关联向量机及其在入侵检测中的应用探讨

介绍一种稀疏的贝叶斯学习算法——关联向量机(RVM)，它在再生核希尔伯特空间中学习，利用贝叶斯方法推理，推广能力好，与支持向量机相比不仅解更为稀疏而且不需要调整超参数。应用RVM的对小样本的良好分类能力，提出一种基于RVM的入侵检测原型系统。     

Context matters: The drivers of environmental concern in European regions

Environmental concern is crucial as bottom-up support for policies that aim to tackle the multiple ecological crises. This paper investigates which characteristics of 206 European regions are robust drivers of generalized environmental concern. To this end, 25 Eurobarometer survey waves between 2009 and 2019 were combined with measures of the regional economy, population, geography, environmental quality, and meteorological events. Bayesian model averaging is used to systematically account for model uncertainty in the estimation of partial correlations. The results indicate that environmental concern increases with income level, a more equal distribution of income and wealth, and a less greenhouse gas-intensive industrial sector. Furthermore, regions with younger and better educated populations exhibit higher levels of environmental concern. In terms of environmental characteristics, both geographical vulnerability to natural hazards and meteorological events affect environmental concern. The results highlight the importance of the socio-economic and environmental context of opinion formation and have implications for designing and communicating environmental policies.     

Crop discrimination in Northern China with double cropping systems using Fourier analysis of time-series MODIS data

Crop identification is the basis of crop monitoring using remote sensing. Remote sensing the extent and distribution of individual crop types has proven useful to a wide range of users, including policy-makers, farmers, and scientists. Northern China is not merely the political, economic, and cultural centre of China, but also an important base for grain production. Its main grains are wheat, maize, and cotton. By employing the Fourier analysis method, we studied crop planting patterns in the Northern China plain. Then, using time-series EOS-MODIS NDVI data, we extracted the key parameters to discriminate crop types. The results showed that the estimated area and the statistics were correlated well at the county-level. Furthermore, there was little difference between the crop area estimated by the MODIS data and the statistics at province-level. Our study shows that the method we designed is promising for use in regional spatial scale crop mapping in Northern China using the MODIS NDVI time-series.     

Bayes estimate of the probability of exceedance of annual floods

In this paper Lindley's Bayesian approximation procedure is used to obtain the Bayes estimate of the probability of exceedence of a flood discharge. The Bayes estimates of the probability of exceedence has been shown by S.K. Sinha to be equivalent to the estimate of the probability of exceedence from the predictive or Bayesian disribution, of a future flood discharge. The evaluation of complex ratios of multiple integrals common in a Bayesian analysis is not necessary using Lindley's procedure. The Bayes estimates are compared to those obtained by the method of maximum likelihood and the method of moments. The results show that Bayes estimates of the probability of exceedence are larger as expected, but have smaller posterior standard deviations.     

Bayesian probabilities of earthquake occurrences in Greece and surrounding areas

The Bayesian extreme-value distribution of earthquake occurrences has been adopted to estimate the seismic hazard in some seismogenic zones in Greece and surrounding regions. Seismic moment, slip rate, earthquake recurrence rate and magnitude were considered as basic parameters for computing the prior estimates of the seismicity. These estimates are then updated in terms of Bayes' theorem and historical estimates of seismicity associated with each zone.High probabilities for earthquakes withM6.0 have been obtained for the northwestern part of Greece as well as for the southwestern part of the Hellenic arc.     

Manual hierarchical clustering of regional geochemical data using a Bayesian finite mixture model

Interpretation of regional scale, multivariate geochemical data is aided by a statistical technique called “clustering.” We investigate a particular clustering procedure by applying it to geochemical data collected in the State of Colorado, United States of America. The clustering procedure partitions the field samples for the entire survey area into two clusters. The field samples in each cluster are partitioned again to create two subclusters, and so on. This manual procedure generates a hierarchy of clusters, and the different levels of the hierarchy show geochemical and geological processes occurring at different spatial scales. Although there are many different clustering methods, we use Bayesian finite mixture modeling with two probability distributions, which yields two clusters. The model parameters are estimated with Hamiltonian Monte Carlo sampling of the posterior probability density function, which usually has multiple modes. Each mode has its own set of model parameters; each set is checked to ensure that it is consistent both with the data and with independent geologic knowledge. The set of model parameters that is most consistent with the independent geologic knowledge is selected for detailed interpretation and partitioning of the field samples.     

Bayesian Equivalent Sample Toolkit (BEST): an Excel VBA program for probabilistic characterisation of geotechnical properties from limited observation data

In site investigation, the amount of observation data obtained for geotechnical property characterisation is often too sparse to obtain meaningful statistics and probability distributions of geotechnical properties. To address this problem, a Bayesian equivalent sample method was recently developed. This paper aims to generalize the Bayesian equivalent sample method to various geotechnical properties, when measured by different direct or indirect test procedures, and to implement the generalized method in Excel by developing an Excel VBA program called Bayesian Equivalent Sample Toolkit (BEST). The BEST program makes it possible for practitioners to apply the Bayesian equivalent sample method without being compromised by sophisticated algorithms in probability, statistics and simulation. The program is demonstrated and validated through examples of soil and rock property characterisations.     

Prediction of categorical spatial data via Bayesian updating

This study introduces a transition probability-based Bayesian updating (BU) approach for spatial classification through expert system. Transition probabilities are interpreted as expert opinions for updating the prior marginal probabilities of categorical response variables. The main objective of this paper is to provide a spatial categorical variable prediction method which has a solid theoretical foundation and yields relatively higher classification accuracy compared with conventional ones. The basic idea is to first build a linear Bayesian updating (LBU) model that corresponds to an application of Bayes’ theorem. Since the linear opinion pool is intrinsically suboptimal and underconfident, the beta-transformed Bayesian updating (BBU) model is proposed to overcome this limitation. Another type of BU approach, conditional independent Bayesian updating (CIBU), is derived based on conditional independent experts. It is shown that traditional Markovian-type categorical prediction (MCP) is equivalent to a particular CIBU model with specific parameters. As three variants of the BU method, these techniques are illustrated in synthetic and real-world case studies, comparison results with both the LBU and MCP favor the BBU model.     

天宝GX200地面三维激光扫描仪鉴别率检定

三维激光扫描技术是一种新兴的全自动、高精度测量技术。三维激光扫描仪能够在短时间内大面积、高密度地获取目标的空间点云数据,逼真细腻地描述目标表面。三维激光扫描仪作为一种测量仪器,本身也存在误差。目前,我国三维激光扫描仪检定技术较为薄弱且尚未制定系统的技术规范。本文结合国内外对三维激光扫描仪性能检定的理论方法,设计相应的实验方案,对所用Trimble GX200扫描仪的鉴别率进行检定。