Centrality is an important concept in the study of social network analysis (SNA), which is used to measure the importance of a node in a network. While many different centrality measures exist, most of them are proposed and applied to static networks. However, most types of networks are dynamic that their topology changes over time. A popular approach to represent such networks is to construct a sequence of time windows with a single aggregated static graph that aggregates all edges observed over some time period. In this paper, an approach which overcomes the limitation of this representation is proposed based on the notion of the time-ordered graph, to measure the communication centrality of a node in dynamic networks.

In this paper, an efficient filter method for salt-and-pepper noise removal is proposed. This method is developed by using cubic B-spline. A noise detector is employed to check whether the selected pixel is noisy or noise free. In this method, noise free pixels are left unaltered. Since not every pixel is filtered, undue distortion can be avoided. Noise pixels are subjected to the filtering operation to reconstruct the intensity values of the noisy pixels. The noise free pixels are only considered in the filter operation. The cubic B-spline is used as a fitting function to generate additional values within the noise free pixels. The noisy pixel is replaced by the mean value of these pixel values. The window size is selected as 3 X 3 in the first step. If all pixels within the window are considered to be noise, then change the selected window size to 5 X 5. If all the pixels within this window are considered to be noise, then the noisy pixel is replaced by the previous resultant pixel. Comparison of the given filter with other existing filters is provided in this paper. The results demonstrate that the proposed technique can obtain better performances than other existing denoising techniques. As a result of this, the proposed method removes the noise effectively even at noise level as high as 97%.

This paper presents an efficient and simple adaptive method for high density salt-and-pepper noise removal. A noise detector is utilized to check whether the selected pixel is noisy or noise free. Noise pixels will then be subjected to the second stage of the filtering action, while the noise free pixels are left unaltered. Since not every pixel is filtered, undue distortion can be avoided. The noise free pixels are only considered in the filter operation for finding the value of the processed pixel. The window size is selected as 3 X 3 in the first step. If all pixels within the window are considered to be noise, then change the selected window size to 5 X 5. If all the pixels within the selected 5 x 5 window are considered to be noise, then the processing pixel is replaced by the previous resultant pixel. This technique requires one nonnoise original image as training image. The key point of the filter operation is based on the solution of the equations system X=A-1B in the nonnoise original image. An algorithm to extract the data from the nonnoisy image and form it in the linear equation system is presented. Comparison of the given filter with other existing filters is provided in this paper. The results demonstrate that the proposed technique can obtain better performances than other existing denoising techniques. The proposed method works well for high-density salt & pepper noise even up to a noise density of 97%.