Morphological Classification of Galaxies Using SpinalNet

Author(s):  
Dim Shaiakhmetov ◽  
Remudin Reshid Mekuria ◽  
Ruslan Isaev ◽  
Fatma Unsal
Author(s):  
S. N. Bogdanov ◽  
◽  
S. Ju. Babaev ◽  
A. V. Strazhnov ◽  
A. B. Stroganov ◽  
...  

2021 ◽  
Vol 503 (2) ◽  
pp. 1828-1846
Author(s):  
Burger Becker ◽  
Mattia Vaccari ◽  
Matthew Prescott ◽  
Trienko Grobler

ABSTRACT The morphological classification of radio sources is important to gain a full understanding of galaxy evolution processes and their relation with local environmental properties. Furthermore, the complex nature of the problem, its appeal for citizen scientists, and the large data rates generated by existing and upcoming radio telescopes combine to make the morphological classification of radio sources an ideal test case for the application of machine learning techniques. One approach that has shown great promise recently is convolutional neural networks (CNNs). Literature, however, lacks two major things when it comes to CNNs and radio galaxy morphological classification. First, a proper analysis of whether overfitting occurs when training CNNs to perform radio galaxy morphological classification using a small curated training set is needed. Secondly, a good comparative study regarding the practical applicability of the CNN architectures in literature is required. Both of these shortcomings are addressed in this paper. Multiple performance metrics are used for the latter comparative study, such as inference time, model complexity, computational complexity, and mean per class accuracy. As part of this study, we also investigate the effect that receptive field, stride length, and coverage have on recognition performance. For the sake of completeness, we also investigate the recognition performance gains that we can obtain by employing classification ensembles. A ranking system based upon recognition and computational performance is proposed. MCRGNet, Radio Galaxy Zoo, and ConvXpress (novel classifier) are the architectures that best balance computational requirements with recognition performance.


Author(s):  
Saad Elzayat ◽  
Hitham H. Elfarargy ◽  
Islam Soltan ◽  
Mona A. Abdel-Kareem ◽  
Maurizio Barbara ◽  
...  

2011 ◽  
Vol 20 (11) ◽  
pp. 1925-1935 ◽  
Author(s):  
Jung Mo Kim ◽  
Sung-Hwan Moon ◽  
Sung Geum Lee ◽  
Youn Jeong Cho ◽  
Ki Sung Hong ◽  
...  

2021 ◽  
pp. jclinpath-2021-207863
Author(s):  
Lisa N van der Vorm ◽  
Henriët A Hendriks ◽  
Simone M Smits

AimsRecently, a new automated digital cell imaging analyser (Sysmex CellaVision DC-1), intended for use in low-volume and small satellite laboratories, has become available. The purpose of this study was to compare the performance of the DC-1 with the Sysmex DI-60 system and the gold standard, manual microscopy.MethodsWhite blood cell (WBC) differential counts in 100 normal and 100 abnormal peripheral blood smears were compared between the DC-1, the DI-60 and manual microscopy to establish accuracy, within-run imprecision, clinical sensitivity and specificity. Moreover, the agreement between precharacterisation and postcharacterisation of red blood cell (RBC) morphological abnormalities was determined for the DC-1.ResultsWBC preclassification and postclassification results of the DC-1 showed good correlation compared with DI-60 results and manual microscopy. In addition, the within-run SD of the DC-1 was below 1 for all five major WBC classes, indicating good reproducibility. Clinical sensitivity and specificity were, respectively, 96.7%/95.9% compared with the DI-60% and 96.6%/95.3% compared with manual microscopy. The overall agreement on RBC morphology between the precharacterisation and postcharacterisation results ranged from 49% (poikilocytosis) to 100% (hypochromasia, microcytosis and macrocytosis).ConclusionsThe DC-1 has proven to be an accurate digital cell imaging system for differential counting and morphological classification of WBCs and RBCs in peripheral blood smears. It is a compact and easily operated instrument that can offer low-volume and small satellite laboratories the possibilities of readily available blood cell analysis that can be stored and retrieved for consultation with remote locations.


Author(s):  
Pavlova N.R. ◽  
Dzerkal V.M. ◽  
Ponomareva А.А.

In order to preserve, reproduce and effectively use the natural complexes and objects of the DniproDelta as one of the most valuable natural floodplain-littoral complexes in Europe, which have special environmental, recreational, historical and cultural, scientific, educational and aesthetic value, and ensurethe conservationof «DniproDelta»wetland of theinternational importance,the National Natural Park «Lower Dnipro»was created(Decree of the President of Ukraine of November 24, 2015 No 657/2015).The flora of the higher vascular plants of the Park contains 820 species, 40 species of which (4.9% of the total number) are woody plants. Rosaceae Juss. (14 species), Salicaceae Mirb. (7 species), Aceraceae Juss. (3 types) are leading families of the dendroflora of the Park.Biomorphological characteristics of tree plant species in the flora of the Lower Dnipro National Nature Park were carried out according to the following classifications: 1) K. Raunkiersystem of plant life forms; 2) ecological and morphological classification of life forms of I. G. Serebryakov; 3) architectural models of F. Alle, R. Oldeman and P. Tomlinson; 4) classification of the life forms of plants of the temperate zone, which takes into account the vegetative propagation by O. V. Smirnova, L. B. Zaugolnova.AnalysisoftypesofbiomorphsaccordingtotheclassificationofK. Raunkiershowedthatthevastmajorityofdendrofloraspeciesbelongtophanerophytes, amongthem, dependingontheheightoftheplant, therearedifferentgroups-megaphanerophytes(e.g., Populustremula), mesophanerophytes(Salixalba), microphaneorphytes, nanophanerophytes(Amygdalusnana) andhamephytes(Ephedradistachia).According to the ecological and morphological classification of I. G. Serebryakov life forms, the flora of the Park is dominated by forest-steppe trees and forest-type trees.The trees which belong to one life form often differ in the principles of growth and formation of the crown, branching, and general habitus, which is generally considered as an architectural model of a particular species. According to the classification of architectural models by F. Alle, R. Oldeman and P. Tomlinson, in the flora of the Park, there are five models among which the species formed by the model of Tomlinson have a significant representation, and the species formed by the models of Manzheno and Champagne have a smaller representation.Key words:flora, tree, classification, life form, bush. З метою збереження, відтворення і ефективного використання природних комплексів та об’єктів дельти річки Дніпро як одного з найцінніших природних заплавно-літоральних комплексів у Європі, які мають особливу природоохоронну, оздоровчу, історико-культурну, наукову, освітню та естетичну цінність, забезпечення збереження водно-болотного угіддя міжнародного значення «Дельта р. Дніпро» створено Національний природний парк «Нижньодніпровський» (Указ президента України від 24 листопада 2015 року No 657/2015).Флора вищих судинних рослин Парку попередньо складає 820 видів, з них 40 видів (4,9% від загальної кількості) –деревні рослини.Провідні родини дендрофлори Парку –Rosaceae Juss. (14 видів), SalicaceaeMirb. (7 видів), AceraceaeJuss. (3 види). Біоморфологічну характеристику видів деревних рослин у флорі національного природнього парку «Нижньодніпровський» проведено за класифікаціями: 1) система життєвих форм рослин К. Раункієра; 2) еколого-морфологічна класифікація життєвих форм І. Г. Сєрєбрякова; 3) архітектурні моделі Ф. Аллє, Р. Ольдемана і П. Томлінсона; 4)класифікація життєвих форм рослин помірної зони, яка враховує вегетативне розмноження О. В. Смирнової, Л. Б. Заугольнової.Аналіз типів біоморф за класифікацією К. Раункієра показав, що переважна більшість видів дендрофлори належить до фанерофітів, серед них, в залежності від висоти рослини, виділяють різні групи –мегафанерофіти (наприклад, Populus tremula), мезофанерофіти (Salix alba), мікрофанерофіти (Amorpha fruticosa), нанофанерофіти (Amygdalus nana) та хамефіти (Ephedra distachia).За еколого-морфологічною класифікацією життєвих форм І. Г. Сєрєбрякова у флорі Парку домінують дерева лісостепового типу та дерева лісового типу.Дерева, які відносяться до однієї життєвої форми, часто відрізняютьсяпринципами наростання та формування крони, галуженням, загальним габітусом, що загалом розглядається як архітектурна модель конкретного виду. За класифікацією архітектурних моделей Ф.Аллє, Р. Ольдемана і П. Томлінсона у флорі Парку виділено п’ять моделей, серед яких, значне представництво мають види, що формуються за моделлю Томлінсона, менше представництво мають види, що формуються за моделями Манжено та Шампанії.Ключові слова: флора, дерево, класифікація, життєва форма, кущ.


1988 ◽  
Vol 60 (1) ◽  
pp. 232-262 ◽  
Author(s):  
A. K. Moschovakis ◽  
A. B. Karabelas ◽  
S. M. Highstein

1. Neurons in the superior colliculus (SC) of anesthetized paralyzed squirrel monkeys were injected intracellularly with horseradish peroxidase (HRP) to establish a morphological classification of tectal efferent neurons in this species. These neurons were physiologically identified by their antidromic responses following stimulation of the contralateral predorsal bundle or SC. These cells also responded with postsynaptic potentials to stimulation of the ipsilateral substantia nigra and cerebral peduncle and the contralateral tectum. 2. Quantitative light microscopic analysis of the somatodendritic profiles and axonal trajectories of 27 recovered cells revealed the existence of three major groups of tectal efferent neurons: L (n = 7), X (n = 8), and T (n = 12). 3. L neurons are small or medium size cells with relatively elaborate dendritic trees and are located mainly in the superficial layers of the SC. They participate in the ipsilateral descending and dorsal ascending tectofugal bundles. Intrinsic collaterals of L axons deploy a large number of boutons both near the parent cell body and more ventrally within the deeper tectal layers. 4. X neurons are mostly large in size and multipolar in shape with relatively complex dendritic trees. Their cell bodies are situated mainly in the stratum griseum intermedium and occasionally in the stratum opticum. Axons of X neurons participate in the crossed descending and ipsilateral ventral ascending projections of the SC. In addition, the axonal system of about half of the X neurons includes recurrent collaterals. 5. T neurons are located mainly in the ventral stratum opticum and the dorsal stratum griseum intermedium. They have small or medium-sized, trapezoid or ovoid cell bodies and relatively simple radiating or vertical dendritic trees. Their axons usually participate in two of the major tectofugal bundles besides providing a commissural component and recurrent collaterals. 6. Morphological details revealed in the present study support the notion that distinct tectofugal axonal systems originate from efferent neurons of the primate SC that differ both as to their location in the tectum as well as the appearance of their somata and dendritic trees. The resulting morphological classification of tectal efferent cells provides a framework for the analysis of tectal function in terms of populations of identified neurons.


Sign in / Sign up

Export Citation Format

Share Document