计数型数据控制图:过去和未来趋势

计数型数据的应用涉及多种制造或服务过程,已引起学界和业界的高度重视.虽然相对计量型数据控制图而言,针对计数型数据控制图的研究较少,但是近二十年也有大量文献涌现.系统回顾和梳理计数型数据控制图的研究进展,以期能为学界和业界工作者提供理论全貌和实践指导.首先,回顾总结了一元计数型数据控制图的相关研究.然后,按照数据复杂程度逐步增加,先后梳理了多元计数型数据控制图、响应为计数型数据的轮廓控制图以及关联关系为计数型数据的网络控制图.最后,综合文献梳理结果,给出未来的研究方向.

地理国情普查统计数据网格化

针对地理国情普查中统计单元不统一,数据统计分析处理过程空间范围不匹配的问题,该文提出了一种地理国情普查统计数据网格化的方法。方法通过分析统计数据中的和值变量型数据,结合统计对象空间分布的实际情况,实现了基于影响因子的统计数据网格化;利用层次分析法确定了影响因子权重,并将该权重值应用到统计数据网格化过程中。实验结果表明:与传统的网格化方法相比,该方法的网格化结果更符合统计对象的空间实际分布情况。

OBJECT ORIENTED DATA MODELLING WITH APPLICATIONS TO CAD

An object oriented data modelling in computer aided design (CAD) databases is focused. Starting with the discussion of data modelling requirements for CAD applications, appropriate data modelling features are introduced herewith. A feasible approach to select the “best” data model for an application is to analyze the data which has to be stored in the database. A data model is appropriate for modelling a given task if the information of the application environment can be easily mapped to the data model. Thus, the involved data are analyzed and then object oriented data model appropriate for CAD applications are derived. Based on the reviewed object oriented techniques applied in CAD, object oriented data modelling in CAD is addressed in details. At last 3D geometrical data models and implementation of their data model using the object oriented method are presented.

Non-Gaussian Phase Screen Based on log-Poisson Distribution and Effect on Imaging

Gaussian models without intermittency are extensively used in estimating the effect of turbulence,but italso brings some puzzles,for example the observed pulse shape that disagrees with the result of the standard theoryof interstellar scintillations.Indeed the property of intermittency is inherent in turbulence,i.e.,all the quantities thatcharacterize it suffer from strong fluctuations.So it is necessary to consider turbulent intermittency in many applications.In this paper we propose a non-Gaussian phase screen,which obeys log-Poisson statistics,and also offers the correspondingpoint spread function(PSF).These results describe that intermittency leads to the more extent and different directionaldistribution of PSF.Theoretical analysis is made under the hypothesis of the phase difference satisfying log-Poissonstatistics,and the average point spread function,which accord qualitatively with the result of the above generated phasescreen,is derived.

Organizational Data Management： Proposing a Metadata-Driven Data Warehouse （DW） Model

Discussing the matter of organizational data management implies, almost automatically, the concept of data warehousing as one of the most important parts of decision support system （DSS）, as it supports the integration of information management by aggregating all data formats and provisioning external systems with consistent data content and flows, together with the metadata concept, as one of the easiest ways of integration for software and database systems. Since organizational data management uses the metadata channel for creating a bi-directional flow, when correctly managed, metadata can save both time and resources for organizations. This paperI will focus on providing theoretical aspects of the two concepts, together with a short brief over a proposed model of design for an organizational management tool.

Design of database management system of oil shale resource evaluation based on GIS

Base on the oil shale data model,the authors analyz the four main data types and their mutual relations,grasped the focus on the oil shale data management,established UML visual demand model for oil shale resources in the field of evaluation,constructed three-tier system and developed oil shale resource evaluation database management system. The system can be used for managing oil shale data storage,enhancing the efficiency and quality of the oil shale resource evaluation.

Towards a New Geoid Model of Tanzania Using Precise Gravity Data

The new geoid model of Tanzania is a major breakthrough in the determination of vertical heights for the past 60 years. A new geoid model has been computed using precise gravity data supplemented with marine gravity data from Gravity Recovery and Climate Experiment （GRACE） satellite and new high-resolution satellite gravity data from Gravity field and steady-state Ocean Circulation Explorer （GOCE）. A digital terrain model was also used based on 15＂ Shuttle and Rader Terrain Model （SRTM） data. The use of gravity data makes an orthometric height easily computed using Global Navigation Satellite System （GNSS）. The GNSS is being used in many African countries including Tanzania and soon it will replace conventional leveling technique and avoid frequent maintenance of benchmarks. This paper presents preliminary result of a new geoid model which shows that by using precious gravity data and Remove-Compute-Restore technique, an accuracy of 10 cm can be reached.

Local Polynomial-Brunk Estimation in Semi-Parametric Monotone Errors-in-Variables Model with Right-Censored Data

This paper introduces a semi-parametric model with right-censored data and a monotone constraint on the nonparametrie part. The authors study the local linear estimators of the parametric coefficients and apply B-spline method to approximate the nonparametric part based on grouped data. The authors obtain the rates of convergence for parametric and nonparametric estimators. Moreover, the authors also prove that the nonparametric estimator is consistent at the boundary. At last, the authors investigate the finite sample performance of the estimation.

A Web-based Geographic Hypermedia System:Data Model,System Design and Prototype Applications

Geographic Hypermedia(GH)is a rich and interactive map document with geo-tagged graphics,sound and video ele-ments.A Geographic Hypermedia System(GHS)is designed to manage,query,display and explore GH resources.Recognizing emerging geo-tagged videos and measurable images as valuable geographic data resources,this paper aims to design a web-based GHS using web mapping,geoprocessing,video streaming and XMLHTTP services.The concept,data model,system design and implementation of this GHS are discussed in detail.Geo-tagged videos are modeled as temporal,spatial and metadata entities such as video clip,video path and frame-based descriptions.Similarly,geo-tagged stereo video and derived data are modeled as interre-lated entities:original video,rectified video,stereo video,video path,frame-based description and measurable image(rectified and disparity image with baseline,interior and exterior parameters).The entity data are organized into video files,GIS layers with linear referencing and XML documents for web publishing.These data can be integrated in HTML pages or used as Rich Internet Appli-cations(RIA)using standard web technologies such as the AJAX,ASP.NET and RIA frameworks.An SOA-based GHS is designed using four types of web services:ArcGIS Server 9.3 web mapping and geoprocessing services,Flash FMS 3.0 video streaming ser-vices and GeoRSS XMLHTTP services.GHS applications in road facility management and campus hypermapping indicate that the GH data models and technical solutions introduced in this paper are useful and flexible enough for wider deployment as a GHS.

AN ALGORITHM FOR MAXIMUM LIKELIHOOD ESTIMATES TO SEMI-PARAMETRIC REGRESSION MODEL WITH INTERVAL CENSORED DATA

In this paper we study the practical procedure for getting the maximumlikelihood estimates in a semi-parametric regression model with interval censored data.On the basis of the on previous theoretical results, we give the detailed algorithms when there are one or two covariates in the model.