How to obtain proper prior distribution is one of the most critical problems in Bayesian analysis. In many practical cases, the prior information often comes from different sources, and the prior distribution form cou...How to obtain proper prior distribution is one of the most critical problems in Bayesian analysis. In many practical cases, the prior information often comes from different sources, and the prior distribution form could be easily known in some certain way while the parameters are hard to determine. In this paper, based on the evidence theory, a new method is presented to fuse the information of multiple sources and determine the parameters of the prior distribution when the form is known. By taking the prior distributions which result from the information of multiple sources and converting them into corresponding mass functions which can be combined by Dempster-Shafer (D-S) method, we get the combined mass function and the representative points of the prior distribution. These points are used to fit with the given distribution form to determine the parameters of the prior distribution. And then the fused prior distribution is obtained and Bayesian analysis can be performed. How to convert the prior distributions into mass functions properly and get the representative points of the fused prior distribution is the central question we address in this paper. The simulation example shows that the proposed method is effective.展开更多
Statistical shape prior model is employed to construct the dynamics in probabilistic contour estimation.By applying principal component analysis,plausible shape samples are efficiently generated to predict contour sam...Statistical shape prior model is employed to construct the dynamics in probabilistic contour estimation.By applying principal component analysis,plausible shape samples are efficiently generated to predict contour samples.Based on the shape-dependent dynamics and probabilistic image model,a particle filter is used to estimate the contour with a specific shape.Compared with the deterministic approach with shape information,the proposed method is simple yet more effective in extracting contours from images with shape variations and occlusion.展开更多
In this paper, based on the utility preferential attachment, we propose a new unified model to generate different network topologies such as scale-free, small-world and random networks. Moreover, a new network structu...In this paper, based on the utility preferential attachment, we propose a new unified model to generate different network topologies such as scale-free, small-world and random networks. Moreover, a new network structure named super scale network is found, which has monopoly characteristic in our simulation experiments. Finally, the characteristics of this new network are given.展开更多
文摘How to obtain proper prior distribution is one of the most critical problems in Bayesian analysis. In many practical cases, the prior information often comes from different sources, and the prior distribution form could be easily known in some certain way while the parameters are hard to determine. In this paper, based on the evidence theory, a new method is presented to fuse the information of multiple sources and determine the parameters of the prior distribution when the form is known. By taking the prior distributions which result from the information of multiple sources and converting them into corresponding mass functions which can be combined by Dempster-Shafer (D-S) method, we get the combined mass function and the representative points of the prior distribution. These points are used to fit with the given distribution form to determine the parameters of the prior distribution. And then the fused prior distribution is obtained and Bayesian analysis can be performed. How to convert the prior distributions into mass functions properly and get the representative points of the fused prior distribution is the central question we address in this paper. The simulation example shows that the proposed method is effective.
基金Supported by a grant from Hi-Tech 863 plan of People's Republic ofChina (No.2002AA311141)
文摘Statistical shape prior model is employed to construct the dynamics in probabilistic contour estimation.By applying principal component analysis,plausible shape samples are efficiently generated to predict contour samples.Based on the shape-dependent dynamics and probabilistic image model,a particle filter is used to estimate the contour with a specific shape.Compared with the deterministic approach with shape information,the proposed method is simple yet more effective in extracting contours from images with shape variations and occlusion.
基金The project partly supported by the State 0utstanding Youth Foundation under Grant No. 70225005, National Natural Science Foundation of China under Grant Nos. 70501005, 70501004, and 70471088, the Natural Science Foundation of Beijing under Grant No. 9042006, the Special Program for Preliminary Research of Momentous Fundamental Research under Grant No. 2005CCA03900, the Innovation Foundation of Science and Technology for Excellent Doctorial Candidate of Beijing Jiaotong University under Grant No. 48006
文摘In this paper, based on the utility preferential attachment, we propose a new unified model to generate different network topologies such as scale-free, small-world and random networks. Moreover, a new network structure named super scale network is found, which has monopoly characteristic in our simulation experiments. Finally, the characteristics of this new network are given.
