基于智能对象的决策支持系统体系结构研究

分析了决策问题及其求解过程 ,揭示了传统IDSS体系结构的不足 ,阐述了应用面向对象的结构化知识表达构造智能对象 ,提供了智能决策过程支持的方法和新的IDSS体系结构 ,并在农业空间决策信息系统的实践中进行了验证     

Discourse,representation and urban planning: How a critical approach to discourse helps reveal the spatial re-ordering of street sex work1

This paper shows how a critical approach to discourse sheds light on processes of spatial re-orderings. It uses a case study of urban planning in an area of street sex work to explore the ways in which various representations of prostitution can be used to inform planning decisions. Representations of sex worker identity also expose complex spatial and social geographies and evolving processes of marginalisation and exclusion.     

Knowledge Representation Methods in Expert System for Earthquake Prediction ESEP 3.0

INTRODUCTIONKnowledgerepresentationandknowledgeacquisitionarekeyissuesinbuildinganexpertsystem .Theyarecloselyrelatedtothedomainproblem solvinglevelandcompetenceoftheexpertsystem .Intheknowledgeacquisitionprocess,thedomainexpertwillfirstofferandorganizepr…     

Inference and uncertainty of snow depth spatial distribution at the kilometre scale in the Colorado Rocky Mountains: the effects of sample size,random sampling,predictor quality,and validation procedures

Historically, observing snow depth over large areas has been difficult. When snow depth observations are sparse, regression models can be used to infer the snow depth over a given area. Data sparsity has also left many important questions about such inference unexamined. Improved inference, or estimation, of snow depth and its spatial distribution from a given set of observations can benefit a wide range of applications from water resource management, to ecological studies, to validation of satellite estimates of snow pack. The development of Light Detection and Ranging (LiDAR) technology has provided non‐sparse snow depth measurements, which we use in this study, to address fundamental questions about snow depth inference using both sparse and non‐sparse observations. For example, when are more data needed and when are data redundant? Results apply to both traditional and manual snow depth measurements and to LiDAR observations. Through sampling experiments on high‐resolution LiDAR snow depth observations at six separate 1.17‐km² sites in the Colorado Rocky Mountains, we provide novel perspectives on a variety of issues affecting the regression estimation of snow depth from sparse observations. We measure the effects of observation count, random selection of observations, quality of predictor variables, and cross‐validation procedures using three skill metrics: percent error in total snow volume, root mean squared error (RMSE), and R². Extremes of predictor quality are used to understand the range of its effect; how do predictors downloaded from internet perform against more accurate predictors measured by LiDAR? Whereas cross validation remains the only option for validating inference from sparse observations, in our experiments, the full set of LiDAR‐measured snow depths can be considered the ‘true’ spatial distribution and used to understand cross‐validation bias at the spatial scale of inference. We model at the 30‐m resolution of readily available predictors, which is a popular spatial resolution in the literature. Three regression models are also compared, and we briefly examine how sampling design affects model skill. Results quantify the primary dependence of each skill metric on observation count that ranges over three orders of magnitude, doubling at each step from 25 up to 3200. Whereas uncertainty (resulting from random selection of observations) in percent error of true total snow volume is typically well constrained by 100–200 observations, there is considerable uncertainty in the inferred spatial distribution (R²) even at medium observation counts (200–800). We show that percent error in total snow volume is not sensitive to predictor quality, although RMSE and R² (measures of spatial distribution) often depend critically on it. Inaccuracies of downloaded predictors (most often the vegetation predictors) can easily require a quadrupling of observation count to match RMSE and R² scores obtained by LiDAR‐measured predictors. Under cross validation, the RMSE and R² skill measures are consistently biased towards poorer results than their true validations. This is primarily a result of greater variance at the spatial scales of point observations used for cross validation than at the 30‐m resolution of the model. The magnitude of this bias depends on individual site characteristics, observation count (for our experimental design), and sampling design. Sampling designs that maximize independent information maximize cross‐validation bias but also maximize true R². The bagging tree model is found to generally outperform the other regression models in the study on several criteria. Finally, we discuss and recommend use of LiDAR in conjunction with regression modelling to advance understanding of snow depth spatial distribution at spatial scales of thousands of square kilometres. Copyright © 2012 John Wiley & Sons, Ltd.     

高光谱影像概率分类向量机分类方法研究

从分析基于支持向量机和相关向量机的高光谱影像分类方法的优势和不足出发,将基于概率分类向量机的方法用于高光谱影像分类试验。在贝叶斯理论框架下,概率分类向量机为基函数权值引入截断Gauss先验概率分布,使得不同类别的基函数权值具有不同符号的先验分布,并利用EM算法进行参数推断,得到足够稀疏的概率模型,弥补了相关向量机选取错误类别的样本作为相关向量的不足,从而有效地提高了模型的分类精度和稳定性。OMIS和PHI影像分类试验表明,概率分类向量机能够很好地应用在高光谱影像分类。     

基于改进K-SVD字典学习方法的地震数据去噪

为实现更好的地震数据去噪技术,笔者引入一种新的算法:快速迭代收缩阀值法(FISTA),通过FISTA和K-奇异值分解(K-SVD)不断迭代更新K-SVD字典,利用更新得到的K-SVD字典对地震数据进行稀疏表示,去除稀疏系数中较小的数值,使数据中的随机噪声得到压制。对层状模型合成地震记录,Marmousi模型合成地震记录以及实际地震数据进行对比实验,得出FISTA算法较OMP算法能更好地提高地震数据的信噪比,同时有效地保护了反射信号。     

Representation and participation in formulating Nepal’s REDD+ approach

ABSTRACT

REDD+ is an international policy aimed at incentivizing forest conservation and management and improving forest governance. In this article, we interrogate how newly articulated REDD+ governance processes established to guide the formulation of Nepal’s REDD+ approach address issues of participation for different social groups. Specifically, we analyse available forums of participation for different social groups, as well as the nature of their representation and degree of participation during the country’s REDD+ preparedness phase. We find that spaces for participation and decision-making in REDD+ have been to date defined and dominated by government actors and influential civil society groups, whereas the influence of other actors, particularly marginalized groups such as Dalits and women’s organizations, have remained limited. REDD+ has also resulted in a reduction of influence for some hitherto powerful actors (e.g. community forestry activists) and constrained their critical voice. These governance weaknesses related to misrepresentation and uneven power relations in Nepal cast doubt on the extent to which procedural justice has been promoted through REDD+ and imply that implementation may, as a consequence, lack the required social legitimacy and support. We discuss possible ways to address these shortcomings, such as granting greater prominence to neglected civil society forums within the REDD+ process, allowing for an increase in their influence on policy design, enhancing capacity and leadership of marginalized groups and institutionalizing participation through continued forest governance reform.

Key policy insights

• Participation is a critical asset in public policy design.

• Ensuring wide and meaningful participation can enhance policy legitimacy and thus its endorsement and potential effective implementation.

• Fostering inclusive processes through dedicated forums such as multi-stakeholder groups can help overcome power dynamics.

• While REDD+ is open to participation by different actors through a variety of formal means, many countries lack a clear framework for participation in national policy processes.

• Nepal’s experience with representation and participation of non-state actors in its REDD+ preparedness programme provides useful insights for similar social and policy contexts.

     

基于镜像图的LRC和CRC偏差结合的人脸识别

为了提高人脸识别率及更好地显示人脸特征,本文提出了一种基于镜像图的LRC和CRC偏差结合的人脸识别方法.该方法首先生成一种镜像人脸,再通过融合原始人脸和镜像人脸形成新的混合训练样本,最后利用LRC和CRC偏差结合进行人脸识别.新方法增加了训练样本的数目,克服了由于光照和姿态等外部因素带来的影响.实验结果表明,镜像图与LRC和CRC偏差结合的人脸识别方法提高了人脸识别的准确性.