Using principal component analysis and elastic net in logistic regression to identify the location of objects in EIT
Ładowanie...
Data
2022
Inny tytuł
Typ
Artykuł recenzyjny (pokonferencyjny)
Redaktor
dc.contributor.advisor
Dyscyplina PBN
Informatyka techniczna i telekomunikacja
Czasopismo lub seria
Journal of Physics: Conference Series
ISSN
1742-6588
ISBN
DOI
10.1088/1742-6596/2408/1/012025
Strona internetowa
Wydawca
Wydawca
Wydanie
Numer
Strony od-do
Tytuł monografii
item.page.defence
Tytuł tomu
Opis
Rodzaj licencji
Abstrakt (en)
This paper presents the research results on the use of machine learning algorithms and electrical tomography to detect moisture in the tank. The article presents methods such as principal component analysis and elastic net in logistic regression, for identifying object locations. Tomographic methods show a spatial image of the interior, not individual points of the examined cross-section. Previous studies have shown that the choice of machine learning model has a significant impact on the quality of the results obtained. Machine learning is more likely to provide accurate tomogram reconstructions than traditional mathematical methods. In this study, linear regression models performed slightly worse than neural networks. A specially developed numerical model was used in this study. The characteristic feature of the analyzed solution is the partition of the modeled object into a set of elements using a specially developed mesh.