toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Record Links
Author Koki Asami; Shono Fujita; Kei Hiroi; Michinori Hatayama pdf  isbn
openurl 
  Title Data Augmentation with Synthesized Damaged Roof Images Generated by GAN Type Conference Article
  Year 2022 Publication ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal Iscram 2022  
  Volume Issue Pages 256-265  
  Keywords disaster response; generative adversarial networks; data augmentation; damage classification  
  Abstract The lack of availability of large and diverse labeled datasets is one of the most critical issues in the use of machine learning in disaster prevention. Natural disasters are rare occurrences, which makes it difficult to collect sufficient disaster data for training machine learning models. The imbalance between disaster and non-disaster data affects the performance of machine learning algorithms. This study proposes a generative adversarial network (GAN)- based data augmentation, which generates realistic synthesized disaster data to expand the disaster dataset. The effect of the proposed augmentation was validated in the roof damage rate classification task, which improved the recall score by 11.4% on average for classes with small raw data and a high ratio of conventional augmentations such as rotation of image, and the overall recall score improved by 3.9%.  
  Address Kyoto University; Kyoto University; Kyoto University; Kyoto University  
  Corporate Author Thesis  
  Publisher Place of Publication (up) Tarbes, France Editor Rob Grace; Hossein Baharmand  
  Language English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2411-3387 ISBN 978-82-8427-099-9 Medium  
  Track AI and Intelligent Systems for Crises and Risks Expedition Conference  
  Notes Approved no  
  Call Number ISCRAM @ idladmin @ Serial 2415  
Share this record to Facebook
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: