Bayesian active learning with fully Bayesian Gaussian processes
The bias-variance trade-off is a well-known problem in machine learning that only gets more
pronounced the less available data there is. In active learning, where labeled data is scarce …
pronounced the less available data there is. In active learning, where labeled data is scarce …
[HTML][HTML] Explainable active learning metamodeling for simulations: Method and experiments for ATM performance assessment
The use of Air traffic management (ATM) simulators for planing and operations can be
challenging due to their modelling complexity. This paper presents XALM (eXplainable …
challenging due to their modelling complexity. This paper presents XALM (eXplainable …
Explainable Metamodels for ATM Performance Assessment
Fast-time simulation constitutes a well-known and long-established technique within the Air
Traffic Management (ATM) community. However, it is often the case that simulation input and …
Traffic Management (ATM) community. However, it is often the case that simulation input and …
Active Learning Metamodelling for R-NEST
The computational cost of realistic air traffic simulations is a barrier for a comprehensive
assessment of new ATM concepts and solutions, which, in practice, restricts the simulations …
assessment of new ATM concepts and solutions, which, in practice, restricts the simulations …
Mixture of Gaussian Processes for Bayesian Active Learning
This paper introduces a Mixture of Gaussian processes (MGP) model and explores its
application in the context of Bayesian active learning. The MGP offers an alternative …
application in the context of Bayesian active learning. The MGP offers an alternative …
Dispatcher3–Machine learning for efficient flight planning: approach and challenges for data-driven prototypes in air transport
L Delgado Muñoz, S Mas Pujol… - TSAS 2022: 4th …, 2022 - upcommons.upc.edu
Machine learning techniques to support decisionmaking processes are in trend. These are
particularly relevant in the context of flight management where large datasets of planned …
particularly relevant in the context of flight management where large datasets of planned …
NOSTROMO-D1. 2-Final Project Results Report
G Gurtner, F Camara Pereira, M Cano… - 2022 - westminsterresearch.westminster.ac …
The main objective of the NOSTROMO project has been to develop, demonstrate and
evaluate an innovative modelling approach for the rigorous and comprehensive assessment …
evaluate an innovative modelling approach for the rigorous and comprehensive assessment …
[PDF][PDF] Project Title
DTU Leader, LTL DTU, C Lima - 2023 - emotionalcities-h2020.eu
This document is the deliverable “D7. 2: Metamodeling Library” that belongs to the “WP7:
Scenario Discovery” of the European project “eMOTIONAL Cities: Mapping the cities through …
Scenario Discovery” of the European project “eMOTIONAL Cities: Mapping the cities through …