DOE OSTI · 3024379
Explosion Detection using Transfer Learning via YAMNet [Poster]
Abstract
The acoustic data of explosions and noise collected on smartphones were fed to the YAMNet model to obtain the scores of each class. The data was split 60/20/20 for training, validation, and testing. A single-layered neural network was trained using the computed scores to predict if the data was an explosion or noise. The trained model was then combined with the YAMNet model. The combined model was tested with the ESC-50 dataset to investigate overall accuracy and class based false positive rates.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Takazawa, Samuel Kei, Garces, Milton, Ocampo Giraldo, Luis A., Hix, Jay D., Chichester, David L., Zeiler, Cleat. 2022-05-20. Explosion Detection using Transfer Learning via YAMNet [Poster]. https://doi.org/10.2172/3024379. https://searchnasa.com/record/osti%3A3024379/explosion-detection-using-transfer-learning-via-yamnet-poster
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.