RCP-based GIS System And Clustering Technology Research

RCP(Rich Client Platform) is a kind of application of Eclipse plug-in development, it change the disadvantage position of Java application development in desktop application.And uDig is an open source desktop application framework of GIS,which can be convenient to redevelop GIS on it.We try to introduce clustering into the GIS system when we are developing it.Therefore we point to clustering analysis technique to launch research.Clustering is a technique that tries to divides the physical or abstract objects set into different clusters with similarities or dissimilarities between objects.Clustering which is important mankind's behavior plays an important role in many engineering fields such as data mining, image analysis, computer vision, bioinformatics, text analysis.In this paper,we give a introduction to uDig firstly which is an open source desktop application framework of GIS based on RCP technique. Then we make a concrete research on clustering. The main work of this paper was summarized as follows:The first section is exordium. In this section we introduce the research status of RCP. And reviews the clustering technique , analysising representative clustering algorithm.In the second section . we have introduced the RCP technique and uDig which is based on RCP can be conveniently applied to develop GIS.In the third section, A mercer-kernel based mixed c-means fuzzy clustering algorithm with attributes weights in feature space is proposed, which considers the imbalance between the attributes fully and uses kernel function to make it possible to cluster data that is linearly non-separable in the original space into homogeneous groups in the transformed high dimensional space with optimized kernel parameters. The experimental results show that the proposed algorithm can precisely find the ideal cluster centers and gives better results.In the fourth section, a fuzzy clustering algorithm for relational data with multiple medoids weighted is proposed. In the algorithm, multiple objects in each cluster carry different weights called medoids weights to represent their degrees of representativeness in that cluster.This mechanism can make each cluster to be represented by multiple objects instead of using only one object to represent the whole cluster. The experimental results show that the proposed algorithm can capture the underlying structures of the data more accurately and provide richer information for the description of the resulting clusters.In the fifth section, a Semi-supervised mercer-kernel based Fuzzy clustering algorithm with Pairwise Constraints and attributes weighted is proposed which incorporates both semi-supervised learning technique and the kernel method into the traditional fuzzy clustering algorithm.The proposed algorithm performs clustering in high feature space mapped by a mercer kernels and consider the imbalance between the attributes fully.Due to the Pairwise Constraints,it can provide a better clustering result.In the sixth section, a two-level clustering algorithm for High-Dimensional data of GIS is proposed.in the method, it provides a example data to demonstrate the application of clustering in the GIS system.