Liu Xu-min

Research on k-means Clustering Algorithm: An Improved k-means Clustering Algorithm

Clustering analysis method is one of the main analytical methods in data mining, the method of clustering algorithm will influence the clustering results directly. This paper discusses the standard k-means clustering algorithm and analyzes the shortcomings of standard k-means algorithm, such as the k-means clustering algorithm has to calculate the distance between each data object and all cluster centers in each iteration, which makes the efficiency of clustering is not high. This paper proposes an improved k-means algorithm in order to solve this question, requiring a simple data structure to store some information in every iteration, which is to be used in the next interation. The improved method avoids computing the distance of each data object to the cluster centers repeatly, saving the running time. Experimental results show that the improved method can effectively improve the speed of clustering and accuracy, reducing the computational complexity of the k-means.

Efficiently Using Matrix in Mining Maximum Frequent Itemset

an efficient way to discover the maximum frequent itemset can be very useful for mining association rules, correlations, episodes patterns, etc. Most existing work focuses on the technique for mining candidate maximal frequent itemset and ignores the technique for MFI checking. However the efficient of a MFS mining algorithm lies on these two parts. In this paper, a new MFI checking method is presented based on the optimizing of the former called MaxMatrix and an additional constraint for association rules generating is discussed to save mining time. In order to understand the process of MaxMatrix easily, an example is provided in detail.

Trigonometric polynomial uniform B-spline surface with shape parameter

In this paper, we study in depth a new modeling method of the parameter curve and surface, i.e. uniform trigonometric polynomial B-spline surface with shape parameters. We have designed a series of algorithms. We also develop a Space Freedom Surface Modeling System under Microsoft Visual C++6.0 programmed circumstance, with some examples given as the application of the model. Through experiments, we present the range of change of the shape parameters in this model and discuss its effect on the surface when the controlling polygon remains constant.In this paper, we study in depth a new modeling method of the parameter curve and surface, i.e. uniform trigonometric polynomial B-spline surface with shape parameters. We have designed a series of algorithms. We also develop a Space Freedom Surface Modeling System under Microsoft Visual C++6.0 programmed circumstance, with some examples given as the application of the model. Through experiments, we present the range of change of the shape parameters in this model and discuss its effect on the surface when the controlling polygon remains constant.

Uniform B-Spline Curve and Surface with Shape Parameters

In this paper, we have studied in depth a new modeling method of the parameter curve and surface-uniform b-spline surface with shape parameters. Based on this model, we have given an example of Free-form curve modeling, and analyzed the effect that different shape parameters have on the change of the shape of the curves. In light of the theory of computer graphics, we developed a space free-form surface modeling system (SFSMS) on Microsoft computer. Through the prototype system, we processed with the Free-form surface modeling, gave examples for its application, and discussed how the adjustment of the shape parameters affects the change of the shape of free-form surface.

A Research about Adaptive Subdivision Algorithm Based On DooSabin Mode

Subdivision surface method is a series of iterative operation adopts a certain subdivision formula for an initial grid, obtains the smooth limits surface finally, and can dispose any arbitrary complex topology grid. At present most of the subdivision algorithm are 1-4 subdivisions and as the number of subdivision increase, the grid grow so toorapid in the number of patch that it is difficult for the model after subdivision to deal with other things. We proposed an adaptive Doo-Sabin Mode subdivision algorithm to solve this problem, which take the average vector of the vertex and the angle between the intersecting surfaces of the vertex as a measurement criterion. This criterion is used to divide the surface, and then make local subdivision. In this way, when the times of subdivision are fewer (the demand of smoothness is not too high), the effect of subdivision has little difference, but efficiency of the algorithm can be greatly improved. Compared with the normal Doo-Sabin subdivision model, experimental results showed that adaptive Doo-Sabin subdivision algorithm can largely slow the growth speed of the amount of model data on the premise that guarantee the quality of surface.

Anisotropic Smoothing Algorithm for Triangular Mesh Models

An anisotropic smoothing algorithm for removing noise of triangular mesh models is proposed. First, the desirable normals of the triangles are approximated using our desirable normal computing schemes, and then each vertex is repositioned according to desirable normals of adjacent triangular faces. The desirable normals estimated by a weighted sum of normals at neighboring faces. If the face differs strongly from its neighboring face, the weight associated with that neighboring face is set small, and vice versa. We perform the anisotropic smoothing algorithm by controlling the magnitude of weight on estimation desirable normal of each triangular face. Many experimental results demonstrate the smoothing algorithm can not only efficiently remove the noise but also preserve original model’s sharp features and avoid oversmoothing.