基于近似域划分的可变离散精度粗逻辑网络及其遥感图像分类应用

张东波; 王耀南

doi:10.3724/SP.J.1146.2006.00584

基于近似域划分的可变离散精度粗逻辑网络及其遥感图像分类应用

doi: 10.3724/SP.J.1146.2006.00584

张东波^{①②;王耀南},
王耀南

基金项目:

国家自然科学基金(60375001)，高等学校博士点基金(20030532004)和湖南省教育厅科研项目(05C093)资助课题

计量
- 文章访问数: 3157
- HTML全文浏览量: 99
- PDF下载量: 753
- 被引次数: 0
出版历程
- 收稿日期: 2006-05-08
- 修回日期: 2006-10-08
- 刊出日期: 2007-11-19

Variable Discretization Precision Rough Logic Neural Network Based on Approximation Area Partition and Its Application toRemote Sensing Image Classification

Zhang Dong-bo^{①②;王耀南},
Wang Yao-nan

摘要

摘要: 为解决粗逻辑神经网络精度与网络规模复杂性和推广泛化能力之间的矛盾，该文提出了一种具有可变离散精度的粗逻辑神经网络设计方法。该方法通过近似域划分，将论域空间划分为确定性区域和可能性区域，由于可能性区域信息粒度过大是造成误分类的重要原因，只需对可能性区域离散区间进一步细化，即可达到提高粗逻辑网络的精度，同时抑制网络规模增长过快的目的。在长白山地区的遥感图像分类实验中，常规方法在离散等级为7时有最好性能，而该文方法以较小的网络代价和训练时间获得了逼近的分类结果。
- 遥感图像分类;粗糙集;粗逻辑网络
Abstract: A variable discretization precision rough logic neural network is proposed to solve contradiction between network precision and the size of network as well as generalization ability. Based on the approximation area partition, the universe discussed can be partitioned into certain area and possibility area. The important reason of misclassification is the granularity of the possibility area is too coarse. In this work, only possibility area is refined and the precision of the rough logic neural network is improved while the size of network is restrained. In the experiment of the remote sensing image classification about Changbai mountain area, the performance of conventional method is best when the discretization level is 7. The most approximated result is acquired, while less network cost and training time are expended, when this method is used.

HTML全文

参考文献(1)

Pawlak Z. Rough set theory and its application to data analysis[J].Cybernetics and Systems.1998, 29(9):661-688[2]Pawlak Z. Rough set theory for intelligent industrial applications. Intelligent Processing and Manufacturing of Materials, 1999, IPMM'99,Honolu, 10-15 July, 1999, 1: 37-44.[3]Pawlak Z. Rough logic. Bulletin of the Polish Academy of Sciences, Technical Science, 1987, 35: 253-258.[4]张东波, 王耀南, 易灵芝. 粗集神经网络及其在智能信息处理领域的应用. 控制与决策, 2005, 20(2): 121-126. Zhang Dong-bo, Wang Yao-nan and Yi Ling-zhi. Rough neural network and its application to intelligent information processing. Control and Decision, 2005, 20(2): 121-126.[5]Mohua B, Sushmita M, and Sankar K P. Rough fuzzy MLP: knowledge encoding and classification. IEEE Trans. on Neural Networks, 1998, 9(6): 203-1216.[6]Yu C Y, Wu M H, and Wu M. Combining rough set theory with neural network theory for pattern recognition. International Conference on Robotics, Intelligent Systems and Signal Processing, Changsha, 2003: 880-885.[7]Chen S Y and Yi J K. A fuzzy neural network based on rough sets and its applications to chemical production process. Info-tech and Info-net, 2001. Proceedings, Beijing Oct 29- Nov 1, 2001, 4: 405-410.[8]Wu Z C. Research on remote sensing image classification using neural network based on rough sets. Info-tech and Info-net, 2001. Proceedings, Beijing Oct 29-Nov 1, 2001, 4: 79-284.[9]Liu H J, Tuo H Y, and Liu Y C. Rough neural network of variable precision[J].Neural Processing Letters.2004, 19(1):73-87[10]Dougherty J, Kohavi R, and Shami M. Supervised and unsupervised discretization of continuous features. Proceedings of 12th International Conference on Machine Learning, CA: Morgan Kaufmann, 1995: 194-202.Nguyen H S and Skowron A. Quantization of real-valued attributes, rough set and Boolean reasoning approaches. 2nd International Joint Conference on Information Sciences, Wrightsville Beach, NC, USA, 1995: 34-37.

施引文献

资源附件(0)

访问统计