اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMorphological Classification of Galaxies in S-PLUS using an Ensemble of Convolutional Networks
98
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The universe is composed of galaxies that have diverse shapes. Once the structure of a galaxy is determined, it is possible to obtain important information about its formation and evolution. Morphologically classifying galaxies means cataloging them according to their visual appearance and the classification is linked to the physical properties of the galaxy. A morphological classification made through visual inspection is subject to biases introduced by subjective observations made by human volunteers. For this reason, systematic, objective and easily reproducible classification of galaxies has been gaining importance since the astronomer Edwin Hubble created his famous classification method. In this work, we combine accurate visual classifications of the Galaxy Zoo project with emph {Deep Learning} methods. The goal is to find an efficient technique at human performance level classification, but in a systematic and automatic way, for classification of elliptical and spiral galaxies. For this, a neural network model was created through an Ensemble of four other convolutional models, allowing a greater accuracy in the classification than what would be obtained with any one individual. Details of the individual models and improvements made are also described. The present work is entirely based on the analysis of images (not parameter tables) from DR1 (www.datalab.noao.edu) of the Southern Photometric Local Universe Survey (S-PLUS). In terms of classification, we achieved, with the Ensemble, an accuracy of $approx 99 %$ in the test sample (using pre-trained networks).
قيم البحث
اقرأ أيضاً
Breast cancer is one of the leading causes of death across the world in women. Early diagnosis of this type of cancer is critical for treatment and patient care. Computer-aided detection (CAD) systems using convolutional neural networks (CNN) could a
ssist in the classification of abnormalities. In this study, we proposed an ensemble deep learning-based approach for automatic binary classification of breast histology images. The proposed ensemble model adapts three pre-trained CNNs, namely VGG19, MobileNet, and DenseNet. The ensemble model is used for the feature representation and extraction steps. The extracted features are then fed into a multi-layer perceptron classifier to carry out the classification task. Various pre-processing and CNN tuning techniques such as stain-normalization, data augmentation, hyperparameter tuning, and fine-tuning are used to train the model. The proposed method is validated on four publicly available benchmark datasets, i.e., ICIAR, BreakHis, PatchCamelyon, and Bioimaging. The proposed multi-model ensemble method obtains better predictions than single classifiers and machine learning algorithms with accuracies of 98.13%, 95.00%, 94.64% and 83.10% for BreakHis, ICIAR, PatchCamelyon and Bioimaging datasets, respectively.
Acute Lymphoblastic Leukemia (ALL) is a blood cell cancer characterized by numerous immature lymphocytes. Even though automation in ALL prognosis is an essential aspect of cancer diagnosis, it is challenging due to the morphological correlation betwe
en malignant and normal cells. The traditional ALL classification strategy demands experienced pathologists to carefully read the cell images, which is arduous, time-consuming, and often suffers inter-observer variations. This article has automated the ALL detection task from microscopic cell images, employing deep Convolutional Neural Networks (CNNs). We explore the weighted ensemble of different deep CNNs to recommend a better ALL cell classifier. The weights for the ensemble candidate models are estimated from their corresponding metrics, such as accuracy, F1-score, AUC, and kappa values. Various data augmentations and pre-processing are incorporated for achieving a better generalization of the network. We utilize the publicly available C-NMC-2019 ALL dataset to conduct all the comprehensive experiments. Our proposed weighted ensemble model, using the kappa values of the ensemble candidates as their weights, has outputted a weighted F1-score of 88.6 %, a balanced accuracy of 86.2 %, and an AUC of 0.941 in the preliminary test set. The qualitative results displaying the gradient class activation maps confirm that the introduced model has a concentrated learned region. In contrast, the ensemble candidate models, such as Xception, VGG-16, DenseNet-121, MobileNet, and InceptionResNet-V2, separately produce coarse and scatter learned areas for most example cases. Since the proposed kappa value-based weighted ensemble yields a better result for the aimed task in this article, it can experiment in other domains of medical diagnostic applications.
Our goal is to morphologically classify the sources identified in the images of the J-PLUS early data release (EDR) into compact (stars) or extended (galaxies) using a suited Bayesian classifier. J-PLUS sources exhibit two distinct populations in the
r-band magnitude vs. concentration plane, corresponding to compact and extended sources. We modelled the two-population distribution with a skewed Gaussian for compact objects and a log-normal function for the extended ones. The derived model and the number density prior based on J-PLUS EDR data were used to estimate the Bayesian probability of a source to be star or galaxy. This procedure was applied pointing-by-pointing to account for varying observing conditions and sky position. Finally, we combined the morphological information from g, r, and i broad bands in order to improve the classification of low signal-to-noise sources. The derived probabilities are used to compute the pointing-by-pointing number counts of stars and galaxies. The former increases as we approach to the Milky Way disk, and the latter are similar across the probed area. The comparison with SDSS in the common regions is satisfactory up to r ~ 21, with consistent numbers of stars and galaxies, and consistent distributions in concentration and (g - i) colour spaces. We implement a morphological star/galaxy classifier based on PDF analysis, providing meaningful probabilities for J-PLUS sources to one magnitude deeper (r ~ 21) than a classical boolean classification. These probabilities are suited for the statistical study of 150k stars and 101k galaxies with 15 < r < 21 present in the 31.7 deg2 of the J-PLUS EDR. In a future version of the classifier, we will include J-PLUS colour information from twelve photometric bands.
Quantitative ultrasound (QUS) can reveal crucial information on tissue properties such as scatterer density. If the scatterer density per resolution cell is above or below 10, the tissue is considered as fully developed speckle (FDS) or low-density s
catterers (LDS), respectively. Conventionally, the scatterer density has been classified using estimated statistical parameters of the amplitude of backscattered echoes. However, if the patch size is small, the estimation is not accurate. These parameters are also highly dependent on imaging settings. In this paper, we propose a convolutional neural network (CNN) architecture for QUS, and train it using simulation data. We further improve the network performance by utilizing patch statistics as additional input channels. We evaluate the network using simulation data, experimental phantoms and in vivo data. We also compare our proposed network with different classic and deep learning models, and demonstrate its superior performance in classification of tissues with different scatterer density values. The results also show that the proposed network is able to work with different imaging parameters with no need for a reference phantom. This work demonstrates the potential of CNNs in classifying scatterer density in ultrasound images.
This work is a Brazilian-Indian collaboration. It aims at investigating the structuralproperties of Lenticular galaxies in the Stripe 82 using a combination of S-PLUS (Southern Photometric Local Universe Survey) and SDSS data. S-PLUS is a noveloptica
l multi-wavelength survey which will cover nearly 8000 square degrees of the Southern hemisphere in the next years and the first data release covers the Stripe 82 area. The morphological classification and study of the galaxies stellar population will be performed combining the Bayesian Spectral type (from BPZ) and Morfometryka (MFMTK) parameters. BPZ and MFMTK are two complementary techniques, since the first one determines the most likely stellar population of a galaxy, in order to obtain its photometric redshift (phot-z), and the second one recovers non-parametric morphological quantities, such as asymmetries and concentration. The combination ofthe two methods allows us to explore the correlation between galaxies shapes (smooth, with spiral arms, etc.) and their stellar contents (old or young population). The preliminary results, presented in this work, show how this new data set opens a new window on our understanding of the nearby universe.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
