| The Monitoring of Red Tides Based on Modular Neural Networks Using Airborne Hyperspectral Remote Sensing |
| |
| 作者姓名： | JI Guangrong SUN Jie ZHAO Wencang ZHANG Hande |
| |
| 作者单位： | [1]School of Information Science and Engineering, Ocean University of China, Qingdao 266003, P. R. China [2]North Sea Branch, State Oceanic Administration, Qingdao 266033, P.R. China |
| |
| 基金项目： | 高比容电子铝箔的研究开发与应用项目 |
| |
| 摘 要： | This paper proposes a red tide monitoring method based on clustering and modular neural networks. To obtain the features of red tide from a mass of aerial remote sensing hyperspectral data, first the Log Residual Correction （LRC） is used to normalize the data, and then clustering analysis is adopted to select and form the training samples for the neural networks. For rapid monitoring, the discriminator is composed of modular neural networks, whose structure and learning parameters are determined by an Adaptive Genetic Algorithm （AGA）. The experiments showed that this method can monitor red tide rapidly and effectively.
|
| 关 键 词： | 遥感技术 光谱数据 空气传播 人工神经网络 赤潮 海洋污染 |
| 收稿时间： | 2004-12-10 |
| 修稿时间： | 2006-01-04 |
The monitoring of red tides based on modular neural networks using airborne hyperspectral remote sensing |
| |
| JI Guangrong SUN Jie ZHAO Wencang ZHANG Hande.The Monitoring of Red Tides Based on Modular Neural Networks Using Airborne Hyperspectral Remote Sensing[J].Journal of Ocean University of China,2006,5(2):169-173. |
| |
| Authors: | Ji Guangrong Sun Jie Zhao Wencang Zhang Hande |
| |
| Institution: | 1. School of Information Science and Engineering, Ocean University of China, Qingdao 266003, P. R. China
2. North Sea Branch, State Oceanic Administration, Qingdao 266033, P.R. China |
| |
| Abstract: | This paper proposes a red tide monitoring method based on clustering and modular neural networks. To obtain the features of red tide from a mass of aerial remote sensing hyperspectral data, first the Log Residual Correction (LRC) is used to normalize the data, and then clustering analysis is adopted to select and form the training samples for the neural networks. For rapid monitoring, the discriminator is composed of modular neural networks, whose structure and learning parameters are determined by an Adaptive Genetic Algorithm (AGA). The experiments showed that this method can monitor red tide rapidly and effectively. |
| |
| Keywords: | aeronautic remote sensing hyper-spectral data red tide monitoring artificial neural networks |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
