Back to Search
Start Over
An Active Learning Framework for Constructing High-Fidelity Mobility Maps.
- Source :
-
IEEE Transactions on Vehicular Technology . Oct2021, Vol. 70 Issue 10, p9803-9813. 11p. - Publication Year :
- 2021
-
Abstract
- Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ACTIVE learning
*MACHINE learning
*STATISTICAL sampling
*TRAINING needs
*ALGORITHMS
Subjects
Details
- Language :
- English
- ISSN :
- 00189545
- Volume :
- 70
- Issue :
- 10
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Vehicular Technology
- Publication Type :
- Academic Journal
- Accession number :
- 153712157
- Full Text :
- https://doi.org/10.1109/TVT.2021.3107338