scholarly journals Using Modern Machine Learning Methods on KASCADE Data for Outreach and Education

2021 ◽  
Author(s):  
Victoria Tokareva ◽  
Dmitriy Kostunin ◽  
Ivan Plokhikh ◽  
Vladimir Sotnikov
Keyword(s):  
Machine Learning ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Modern Machine ◽  
Outreach And Education

Modern Machine Learning Methods for Telemetry-Based Spacecraft Health Monitoring

2021 ◽  
Vol 82 (8) ◽  
pp. 1293-1320
Author(s):  
P. A. Mukhachev ◽  
T. R. Sadretdinov ◽  
D. A. Pritykin ◽  
A. B. Ivanov ◽  
S. V. Solov’ev
Keyword(s):  
Machine Learning ◽  
Health Monitoring ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Modern Machine

Predicting advanced fibrosis using non-invasive clinical tests and modern machine learning methods in TARGET-NASH

2020 ◽  
Vol 73 ◽  
pp. S431-S432
Author(s):  
Peter Mesenbrink ◽  
A. Sidney Barritt ◽  
Rohit Loomba ◽  
Philip N Newsome ◽  
Arun Sanyal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Advanced Fibrosis ◽  
Clinical Tests ◽  
Learning Methods ◽  
Non Invasive ◽  
Machine Learning Methods ◽  
Modern Machine

scholarly journals The Missing 15 Percent of Patent Citations

2020 ◽  
Author(s):  
Cyril Verluise ◽  
Gabriele Cristelli ◽  
Kyle Higham ◽  
Gaetan de Rassenfosse
Keyword(s):  
Machine Learning ◽  
Full Text ◽  
Front Page ◽  
Patent Citations ◽  
Text Similarity ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Widespread Availability ◽  
Patent Documents ◽  
Modern Machine

Patent citations are one of the most commonly-used metrics in the innovation literature. Leading uses of patent-to-patent citations are associated with the quantification of inventions' quality and the measurement of knowledgeflows. Due to their widespread availability, scholars have exploited citations listed on the front-page of patent documents. Citations appearing in the full-text of patent documents have been neglected. We apply modern machine learning methods to extract these citations from the text of USPTO patent documents. Overall, we are able to recover an additional 15 percent of patent citations that could not be found using only front-page data. We show that "in-text" citations bring a different type of information compared to front-page citations. They exhibit higher text-similarity to the citing patents and alter the ranking of patent importance. The dataset is available at patcit.io (CC-BY-4).

scholarly journals Some Observations for Portfolio Management Applications of Modern Machine Learning Methods

2016 ◽  
Vol 16 (1) ◽  
pp. 44-51 ◽  
Author(s):  
Jooyoung Park ◽  
Seongman Heo ◽  
Taehwan Kim ◽  
Jeongho Park ◽  
Jaein Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Portfolio Management ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Modern Machine

DETECTION OF PULSARS AMONG NEUTRON STARS AND ELECTROMAGNETIC RADIATION SOURCES USING MACHINE LEARNING METHODS

2021 ◽  
pp. 55-63
Author(s):  
R. A. Eshenko ◽  
M. C. Petrova ◽  
V. V. Shvets
Keyword(s):  
Machine Learning ◽  
Neutron Stars ◽  
Electromagnetic Radiation ◽  
Image Recognition ◽  
Recognition Algorithm ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Radiation Sources ◽  
Modern Machine

This article describes a way to simplify the process of confirming hypotheses about whether the source of electromagnetic radiation is a pulsar by using modern machine learning methods. In the course of the work, data from more than 17,000 radiation sources were analyzed and an image recognition algorithm that detects pulsars with an accuracy of up to 98 % was used

Sign in / Sign up

Export Citation Format

Share Document