Related papers: Semi-supervised Learning for Detecting Inverse Com…
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets. As a main-stream loss function, the cross entropy can…
Scientists at the Berkeley SETI Research Center are Searching for Extraterrestrial Intelligence (SETI) by a new signal detection method that converts radio signals into spectrograms through Fourier transforms and classifies signals…
The primary purpose of the collective Thomson scattering (CTS) diagnostic at ITER is to measure the properties of fast-ion populations, in particular those of fusion-born $\alpha$-particles. Based on the present design of the diagnostic, we…
In this paper, we propose an anomaly detection algorithm for machine sounds with a deep complex network trained by self-supervision. Using the fact that phase continuity information is crucial for detecting abnormalities in time-series…
The Inert Doublet Model (IDM) is a simple extension of the Standard Model, introducing an additional Higgs doublet that brings in four new scalar particles. The lightest of the IDM scalars is stable and is a good candidate for a dark matter…
Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the first unsupervised anomaly detection framework incorporating a Diffusion Transformer. Raw…
Disentangling coherent and incoherent effects in the photoemission spectra of strongly correlated materials is generally a challenging problem due to the involvement of numerous parameters. In this study, we employ machine learning…
We present a new application of deep learning to reconstruct the cosmic microwave background (CMB) temperature maps from the images of microwave sky, and to use these reconstructed maps to estimate the masses of galaxy clusters. We use a…
Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various…
The field of imbalanced self-supervised learning, especially in the context of tabular data, has not been extensively studied. Existing research has predominantly focused on image datasets. This paper aims to fill this gap by examining the…
We introduce a novel approach to estimate the spectral index, $\beta_s$, of polarised synchrotron emission, combining the moment expansion of CMB and the constrained-ILC. We reconstructed the maps of the first two synchrotron moments,…
The high rate of false alarms in intensive care units (ICUs) is one of the top challenges of using medical technology in hospitals. These false alarms are often caused by patients' movements, detachment of monitoring sensors, or different…
Temperature, density and abundance profiles of the hot intracluster medium (ICM) are important diagnostics of the complex interactions of gravitational and feedback processes in the cores of galaxy clusters. Deprojection of X-ray data by…
Automated anomaly detection is essential for managing information and communications technology (ICT) systems to maintain reliable services with minimum burden on operators. For detecting varying and continually emerging anomalies as…
The role of cosmic rays (CR) in the formation and evolution of clusters of galaxies has been much debated. It may well be related to other fundamental questions, such as the mechanism which heats and virializes the intracluster medium…
Based on a detailed analysis of the high-quality Chandra, XMM-Newton, and Suzaku data of the X-ray bright cluster of galaxies Abell 1795, we report clear evidence for a two-phase intracluster medium (ICM) structure, which consists of a cool…
We use deep archival Chandra and XMM-Newton observations of three of the brightest cluster-centre radio galaxies in the sky, Cygnus A, Hercules A and Hydra A, to search for inverse-Compton emission from the population of electrons…
The integration of communication networks and the Internet of Things (IoT) in Industrial Control Systems (ICSs) increases their vulnerability towards cyber-attacks, causing devastating outcomes. Traditional Intrusion Detection Systems…
In our digital universe nowadays, enormous amount of data are produced in a streaming manner in a variety of application areas. These data are often unlabelled. In this case, identifying infrequent events, such as anomalies, poses a great…
Over the past two decades, the most commonly adopted explanation for high and hard X-ray emission in resolved quasar jets has been inverse Compton upscattering of the Cosmic Microwave Background (IC/CMB), which requires jets which remain…