Conference paper
Active Learning for Input Space Exploration in Traffic Simulators
Urban environments are systems of overwhelming complexity and dynamism, involving numerous variables and idiosyncrasies which not usually easy to model from a functional perspective. Simulation modeling is a common and well-accepted approach to study such systems, specially those that prove to be too complex to be analyzed by standard analytic methods.
However, such urban simulation models can become computationally very expensive to run. To address this drawback, simulation metamodels can be employed to approximate the underlying simulation function. In this paper, we propose a batch-mode active learning strategy based on Gaussian Processes metamodeling that searches for the most informative data points in batches with respect to their corresponding predictive variances.
These points are selected in such a way that they originate from different high variance neighborhoods. Eventually, this allows us to analyze the simulation output behavior with fewer simulation requests. Using an illustrative traffic simulation example, the results show that the proposed restricted batch-mode strategy is able to increase the simulation input space exploration efficiency in comparison with standard batch-mode strategies.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2018 |
Pages: | 1-8 |
Proceedings: | 2018 International Joint Conference on Neural Networks (IJCNN) |
ISBN: | 1509060146 , 1509060154 , 9781509060146 and 9781509060153 |
ISSN: | 21614407 and 21614393 |
Types: | Conference paper |
DOI: | 10.1109/IJCNN.2018.8489302 |
ORCIDs: | Pereira, Francisco Camara |
Analytical models Computational modeling Context modeling Data models Gaussian Processes metamodeling Gaussian processes Metamodeling Predictive models Training batch-mode active learning strategy digital simulation informative data points learning (artificial intelligence) predictive variances restricted batch-mode strategy simulation input space exploration efficiency simulation metamodels standard batch-mode strategies traffic engineering computing traffic simulation traffic simulators urban environments urban simulation models