scholarly journals Galaxy Morphological Image Classification using ResNet

2021 ◽  
pp. 3690-3696
Author(s):  
Siddhartha Banerjee ◽  
Bibek Ranjan Ghosh ◽  
Ayan Gangapadhyay ◽  
Himadri Sankar Chatterjee

     Machine learning-based techniques are used widely for the classification of images into various categories. The advancement of Convolutional Neural Network (CNN) affects the field of computer vision on a large scale. It has been applied to classify and localize objects in images. Among the fields of applications of CNN, it has been applied to understand huge unstructured astronomical data being collected every second. Galaxies have diverse and complex shapes and their morphology carries fundamental information about the whole universe. Studying these galaxies has been a tremendous task for the researchers around the world. Researchers have already applied some basic CNN models to predict the morphological classes of the galaxies. In this paper, a residual network (ResNet) model is applied for this purpose. The proposed methodology classified the galaxies depending on their shape into 37 different classes. The performance of the methodology was evaluated using the data set provided by Kaggle. In this data set, 61,578 galaxy images are given, which are classified by human eye. The model achieved nearly 98% accuracy.

2018 ◽  
Vol 48 (4) ◽  
pp. 564-588 ◽  
Author(s):  
Dick Kasperowski ◽  
Thomas Hillman

In the past decade, some areas of science have begun turning to masses of online volunteers through open calls for generating and classifying very large sets of data. The purpose of this study is to investigate the epistemic culture of a large-scale online citizen science project, the Galaxy Zoo, that turns to volunteers for the classification of images of galaxies. For this task, we chose to apply the concepts of programs and antiprograms to examine the ‘essential tensions’ that arise in relation to the mobilizing values of a citizen science project and the epistemic subjects and cultures that are enacted by its volunteers. Our premise is that these tensions reveal central features of the epistemic subjects and distributed cognition of epistemic cultures in these large-scale citizen science projects.


2012 ◽  
Vol 2012 ◽  
pp. 1-13
Author(s):  
Chao Dong ◽  
Lianfang Tian

Benefiting from the kernel skill and the sparse property, the relevance vector machine (RVM) could acquire a sparse solution, with an equivalent generalization ability compared with the support vector machine. The sparse property requires much less time in the prediction, making RVM potential in classifying the large-scale hyperspectral image. However, RVM is not widespread influenced by its slow training procedure. To solve the problem, the classification of the hyperspectral image using RVM is accelerated by the parallel computing technique in this paper. The parallelization is revealed from the aspects of the multiclass strategy, the ensemble of multiple weak classifiers, and the matrix operations. The parallel RVMs are implemented using the C language plus the parallel functions of the linear algebra packages and the message passing interface library. The proposed methods are evaluated by the AVIRIS Indian Pines data set on the Beowulf cluster and the multicore platforms. It shows that the parallel RVMs accelerate the training procedure obviously.


Author(s):  
G. Keerthi Devipriya ◽  
E. Chandana ◽  
B. Prathyusha ◽  
T. Seshu Chakravarthy

Here by in this paper we are interested for classification of Images and Recognition. We expose the performance of training models by using a classifier algorithm and an API that contains set of images where we need to compare the uploaded image with the set of images available in the data set that we have taken. After identifying its respective category the image need to be placed in it. In order to classify images we are using a machine learning algorithm that comparing and placing the images.


Over the few years the world has seen a surge in fake news and some people are even calling it an epidemic. Misleading false articles are sold as news items over social media, whatsapp etc where no proper barrier is set to check the authenticity of posts. And not only articles but news items also contain images which are doctored to mislead the public or cause sabotage. Hence a proper barrier to check for authenticity of images related to news items is absolutely necessary. And hence classification of images(related to news items) on the basis of authenticity is imminent. This paper discusses the possibilities of identifying fake images using machine learning techniques. This is an introduction into fake news detection using the latest evolving neural network models


GEOgraphia ◽  
2010 ◽  
Vol 10 (19) ◽  
pp. 7
Author(s):  
Jörg Scheffer

Resumo: As divisões do mundo pautadas por marcos culturais têm uma longa tradição na geografia germanófona. Até os dias de hoje, a cultura é conceitualizada como totalidade, o que leva conseqüentemente a que cada divisão absolutize as diferenças culturais. O artigo descreve esta problemática com base nos conceitos clássicos desde os primórdios da geografia até a geografia do presente. Também para a discussão atual pode-se constatar que a idéia de um conceito holístico de cultura ainda permanece usual e até agora não foi substituída por uma regionalização alternativa. O artigo conclui com uma sugestão de como esta regionalização alternativa poderia ser na era da globalização. Culture as holism: large-scale classification of the world in German-speaking geography Abstract: Divisions of the world using culture as the defining trait have had a long history in German geography. Until this day, culture is being conceptionalized as a whole, with the consequence that each division poses cultural differences as absolutes. This essay aims to describe the problem by using traditional concepts from the beginning of geography up to the present. Even in the current debate, as will be shown, the idea of a holistic concept of culture is still in use and has not been replaced yet by an alternative form of regionalisation. The article will conclude with a suggestion of what this would look like in the age of globalisation. Keywords: Culture, division of the world, holism, globalisation, German classics


2021 ◽  
Author(s):  
Joanne Chen Lyu ◽  
Eileen Le Han ◽  
Garving K Luli

BACKGROUND Vaccination is a cornerstone of the prevention of communicable infectious diseases; however, vaccines have traditionally met with public fear and hesitancy, and COVID-19 vaccines are no exception. Social media use has been demonstrated to play a role in the low acceptance of vaccines. OBJECTIVE The aim of this study is to identify the topics and sentiments in the public COVID-19 vaccine–related discussion on social media and discern the salient changes in topics and sentiments over time to better understand the public perceptions, concerns, and emotions that may influence the achievement of herd immunity goals. METHODS Tweets were downloaded from a large-scale COVID-19 Twitter chatter data set from March 11, 2020, the day the World Health Organization declared COVID-19 a pandemic, to January 31, 2021. We used R software to clean the tweets and retain tweets that contained the keywords <i>vaccination</i>, <i>vaccinations</i>, <i>vaccine</i>, <i>vaccines</i>, <i>immunization</i>, <i>vaccinate</i>, and <i>vaccinated</i>. The final data set included in the analysis consisted of 1,499,421 unique tweets from 583,499 different users. We used R to perform latent Dirichlet allocation for topic modeling as well as sentiment and emotion analysis using the National Research Council of Canada Emotion Lexicon. RESULTS Topic modeling of tweets related to COVID-19 vaccines yielded 16 topics, which were grouped into 5 overarching themes. Opinions about vaccination (227,840/1,499,421 tweets, 15.2%) was the most tweeted topic and remained a highly discussed topic during the majority of the period of our examination. Vaccine progress around the world became the most discussed topic around August 11, 2020, when Russia approved the world’s first COVID-19 vaccine. With the advancement of vaccine administration, the topic of instruction on getting vaccines gradually became more salient and became the most discussed topic after the first week of January 2021. Weekly mean sentiment scores showed that despite fluctuations, the sentiment was increasingly positive in general. Emotion analysis further showed that trust was the most predominant emotion, followed by anticipation, fear, sadness, etc. The trust emotion reached its peak on November 9, 2020, when Pfizer announced that its vaccine is 90% effective. CONCLUSIONS Public COVID-19 vaccine–related discussion on Twitter was largely driven by major events about COVID-19 vaccines and mirrored the active news topics in mainstream media. The discussion also demonstrated a global perspective. The increasingly positive sentiment around COVID-19 vaccines and the dominant emotion of trust shown in the social media discussion may imply higher acceptance of COVID-19 vaccines compared with previous vaccines.


2019 ◽  
pp. 18-38 ◽  
Author(s):  
D. G. Grummo ◽  
R. V. Tsvirko ◽  
N. A. Zeliankevich ◽  
E. Y. Kulikova ◽  
O. V. Sozinov

In 2013–2018 studies of phytocoenotic diversity were carried out in the territory of the National Park “Belovezhskaya Pushcha” (Belarus). As a result, a classification scheme of vegetation was developed based on the floristic approach (Braun-Blanquet method) and a large-scale (1 : 100 000) geobotanical map was made. The map is compiled on the basis of the field data, analysis of remote sensing data, literary and cartographic sources, land and forest inventory materials. The compilation of this geobotanical map was consisted of 4 stages. 1) The pre-field (cameral) stage included: collection of archive data about the investigated territory, selection of space imagery, primary processing of digital images and data visualization, interpretation, automatic non-controlled classification, preliminary map compilation. 2) Field studies provided for surface interpretation of vegetation based on satellite imagery.In total, 1851 complete geobotanical relevés were made during field studies, including 743 forest, 452 mire, 576 meadow, segetal and ruderal plant communities. 3) The post-field (cameral) stage, including the preparation of the cartographic base; the systematization of field materials; the development of the final legend; the systematization of image standards for creating cartographic models; the controlled classification of images with preliminary segmentation by the method of superpixels (SNIC-Simple Non-Iterative Clustering); assessment reliability of classification results; geometric and geographical generalization; making an original map. 4) Field check (verification) of geobotanical map. During the 2018 field season a vegetation map of the protected area was checked with the compilation of the final reliability protocol. The main unit of the map legend, a syntaxon of the floristic classification of vegetation, is the association, however, along with the association, to display the typology of the vegetation cover, syntaxons of as a higher hierarchical rank (union) and lower (options, facies), as well as rankless communities are used. In establishing the names of associations and subassociations and in comparative analysis various regional works were taken into account (Matuszkiewicz, Matuszkiewicz, 1954; Czerwiński, 1978; Faliński, 1991, 1994а, b; Kwiatkowski, 1994; Bulokhov, Solomeshch, 2003; Semenischenkov, 2014; Lądowe ekosystemy…, 2016; Dubyna et al., 2019;). In the legend, the mapped units reflecting the restoration stages of the association are marked with letter indices. Heterogeneous areas consisting of regularly and repeatedly alternating plant communities are presented on the map as complexes (phytocoenoses-complex). In total, the map legend contains 75 mapped vegetation units, including forest — 40, shrub — 4, mire — 13, meadow and wasteland — 11, ruderal and segetal vegetation — 6, deforestation and disturbed forest habitats — 1. Separate units reflect other lands (water, residential development, etc.) The practical application of the geobotanical map for identifying key (important for biodiversity conservation) habitats and developing a science-based approach to the functional zoning of protected areas is shown.


Biologia ◽  
2015 ◽  
Vol 70 (6) ◽  
Author(s):  
Nasir Ahmad ◽  
Sumaira Mehboob ◽  
Naeem Rashid

AbstractStarch is a major storage product of several economically important crops and the most common carbohydrate in human diets. A variety of enzymes are capable of starch hydrolysis and a large-scale starch processing industry has emerged in the last century. Enzymatic production of dextrose/glucose, maltose and high fructose syrups is increasing day by day as we have seen a shift from the use of traditional cane sugar to these sweeteners all over the world. The best known starch-processing enzymes are α-amylase, β-amylase and glucoamylase. Among starch-processing enzymes, a group whose functions are comparatively less well understood, are 4-α-glucanotransferases. In this review, we report on the classification of starch-processing enzymes based on the amino acid sequence and structural similarity as well as substrate specificity and reaction mechanism with emphasis on 4-α-glucanotransferases. Furthermore, applications of thermostable starch-processing enzymes are discussed.


2014 ◽  
Vol 955-959 ◽  
pp. 1098-1102 ◽  
Author(s):  
Huan Yang ◽  
Rui Hong Yu ◽  
Rui Hong Guo ◽  
Yun Hao ◽  
Yu Jin Zhang

Eutrophication has led to severe water quality problems in aquatic ecosystems throughout the world. The assessment of trophic status for lakes may provide important and fundamental information for trophic state classification and eutrophication control. This paper assesses and analyzes the classification of eutrophication using three different methods in Wuliangsuhai Lake. The aim is to provide the reference for water quality improvement and aquatic environmental protection of the lake in arid area.


2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xun Gong ◽  
Fucheng Wang

With the rapid development of online video data, how to find the required information has become an urgent problem to be solved. This article focuses on sports videos and studies video classification and content-based retrieval techniques. Its purpose is to establish a mark and index of video content and to promote user acquisition through computer processing, analysis, and understanding of video content. Video tennis classification has high research and application value. This article focuses on video tennis based on the selection of the basic frame of each shot and proposes an algorithm for classification of shots based on average grouping. Based on this, we use a color-coded spatial detection method to detect the type of tennis match. Then, it integrates the results of audiovisual analysis to identify and classify exciting events in tennis matches. According to statistics, although the number of people participating in tennis cannot enter the top ten, the number of spectators ranks fourth. Four tennis tournaments, masters, and crown tournaments are held every year around the world. Watching large-scale international tennis matches has become a pillar of leisure and vacation for many people. Tennis matches last from two hours to four hours or more, and there are countless large and small tennis matches around the world every year, so the number of tennis records created is staggering. And artificial intelligence technology is rarely used in tennis in the sports world (5%), but football has reached 50%. Therefore, when dealing with such a large amount of data, we urgently need to find a fast and effective video retrieval classification method to find the required information. The experiment of tennis video classification research based on machine learning technology proves that the accuracy of tennis video classification reaches 98%, so this system has high feasibility.


Sign in / Sign up

Export Citation Format

Share Document