Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAutomatic classification of eclipsing binaries light curves using neural networks
42
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
In this work we present a system for the automatic classification of the light curves of eclipsing binaries. This system is based on a classification scheme that aims to separate eclipsing binary sistems according to their geometrical configuration in a modified version of the traditional classification scheme. The classification is performed by a Bayesian ensemble of neural networks trained with {em Hipparcos} data of seven different categories including eccentric binary systems and two types of pulsating light curve morphologies.
rate research
Read More
We present a catalog of 56 candidate intermediate mass eclipsing binary systems extracted from the 3rd data release of the All Sky Automated Survey. We gather pertinent observational data and derive orbital properties, including ephemerides, for these systems as a prelude to anticipated spectroscopic observations. We find that 37 of the 56, or ~66% of the systems are not identified in the Simbad Astronomical Database as known binaries. As a specific example, we show spectroscopic data obtained for the system HI Mon (B0 V + B0.5 V) observed at key orbital phases based on the computed ephemeris, and we present a combined spectroscopic and photometric solution for the system and give stellar parameters for each component.
The Kepler Mission has provided unprecedented, nearly continuous photometric data of $sim$200,000 objects in the $sim$105 deg$^{2}$ field of view from the beginning of science operations in May of 2009 until the loss of the second reaction wheel in May of 2013. The Kepler Eclipsing Binary Catalog contains information including but not limited to ephemerides, stellar parameters and analytical approximation fits for every known eclipsing binary system in the Kepler Field of View. Using Target Pixel level data collected from Kepler in conjunction with the Kepler Eclipsing Binary Catalog, we identify false positives among eclipsing binaries, i.e. targets that are not eclipsing binaries themselves, but are instead contaminated by eclipsing binary sources nearby on the sky and show eclipsing binary signatures in their light curves. We present methods for identifying these false positives and for extracting new light curves for the true source of the observed binary signal. For each source, we extract three separate light curves for each quarter of available data by optimizing the signal-to-noise ratio, the relative percent eclipse depth and the flux eclipse depth. We present 289 new eclipsing binaries in the Kepler Field of View that were not targets for observation, and these have been added to the Catalog. An online version of this Catalog with downloadable content and visualization tools is maintained at http://keplerEBs.villanova.edu.
Automatic modulation classification (AMC) is of crucial importance for realizing wireless intelligence communications. Many deep learning based models especially convolution neural networks (CNNs) have been proposed for AMC. However, the computation cost is very high, which makes them inappropriate for beyond the fifth generation wireless communication networks that have stringent requirements on the classification accuracy and computing time. In order to tackle those challenges, a novel involution enabled AMC scheme is proposed by using the bottleneck structure of the residual networks. Involution is utilized instead of convolution to enhance the discrimination capability and expressiveness of the model by incorporating a self-attention mechanism. Simulation results demonstrate that our proposed scheme achieves superior classification performance and faster convergence speed comparing with other benchmark schemes.
Colorectal cancer is the third most common cancer-related death after lung cancer and breast cancer worldwide. The risk of developing colorectal cancer could be reduced by early diagnosis of polyps during a colonoscopy. Computer-aided diagnosis systems have the potential to be applied for polyp screening and reduce the number of missing polyps. In this paper, we compare the performance of different deep learning architectures as feature extractors, i.e. ResNet, DenseNet, InceptionV3, InceptionResNetV2 and SE-ResNeXt in the encoder part of a U-Net architecture. We validated the performance of presented ensemble models on the CVC-Clinic (GIANA 2018) dataset. The DenseNet169 feature extractor combined with U-Net architecture outperformed the other counterparts and achieved an accuracy of 99.15%, Dice similarity coefficient of 90.87%, and Jaccard index of 83.82%.
We present a content-based automatic music tagging algorithm using fully convolutional neural networks (FCNs). We evaluate different architectures consisting of 2D convolutional layers and subsampling layers only. In the experiments, we measure the AUC-ROC scores of the architectures with different complexities and input types using the MagnaTagATune dataset, where a 4-layer architecture shows state-of-the-art performance with mel-spectrogram input. Furthermore, we evaluated the performances of the architectures with varying the number of layers on a larger dataset (Million Song Dataset), and found that deeper models outperformed the 4-layer architecture. The experiments show that mel-spectrogram is an effective time-frequency representation for automatic tagging and that more complex models benefit from more training data.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
