頁籤選單縮合
題 名 | Fuzzy Neural Network for Satellite Data Processing-SAR Image Classification=模糊神經網路應用於衛星資料之處理--以合成口徑雷達影像的分類為例 |
---|---|
作 者 | 曾裕強; 陳錕山; | 書刊名 | Proceedings of the National Science Council : Part A, Physical Science and Engineering |
卷 期 | 22:2 1998.03[民87.03] |
頁 次 | 頁243-250 |
分類號 | 448.6 |
關鍵詞 | 模糊神經網路; 動態學習神經網路; Degree of membership; Fuzzy logic; SAR; |
語 文 | 英文(English) |
中文摘要 | 傳統的類神經網路分類器在進行訓練時,係以單一像元單一類別來表示其資訊 。因此,對於類別的混合及像元的隸屬度並未加以考慮,致使其分類準確度降低。本 論文即以動態學習神經網路為基本架構並考慮網路模糊邏輯的表示及隸屬度的設定, 而發展出模糊動態學習神經網路。為展示模糊神經網路的有效性及有用性,我們將動 態學習神經網路及模糊動態學習神經網路應用於合成口徑雷達影像的分類來比較這兩 種類神經網路。實驗結果顯示模糊動態學習神經網路比動態學習神經網路有較好的收 斂恃性,且可改善相似類別間的區別率。 |
英文摘要 | The conventional neural network classifier proceeds the learning process from the representative information within a problem domain on a one- pixel-one-class basis. Therefore, class mixture and the degree of membership of a pixel are generally not taken into account, resulting in poor classification accuracy to some extent. Based on the framework of a dynamic learning neural network (DL), this paper proposes a fuzzy version ( FDL) based on two steps: network representation of fuzzy logic and assignment of membership. Demonstration of its effectiveness and usefulness is provided using SAR image classification. Finally, comparison between DL and FDL are made by applying both neural networks to SAR image classification. Experimental results show that FDL has a faster convergence rate than does DL. In addition, separability between similar classes is improved. |
本系統中英文摘要資訊取自各篇刊載內容。