Related papers: Machine learning based data mining for Milky Way f…
This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy…
In this work we explore the possibility of applying machine learning methods designed for one-dimensional problems to the task of galaxy image classification. The algorithms used for image classification typically rely on multiple costly…
Feature selection is an important task in many problems occurring in pattern recognition, bioinformatics, machine learning and data mining applications. The feature selection approach enables us to reduce the computation burden and the…
We present the first results from the science demonstration phase for the Hi-GAL survey, the Herschel key-project that will map the inner Galactic Plane of the Milky Way in 5 bands. We outline our data reduction strategy and present some…
High-quality astronomical images delivered by modern ground-based and space observatories demand adequate, reliable software for their analysis and accurate extraction of sources, filaments, and other structures, containing massive amounts…
We report the first weak-lensing detection of a large-scale filament funneling matter onto the core of the massive galaxy cluster MACSJ0717.5+3745. Our analysis is based on a mosaic of 18 multi-passband images obtained with ACS aboard the…
This paper introduces a new method of data-driven microscope design for virtual fluorescence microscopy. Our results show that by including a model of illumination within the first layers of a deep convolutional neural network, it is…
This study proposes an automated data mining framework based on autoencoders and experimentally verifies its effectiveness in feature extraction and data dimensionality reduction. Through the encoding-decoding structure, the autoencoder can…
Large scale surveys have brought about a revolution in astronomy. To analyse the resulting wealth of data, we need automated tools to identify, classify, and quantify the important underlying structures. We present here a method for…
A common problem in physics is to fit regression data by a parametric class of functions, and to decide whether a certain functional form allows for a good fit of the data. Common goodness of fit methods are based on the calculation of the…
We consider the task of feature selection for reconstruction which consists in choosing a small subset of features from which whole data instances can be reconstructed. This is of particular importance in several contexts involving for…
By removing irrelevant and redundant features, feature selection aims to find a good representation of the original features. With the prevalence of unlabeled data, unsupervised feature selection has been proven effective in alleviating the…
The cycling of material from the interstellar medium (ISM) into stars and the return of stellar ejecta into the ISM is the engine that drives the "galactic ecology" in normal spirals, a cornerstone in the formation and evolution of galaxies…
Filaments are clearly visible in galaxy distributions, but they are hardly detected by computer algorithms. Most methods of filament detection can be used only with numerical simulations of a large-scale structure. New simple and effective…
The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We…
We present a statistical method to derive the stellar density profiles of the Milky Way from spectroscopic survey data, taking into account selection effects. We assume that the selection function of the spectroscopic survey is based on…
High resolution surveys reveal that the interstellar medium in the Milky Way and nearby galaxies consists of interlinked hierarchies of filamentary structure and superbubbles extending from galactic to subpc scales. The characterization of…
Nuclei segmentation and classification is a significant process in pathology image analysis. Deep learning-based approaches have greatly contributed to the higher accuracy of this task. However, those approaches suffer from the imbalanced…
In the field of transmission electron microscopy, data interpretation often lags behind acquisition methods, as image processing methods often have to be manually tailored to individual datasets. Machine learning offers a promising approach…
We introduce a novel orbit superposition method designed to reconstruct the stellar density structure, kinematics, and chemical abundance distribution of the entire Milky Way by leveraging 6D phase-space information from its resolved…