首页    期刊浏览 2024年11月28日 星期四
登录注册

文章基本信息

  • 标题:Reflectivity Parameter Extraction From RADAR Images Using Back Propagation Algorithms
  • 本地全文:下载
  • 作者:P. Anil Kumar ; B. Anuradha
  • 期刊名称:International Journal of Electrical and Computer Engineering
  • 电子版ISSN:2088-8708
  • 出版年度:2018
  • 卷号:8
  • 期号:5
  • 页码:2795-2803
  • DOI:10.11591/ijece.v8i5.pp2795-2803
  • 语种:English
  • 出版社:Institute of Advanced Engineering and Science (IAES)
  • 摘要:Pattern recognition has been acknowledged as one of the promising research areas and it has drawn the awareness among many researchers since its existence at the beginning of the nineties. Multilayer Neural networks are used in pattern Recognition and classification based on the features derived from the input patterns. The Reflectivity information extracted from the Doppler Weather Radar (DWR) image helps in identifying the convective cloud type which has a strong relation to the precipitation rate. The reflectivity information is rooted in the DWR image with the help of colors and color bar is provided to distinguish among different reflectivity information. Artificial Neural network predicts the color based on the maximum likelihood estimation problem. This paper presents a best possible backpropagation algorithm for color identification in DWR images by comparing various backpropagation algorithms such as Levenberg-Marquardt, Conjugate gradient, and Resilient back propagation etc.,. Pattern recognition using Neural networks presents better results compared to standard distance measures. It is observed that Levenberg-Marquardt backpropagation algorithm yields a regression value of 99% approximately and accuracy of 98%.
  • 其他摘要:Pattern recognition has been acknowledged as one of the promising research areas and it has drawn the awareness among many researchers since its existence at the beginning of the nineties. Multilayer Neural networks are used in pattern Recognition and classification based on the features derived from the input patterns. The Reflectivity information extracted from the Doppler Weather Radar (DWR) image helps in identifying the convective cloud type which has a strong relation to the precipitation rate. The reflectivity information is rooted in the DWR image with the help of colors and color bar is provided to distinguish among different reflectivity information. Artificial Neural network predicts the color based on the maximum likelihood estimation problem. This paper presents a best possible backpropagation algorithm for color identification in DWR images by comparing various backpropagation algorithms such as Levenberg-Marquardt, Conjugate gradient, and Resilient back propagation etc.,. Pattern recognition using Neural networks presents better results compared to standard distance measures. It is observed that Levenberg-Marquardt backpropagation algorithm yields a regression value of 99% approximately and accuracy of 98%.
  • 关键词:Image processing;Neural Networks;Doppler Weather Radar
国家哲学社会科学文献中心版权所有