Results 51 to 60 of about 2,530 (205)

Polar‐low track prediction using machine‐learning methods

Quarterly Journal of the Royal Meteorological Society, EarlyView.
Machine‐learning models are developed to produce reliable and efficient forecasts of polar‐low (PL) trajectories 12 hours ahead. A temporal model (RLSTM) benefiting from the rolling‐forecast strategy, improves overall prediction accuracy and is suitable for quick experimentation, while a spatiotemporal model (PL‐UNet), incorporating both historical and
Ziying Yang, Rune Grand Graversen, Filippo Maria Bianchi, Jiping Liu, Ruibo Lei   +4 more
wiley   +1 more source

Transparency, Sustainable Governance and Digital Accessibility in Municipalities: A Machine Learning Approach

Sustainable Development, EarlyView.
ABSTRACT Achieving the Sustainable Development Goals (SDGs) requires transparent and accountable local governments, yet little is known about the structural drivers of municipal transparency. This study introduces a machine learning approach to predict municipal transparency using the Bidimensional Transparency Index (BTI), which measures both the ...
Ana M. Plata‐Díaz, Elisabeth Zafra‐Gómez, Juan C. Garrido‐Rodríguez, M. Carmen Pérez‐López   +3 more
wiley   +1 more source

Taming Discretised PDDL+ through Multiple Discretisations (Extended Abstract)

Proceedings of the International Symposium on Combinatorial Search
The PDDL+ formalism allows the use of planning techniques in applications that require the ability to perform hybrid discrete-continuous reasoning. PDDL+ problems are notoriously challenging to tackle, and to reason upon them a well-established approach is discretisation.
Cardellini M., Maratea M., Percassi F., Scala E., Vallati M.   +4 more
openaire   +2 more sources

Enhancing Generalisation via Cascaded Inertia SGD With Learnt Hyperparameters

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT A central challenge in deep learning lies in achieving strong model generalisation, an area in which conventional optimisers such as stochastic gradient descent (SGD) often exhibit limitations, even though they ensure convergence. This paper introduces cascaded inertia SGD (CISGD), a novel optimisation algorithm specifically designed to ...
Yongji Guan, Shunbao Zhang, Longbang Wang, Erchao Li   +3 more
wiley   +1 more source

Double‐Integration‐Enhanced Stochastic Gradient Descent Based on Neural Dynamics for Improving Generalisation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Generalisation is a crucial aspect of deep learning, enabling models to perform well on unseen data. Currently, most optimisers that improve generalisation typically suffer from efficiency bottlenecks. This paper proposes a double‐integration‐enhanced stochastic gradient descent (DIESGD) optimiser, which treats the negative gradient as an ...
Ting Li, Longbang Wang, Jiexing Li, Jicheng Li   +3 more
wiley   +1 more source

Convergent Interval Confirmation for Three‐Step Discrete Specific Zeroing Neural Dynamics Illustrated With Repetitive Motion Planning of Redundant Manipulators

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Repetitive motion planning (RMP) for redundant manipulators with high convergent precision becomes an intense research topic due to its more degrees of freedom. In this paper, a specific zeroing neural dynamics (SZND) model for the RMP is first set up via zeroing neurodynamics.
Ying Kong, Shaoyuan Sun, Yunliang Jiang, Lin Wei   +3 more
wiley   +1 more source

Large Eddy Simulation with Energy-Conserving Schemes and the Smagorinsky Model: A Note on Accuracy and Computational Efficiency

Energies, 2018
Despite advances in turbulence modelling, the Smagorinsky model remains a popular choice for large eddy simulation (LES) due to its simplicity and ease of use.
Dhruv Mehta, Ye Zhang, Alexander van Zuijlen, Hester Bijl   +3 more
doaj   +1 more source

An Efficient Method for Transient Temperature Calculation in Oil Natural Transformers Based on the Time‐Space Proper Orthogonal Decomposition

High Voltage, EarlyView.
ABSTRACT A reduced‐order model (ROM) for the temperature field based on time‐space proper orthogonal decomposition (POD) is presented to improve the computational efficiency of transient temperature rise in oil‐immersed power transformers with a complete oil natural convection cooling loop.
Haijuan Lan, Wenhu Tang, Zeyi Zhang, Jiahao Gong, Xiongwen Xu, Goran Strbac   +5 more
wiley   +1 more source

Computing Skinning Weights via Convex Duality

Computer Graphics Forum, EarlyView.
We present an alternate optimization method to compute bounded biharmonic skinning weights. Our method relies on a dual formulation, which can be optimized with a nonnegative linear least squares setup. Abstract We study the problem of optimising for skinning weights through the lens of convex duality.
J. Solomon, O. Stein
wiley   +1 more source

Discretisations, Constraints and Diffeomorphisms in Quantum Gravity [PDF]

Symmetry, Integrability and Geometry: Methods and Applications, 2012
Contribution for a special issue of SIGMA on Loop Quantum Gravity and ...
Bahr, B., Gambini, R., Pullin, J.
openaire   +5 more sources