Narrow Results

A MC method is proposed to compute upper limits, in a pure Bayesian approach, when the errors associated to the experimental sensitivity and to the expected background content are not Gaussian distributed or not small enough to apply the usual approximations. It is relatively easy to extend the procedure to the multichannel case (for instance when different decay branchings, or luminosities or experiments have to be combined). Some of the searches for supersymmetric particles performed in the DELPHI experiment at the LEP electron–positron collider use such a procedure to propagate the systematics into the calculation of the cross-section upper limits. One of these searches will be described as an example.

A Bayesian network is a directed acyclic graph in which each node represents a variable and each arc a probabilistic dependency; they are used to provide: a compact form to represent the knowledge and flexible methods of reasoning. Obtaining it from data is a learning process that is divided in two steps: structural learning and parametric learning. In this paper we define an automatic learning method that optimizes the Bayesian networks applied to classification, using a hybrid method of learning that combines the advantages of the induction techniques of the decision trees (TDIDT-C4.5) with those of the Bayesian networks. The resulting method is applied to prediction in health domain.

Accounting the problem of small sample size in tomato yield statistics, a dual-fusion prediction analysis model based on Bayes theory and deep learning algorithm Cascade-PSPNET is proposed. The tomato yield prediction is conducted based on remote sensing image time series analysis and multi-source information fusion theory with Bayesian theory and credibility weighting. First, the area of tomato planting is analyzed through semantic segmentation algorithms of remote sensing images during the tomato planting process. The yield is predicted by variables such as planting area fluctuation, disaster cycle fluctuation, etc. Through analyzing the reduced yield affected by disasters in different time periods of remote sensing images during planting process, the value chain of tomato industry is calculated by comprehensively analyzing price-value system, inflation coefficient, and unit area yield. At the same time, the annual patent application volume is used to predict the change of tomato yield year by year according to Bayesian theory, and the relationship between annual patent application volume and tomato yield year by year under different confidence levels is analyzed. The results show that it is feasible to use the Bayes method with semantic segmentation algorithms of remote sensing images to predict tomato yield. Next, the experiment of fusion prediction between two prediction models in the same target area will be carried out for verification.

We review the basic statistical tools used by experimental high energy physicists to analyze, interpret, and present data. After an introduction on the meaning of probability, we describe approaches to hypothesis testing, interval estimation, and search procedures.

In order to improve the leaked problem for the user sensitive information, a sensitive data leakage detection model based on Bayes Convolution neural networks (CNN) is proposed. At first, the data is divided in this method, and the leakage degree is detected with the hierarchical clustering algorithm, which the packets are clustered to generate signatures. Then, the frequent items in data acquisition are collected combined with Bayes Convolution neural networks, and access correlation is calculated between the sensitive data and normal data. Finally, through the simulation experiment, the performance of the method and other methods is deeply studied. The results show that this method has good adaptability.

We consider measurements which can be expressed by a nonlinear parametric regression model. Defining and computing point and interval estimators for such parameters in agreement with the data, the model and additional available information are frequent problems in science and engineering. The usual frame works for solving these problems are Maximum Likelihood (ML) and Bayes (B) inference. The ML approach in our case leads to a nonlinear least-squares problem. On the other hand, the B approach leaves several possibilities for inference. Some standard computational methods under the respective approaches are reviewed and presented. Their performance is investigated in a Monte-Carlo study on a test problem from material science. The problem size is chosen to be small (four parameters), nevertheless the problem displays typical intricacies associated with nonlinear regression: parameter dependent correlations, break-down of linear approximations and global optimization difficulties.