|
|||||
|
|
| 基于改进BP神经网络的海底底质分类 | |
| 引用本文： | 唐秋华,刘保华,陈永奇,周兴华.基于改进BP神经网络的海底底质分类[J].海洋测绘,2009,29(5):40-43. |
| 作者姓名： | 唐秋华 刘保华 陈永奇 周兴华 |
| 作者单位： | 1. 中国海洋大学,海洋地球科学学院,山东,青岛266100;国家海洋局,第一海洋研究所,山东,青岛266061;香港理工大学,土地测量与地理资讯学系,香港 2. 国家海洋局,第一海洋研究所,山东,青岛266061 3. 香港理工大学,土地测量与地理资讯学系,香港 |
| 基金项目： | 863计划资助课题，国家自然科学基金，香港RGC项目 |
| 摘 要： | 通过采用遗传算法优化神经网络初始权值的方法,将GA算法与BP神经网络有机结合,应用于海底底质分类。基于多波束测深系统获取的反向散射强度数据,应用改进的BP神经网络分类方法,实现对海底基岩、砾石、砂、细砂和泥等底质类型的快速、准确识别。通过实验比较,GA-BP神经网络分类精度明显高于BP神经网络,证明了该方法的有效性和可靠性。 |
| 关 键 词： | 底质分类 BP神经网络 遗传算法 多波束测深系统 反向散射强度 |
Seabed Classification with Improved BP Neural Network |
|
| TANG Qiu-hu,LIU Bao-hu,CHEN Yong-qi,ZHOU Xing-hua.Seabed Classification with Improved BP Neural Network[J].Hydrographic Surveying and Charting,2009,29(5):40-43. | |
| Authors: | TANG Qiu-hu LIU Bao-hu CHEN Yong-qi ZHOU Xing-hua |
| Institution: | , LIN Xu-bo ( 1. College of Marine Geosciences, Ocean University of China, Qingdao, Shandong, 266100 ; 2. First Institute of Oceanography, State Oceanic Administration, Qingdao, Shandong ,266061 ; 3. The Hong Kong Polytechnic University, Hong Kong) |
| Abstract: | Genetic algorithm （GA） is used to optimize the initial values of BP neural network, and GA-BP neural network is applied in the seabed classification. Using the backscatter data from multibeam echo sounder, the improved BP neural network is used to identify all kinds of seabed sediment types, such as rock, gravel, sand, fine sand and mud on the study area. Comparing the classification precisions between GA-BP and BP, the experiment results indicate that the GA-BP neural network approach is effective and reliable in the acoustic seabed classification. |
| Keywords: | seabed classification BP neural network GA multibeam sounding system backscatter strength |
| 本文献已被 维普 万方数据 等数据库收录！ | |
| 点击此处可从《海洋测绘》浏览原始摘要信息 | |
| 点击此处可从《海洋测绘》下载免费的PDF全文 | |