deep learning; distribution shifts; marine vessels; neuro-symbolic; power prediction; uncertainty; Cargo vessels; Deep learning; Distribution shift; Marine vessels; Neural-networks; Neuro-symbolic; Physics-based formula; Power; Power predictions; Uncertainty; Computer Networks and Communications; Information Systems; Information Systems and Management; Energy Engineering and Power Technology; Renewable Energy, Sustainability and the Environment; Electrical and Electronic Engineering
Abstract :
[en] This paper proposes a neuro-symbolic approach to predict the power of marine cargo vessels. The neuro-symbolic approach combines two parts. The first is a neural networks part, and the second is a symbolic part that relies on physics-based formulae. The Shifts-power dataset was used for evaluation. The experimental results showed that a combination of a physics-based module (symbolic part) with a neural networks model (namely ensemble Monte Carlo dropout) superseded the state-of-the-art results by 2.3% in terms of uncertainty estimation measured using R-AUC, and by 3.4% in terms of power prediction for out-of-distribution (OOD) examples measured using RMSE. It also superseded the symbolic approach by 6.3% in terms of uncertainty and 17.7% in terms of OOD power prediction.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Hammoudeh, Ahmad Tayseer Ahmad ; Université de Mons - UMONS > Faculté Polytechniqu > Service Information, Signal et Intelligence artificielle
A. Christodoulou and J. Woxenius, "Sustainable short sea shipping, " Sustainability, vol. 11, no. 10, p. 2847, 2019.
M. S. Eide, T. Longva, P. Hoffmann, O. Endresen, and S. B. Dalsoren, "Future cost scenarios for reduction of ship CO2 Emissions, " Maritime Policy & Management, vol. 38, no. 1, pp. 11-37, 2011.
International Maritime Organization, "Fourth IMO greenhouse gas study, " 2020. [Online]. Available: https://wwwcdn. imo. org/localresources/en/OurWork/Environment/Do cuments/Fourth%20IMO%20GHG%20Study%202020%20-%20Full%20report%20and%20annexes. pdf. [Accessed: 12-Jan-2023].
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning, " Nature, vol. 521, no. 7553, pp. 436-444, 2015.
A. Goyal and Y. Bengio, "Inductive biases for deep learning of higherlevel cognition, " Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 478, no. 2266, 2022.
G. Marcus, Rebooting ai: Building artificial intelligence we can trust. New York: Vintage Books, 2020.
C. Deng, X. Ji, C. Rainey, J. Zhang, and W. Lu, "Integrating machine learning with human knowledge, " iScience, vol. 23, no. 11, p. 101656, 2020.
E. Oyallon and S. Mallat, "Deep roto-translation scattering for Object Classification, " 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
M. Bronstein, J. Bruna, T. Cohen, and P. Velickovic, Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges. 2021.
A. Hammoudeh and S. Dupont, "How does explicit orientation encoding affect image classification of ConvNets?, " in IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop: NeuroVision, 2022.
T. Cohen, Equivariant convolutional networks, Ph. D dissertation, University of Amsterdam, 2021.
L. T. George Davis, "Chapter 7, Resistance and Powering of Ships, " in Principles of Ship Performance, USA: United States Naval Academy, 2014.
Y. Gal and Z. Ghahramani, "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning", Proc. Int. Conf. Mach. Learn., pp. 1050-1059, 2016.
A. Malinin, N. Band, G. Chesnokov, Y. Gal, M. J. Gales, A. Noskov, et al., "Shifts: A dataset of real distributional shift across multiple largescale tasks", arXiv preprint, 2021.
A. Malinin., A. Athanasopoulos, M. Barakovic, M. Cuadra, M. Gales, C. Granziera, et. al., " Shifts 2. 0: Extending the dataset of real distributional shifts ", arXiv: 2206. 15407, 2022.
A. Malinin, Uncertainty estimation in deep learning with application to spoken language assessment, Ph. D dissertation, University of Cambridge, 2019.
