classification analysis
Recently Published Documents


TOTAL DOCUMENTS

496
(FIVE YEARS 151)

H-INDEX

32
(FIVE YEARS 4)

2022 ◽  
Vol 132 ◽  
pp. 01005
Author(s):  
Jiří Kučera ◽  
Yaroslava Kostiuk ◽  
Daniel Kortiš

The aim of this paper is to determine the possible cause of lagging Czech companies in the field of HR transformation. The basic source of data is data from the Czech Statistical Office. The paper uses the method of classification analysis of graduates in the field of information and communication technologies. The paper is divided into two parts, where the first part deals with the evaluation of tabular data and the second with the testing of the established hypothesis (H0). The number of graduates in the field of information and communication technologies in the Czech Republic has been steadily declining since 2015, although the results achieved so far do not indicate a significant change, which could be the main cause of Czech companies lagging behind in HR transformation. The low involvement of graduates in this field is also caused by older and backward employees in companies, who do not like to change established systems.


2021 ◽  
Vol 11 (2) ◽  
pp. 107-111
Author(s):  
EVA KALINOVÁ ◽  
ADÉLA NEUBERGOVÁ

The topic of influencers has been a widely used word in recent years. It is a person who, through social media networks, influences the target groups of their followers. The aim of this paper is to analyze the communication of selected influencers on the social platform Instagram. Using classification analysis, data on individual influencers are presented. For the sake of interesting results and the proof that the success of an influencer does not only depend on how many followers they have on their profile, the influencers were selected with the help of respondents who assessed them independently. The data were obtained on the social platform Instagram and subsequently processed on the basis of the last five contributions as of April 3, 2020. This work is focused mainly on the number of responses to influencers in the form of likes or comments, furthermore we also calculate what share of their contributions is from 2020, mainly due to the fact that influencers on Instagram started to become known mostly in that year. The statistics of individual Instagram profiles and their subsequent comparison with each other are presented. The results show that it does not entirely depend on how many followers an influencer has, but that it depends more on the quality and impact of individual posts.


2021 ◽  
Vol 7 (12) ◽  
pp. 115645-115666
Author(s):  
Tarcizio da Silva Barbosa ◽  
Léony Luis Lopes Negrão ◽  
Mariana Pereira Carneiro Barata ◽  
Verônica de Menezes Nascimento Nagata

Onco ◽  
2021 ◽  
Vol 1 (2) ◽  
pp. 219-229
Author(s):  
Fleur Jeanquartier ◽  
Claire Jean-Quartier ◽  
Sarah Stryeck ◽  
Andreas Holzinger

Supporting data sharing is paramount to making progress in cancer research. This includes the search for more precise targeted therapies and the search for novel biomarkers, through cluster and classification analysis, and extends to learning details in signal transduction pathways or intra- and intercellular interactions in cancer, through network analysis and network simulation. Our work aims to support and promote the use of publicly available resources in cancer research and demonstrates artificial intelligence (AI) methods to find answers to detailed questions. For example, how targeted therapies can be developed based on precision medicine or how to investigate cell-level phenomena with the help of bioinformatical methods. In our paper, we illustrate the current state of the art with examples from glioma research, in particular, how open data can be used for cancer research in general, and point out several resources and tools that are readily available. Presently, cancer researchers are often not aware of these important resources.


2021 ◽  
Vol 936 (1) ◽  
pp. 012032
Author(s):  
Widya Utama ◽  
Rista Fitri Indriani

Abstract This study aims to determine the effect of physiography based on slope and land cover for water control in Kali Lamong watershed. The data used in this research are DEM data and Landsat 8 imagery data. The process of processing slope data is through conversion coordinates system, DEM clip, create slope, reclassify, dissolve shapefile, and slope classification analysis. Landsat 8 data processing goes through a process through conversion coordinates system, composite band, crop composite, extent shapefile, sharpen band, unsupervised classification, and land cover classification analysis. Slope classification maps and land cover classification maps are used for flow coefficient classification for physiographic analysis based on slope and land cover for water control in Kali Lamong watershed. On the land cover classification map, five land classifications were obtained, namely agriculture (158413000 m2), settlements (72701400 m2), industrial land (11571600 m2), plantations (46017800 m2), and waters (15268500 m2). On the slope classification map obtained 5 classifications, as flat with a slope of 0-8% (288469544 m2), as slope with a slope of 8-15% (7656738 m2), as rather steep with a slope of 15-25% (1905360 m2), as steep with a slope of 25-45 (526614 m2), and as very steep with a slope of more than 45% (32148 m2). From the combination of Landsat 8 image data and slope data, flow coefficient analysis was carried out. The flow coefficient is influenced by land cover and slope. From this research, the classification of low flow coefficient is less than 0.25, medium flow coefficient is 0.25-0.5, and high flow coefficient is more than 0.75. The average flow coefficient of Kali Lamong watershed is 0.49 with a moderate flow coefficient classification value. This shows that 49% of the runoff water is in Kali Lamong watershed. The higher the flow coefficient value, the water runs off the surface. So that it can be used as an initial study for the technical planning of Kali Lamong hydrology and the development, improvement, utilization, and control of water flow in Kali Lamong.


Author(s):  
В’ячеслав Васильович Москаленко ◽  
Микола Олександрович Зарецький ◽  
Альона Сергіївна Москаленко ◽  
Артем Геннадійович Коробов ◽  
Ярослав Юрійович Ковальський

A machine learningsemi-supervised method was developed for the classification analysis of defects on the surface of the sewer pipe based on CCTV video inspection images. The aim of the research is the process of defect detection on the surface of sewage pipes. The subject of the research is a machine learning method for the classification analysis of sewage pipe defects on video inspection images under conditions of a limited and unbalanced set of labeled training data. A five-stage algorithm for classifier training is proposed. In the first stage, contrast training occurs using the instance-prototype contrast loss function, where the normalized Euclidean distance is used to measure the similarity of the encoded samples. The second step considers two variants of regularized loss functions – a triplet NCA function and a contrast-center loss function. The regularizing component in the second stage of training is used to penalize the rounding error of the output feature vector to a discrete form and ensures that the principle of information bottlenecking is implemented. The next step is to calculate the binary code of each class to implement error-correcting codes, but considering the structure of the classes and the relationships between their features. The resulting prototype vector of each class is used as a label of image for training using the cross-entropy loss function.  The last stage of training conducts an optimization of the parameters of the decision rules using the information criterion to consider the variance of the class distribution in Hamming binary space. A micro-averaged metric F1, which is calculated on test data, is used to compare learning outcomes at different stages and within different approaches. The results obtained on the Sewer-ML open dataset confirm the suitability of the training method for practical use, with an F1 metric value of 0.977. The proposed method provides a 9 % increase in the value of the micro-averaged F1 metric compared to the results obtained using the traditional method.


2021 ◽  
Author(s):  
Raja Muhammad Hafiz Raja Khairul Annuar ◽  
Shahrani Shahbudin ◽  
Murizah Kassim ◽  
Farah Yasmin Abdul Rahman

Sign in / Sign up

Export Citation Format

Share Document