from Space. JEM-EUSO has a dedicated…
We present SA-DSVN, a 3D convolutional architecture for voxel-level segmentation of structural defects in reinforced concrete using cosmic-ray muon tomography. Unlike conventional reconstruction methods (POCA, MLSD) that rely solely on muon…
This paper proposes a hierarchical clustering approach for the segmentation of mobile LiDAR point clouds. We perform the hierarchical clustering on unorganized point clouds based on a proximity matrix. The dissimilarity measure in the…