EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Applying Monte Carlo Dropout to Quantify the Uncertainty of Skip Connection-Based Convolutional Neural Networks Optimized by Big Data

Abouzar Choubineh, Jie Chen, Frans Coenen, Fei Ma

Electronics · 19.03.2023 · 12 (6) · 1453

DOI: 10.3390/electronics12061453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 19.03.2023. Verfasst von Abouzar Choubineh und 3 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Program Special Fund in XJTLU, XJTLU Postgraduate Research Scholarship, XJTLU Research Development Funding.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although Deep Learning (DL) models have been introduced in various fields as effective prediction tools, they often do not care about uncertainty. This can be a barrier to their adoption in real-world applications. The current paper aims to apply and evaluate Monte Carlo (MC) dropout, a computationally efficient approach, to investigate the reliability of several skip connection-based Convolutional Neural Network (CNN) models while keeping their high accuracy. To do so, a high-dimensional regression problem is considered in the context of subterranean fluid flow modeling using 376,250 generated samples. The results demonstrate the effectiveness of MC dropout in terms of reliability with a Standard Deviation (SD) of 0.012–0.174, and of accuracy with a coefficient of determination (R2) of 0.7881–0.9584 and Mean Squared Error (MSE) of 0.0113–0.0508, respectively. The findings of this study may contribute to the distribution of pressure in the development of oil/gas fields.

Förderung

  • Key Program Special Fund in XJTLU
  • XJTLU Postgraduate Research Scholarship
  • XJTLU Research Development Funding

Zitieren

APA

Choubineh, A., Chen, J., Coenen, F., & Ma, F. (2023). Applying Monte Carlo Dropout to Quantify the Uncertainty of Skip Connection-Based Convolutional Neural Networks Optimized by Big Data. Electronics, 12(6), 1453. https://doi.org/10.3390/electronics12061453

Vancouver

Choubineh A, Chen J, Coenen F, Ma F. Applying Monte Carlo Dropout to Quantify the Uncertainty of Skip Connection-Based Convolutional Neural Networks Optimized by Big Data. Electronics. 2023;12(6):1453. doi:10.3390/electronics12061453

BibTeX
@article{Choubineh2023,
  author = {Choubineh, Abouzar and Chen, Jie and Coenen, Frans and Ma, Fei},
  title = {Applying Monte Carlo Dropout to Quantify the Uncertainty of Skip Connection-Based Convolutional Neural Networks Optimized by Big Data},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {6},
  pages = {1453},
  doi = {10.3390/electronics12061453}
}
Kostenlos starten →