prikaz prve stranice dokumenta Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms
  Preuzmi
PDF 1.74 MB
Znanstveni rad - Izvorni znanstveni rad
Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms
Pomorstvo, 35 (2021), 2; 275-284. https://doi.org/10.31217/p.35.2.11
Baressi Šegota, Sandi; Lorencin, Ivan; Šercer, Mario; Car, Zlatan

Citirajte ovaj rad

Baressi Šegota, S., Lorencin, I., Šercer, M. i Car, Z. (2021). Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms. Pomorstvo, 35. (2), 275-284. doi: 10.31217/p.35.2.11

Baressi Šegota, Sandi, et al. "Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms." Pomorstvo, vol. 35, br. 2, 2021, str. 275-284. https://doi.org/10.31217/p.35.2.11

Baressi Šegota, Sandi, Ivan Lorencin, Mario Šercer i Zlatan Car. "Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms." Pomorstvo 35, br. 2 (2021): 275-284. https://doi.org/10.31217/p.35.2.11

Baressi Šegota, S., et al. (2021) 'Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms', Pomorstvo, 35(2), str. 275-284. doi: 10.31217/p.35.2.11

Baressi Šegota S, Lorencin I, Šercer M, Car Z. Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms. Pomorstvo [Internet]. 12.2021. [pristupljeno 29.04.2024.];35(2):275-284. doi: 10.31217/p.35.2.11

S. Baressi Šegota, I. Lorencin, M. Šercer i Z. Car, "Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms", Pomorstvo, vol. 35, br. 2, str. 275-284, Prosinac 2021. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:187:446153. [Citirano: 29.04.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:187:446153
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms
AutorSandi Baressi Šegota https://orcid.org/0000-0002-3015-1024
AutorIvan Lorencin
AutorMario Šercer https://orcid.org/0000-0002-4101-4092
AutorZlatan Car https://orcid.org/0000-0003-2817-9252
Autorova ustanovaSveučilište u Rijeci
Pomorski fakultet
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Tehnologija prometa i transport
Sažetak (engleski)
Determining the residuary resistance per unit weight of displacement is one of the key factors in the design of vessels. In this paper, the authors utilize two novel methods – Symbolic Regression (SR) and Gradient Boosted Trees (GBT) to achieve a model which can be used to calculate the value of residuary resistance per unit weight, of displacement from the longitudinal position of the center of buoyancy, prismatic coefficient, length-displacement ratio, beam-draught ratio, length-beam ratio, and Froude number. This data is given as results of 308 experiments provided as a part of a publicly available dataset. The results are evaluated using the coefficient of determination (R2) and Mean Absolute Percentage Error (MAPE). Pre-processing, in the shape of correlation analysis combined with variable elimination and variable scaling, is applied to the dataset. The results show that while both methods achieve regression results, the result of regression of SR is relatively poor in comparison to GBT. Both methods provide slightly poorer, but comparable results to previous research focussing on the use of “black-box” methods, such as neural networks. The elimination of variables does not show a high influence on the modeling performance in the presented case, while variable scaling does achieve better results compared to the models trained with the non-scaled dataset.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaPomorstvo
Brojčani podacivol. 35, br. 2, str. 275-284
p-ISSN1332-0718
e-ISSN1846-8438
DOIhttps://doi.org/10.31217/p.35.2.11
URN:NBNurn:nbn:hr:187:446153
Datum objave publikacije2021-12
URL dokumentahttps://hrcak.srce.hr/267183
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Zaštićeno autorskim pravom.
Datum i vrijeme pohrane2022-02-25 14:14:26