HHFNN Based on Lasso Function and Its Application in Remote Sensing Image Classification

详细信息   

• 责任者：Yu Xianchuan (College of Information Science and Technology ; Beijing Normal University ; Beijing 100875 ; China) ; Dai Sha
• 刊名：Chinese Journal of Geophysics
• 出版年：2011
• 卷期：54(6)
• 关键词：遥感 ; remote sensing
• 页码：p.1672-1678
• 图表：5 illus., 2 tables, 17 refs.
• 分类号：1600
• 出版序号：1260
• issnNo：ISSN0001-5733
• isbnNo：CN11-2074/P

摘要

In this paper, a algorithm for hierarchical hybrid fuzzy-neural network model is proposed. Takagi-Sugeno model and triangular membership function are adopted in fuzzy system, and lasso function of coefficient contraction method is used to reduce the strong interaction among discrete input variables. In the end, an experimental test on surface features classification by using LANDSAT ETM⁺ remote sensing image data of Zhangping Luoyang-Anxi Pantian in Fujian Province is conducted. Compared with other neural networks, the classification with the proposed approach is the most accurate, which proves its feasibility and validity, and can be used as a surface features classification method on remote sensing image.