Shi Wenzhong

Hierarchical support vector machines

The speed and accuracy of a hierarchical SVM (H-SVM) depend on its tree structure. To achieve high performance, more separable classes should be separated at the upper nodes of a decision tree. Because SVM separates classes at feature space determined by the kernel function, separability in feature space should be considered. In this paper, a separability measure in feature space based on support vector data description is proposed. Based on this measure, we present two kinds of H-SVM, binary tree SVM and k-tree SVM, the decision trees of which are constructed with two bottom-up agglomerative clustering algorithms respectively. Results of experimentation with remotely sensed data validate the effectiveness of the two proposed H-SVM.

Development of a hybrid model for three-dimensional GIS

This paper presents a hybrid model for three-dimensional Geographical Information Systems which is an integration of surface- and volume-based models. The Triangulated Irregular Network (TIN) and octree models are integrated in this hybrid models. The TIN model works as a surface-based model which mainly serves for surface presentation and visualization. On the other hand, the octree encoding supports volumetric analysis. The designed data structure brings a major advantage in the three-dimensional selective retrieval. This technique increases the efficiency of three-dimensional data operation.

A GIS-based research on the distribution of rural settlements in Yulin of northern Shaanxi

The development and distribution pattern of rural settlements was greatly limited by their natural and social environment. Taking Yulin prefecture in northern Shaanxi’s Loess Plateau area as an example, 1:250,000 map-scale national geographical database as a major information source, a GIS-based research was conducted to investigate the spatial distribution of the rural settlements. In this paper, many significant characteristics of the rural settlement distribution are reviewed by means of a series of GIS-based information processing methodology. The results obtained in this study should be helpful for the urban and rural settlements reconstruction planning in this area.

A WebGIS Based General Framework of Information Management and Aided Decision Making System for Earthquake Disaster Reduction

This article describes a methodology for establishing a general framework of the information management and aided decision making system for earthquake disaster reduction by means of a WebGIS. The system has a three-tier architecture consisting of data service, middleware, and expression service tiers. The system database is composed of the seismogeological database, the engineering environmental database, the disaster relief resource database and the analysis result database. The function components in the middleware tier include the earthquake hazard analysis, the construction vulnerability estimation, the quantifying economic losses and casualties caused by earthquakes, and the aided decision making components for post-earthquake emergency response. In order to further analyze earthquake damage data, three WebGIS analysis modules are designed on the client side, namely the foundational information module, the earthquake loss module and the emergency response module. In the information system based on this framework, the information about earthquake disaster reduction can be shared, the earthquake disaster data can be all-around analyzed, and aided decision making for post-earthquake emergency response can be efficiently made.

Development of a GIS data model with spatial, temporal and attribute components based on object-oriented approach

This paper presents a conceptual data model, the STA-model, for handling spatial, temporal and attribute aspects of objects in GIS. The model is developed on the basis of object-oriented modeling approach. This model includes two major parts: (a) modeling the signal objects by STA-object elements, and (b) modeling relationships between STA-objects. As an example, the STA-model is applied for modeling land cover change data with spatial, temporal and attribute components.

A fast super-resolution reconstruction from image sequence

Based on the mechanism of imagery, a novel method called the delaminating combining template method, used for the problem of super-resolution reconstruction from image sequence, is described in this paper. The combining template method contains two steps: a delaminating strategy and a combining template algorithm. The delaminating strategy divides the original problem into several sub-problems; each of them is only connected to one degrading factor. The combining template algorithm.is suggested to resolve each sub-problem. In addition, to verify the valid of the method, a new index called oriental entropy is presented. The results from the theoretical analysis and experiments illustrate that this method to be promising and efficient.

Point deletion for dynamic update of CD-TIN

Constrained Delaunay triangular irregular network (CD-TIN) is a basic data structure widely used in GIS, 3D reconstruction, computer geometry and geosciences. Traditional researches on Delaunay triangular irregular networks (D-TIN) paid more attention to the insertion algorithms for points and edges, while little to the deletion algorithms for points and edges. The present algorithms for D-TIN are far insufficient for the dynamic updating of CD-TIN, which demands for not only the insertion for points and edges, but also the deletion for points and constrained edges. Based on the improvements to the present insertion and deletion algorithms for D-TIN, an algorithm for point deletion in CD-TIN, namely integral ear elimination (IEE), which improved from the EE algorithm for D-TIN, is presented. Some examples are demonstrated that the presented algorithms in this paper for the updating of CD-TIN are efficient.

Approximate approaches to geometric corrections of high resolution satellite imagery

The exploitation of different non-rigorous mathematical models as opposed to the satellite rigorous models is discussed for geometric corrections and topographic/thematic maps production of high-resolution satellite imagery (HRSI). Furthermore, this paper focuses on the effects of the number of GCPs and the terrain elevation difference within the area covered by the images on the obtained ground points accuracy. From the research, it is obviously found that non-rigorous orientation and triangulation models can be used successfully in most cases for 2D rectification and 3D ground points determination without a camera model or the satellite ephemeris data. In addition, the accuracy up to the sub-pixel level in plane and about one pixel in elevation can be achieved with a modest number of GCPs.

An oases dynamics model and its application in the Manas oasis

This study applies theories of systems and system dynamics to ecological economic systems in the oasis environment, with the intention of finding the basic characteristics of the oasis environment and its feedback structures. This study explores the inner mechanisms of economic development in the oasis environment and its relationship to policy variables. This model is applied to economic development in the Manas oasis of the Xinjiang Uygur Autonomous Region of China. System dynamics method starts from studying feedback structure within the system study and then searches for the best solution through identifying the right “policy point” and through model simulation in the computer. It embodies the cream of “systems cybernetics theory”. This study is justified because the nature of the oasis system and the simulation results are scientifically sound and practically feasible.