KGI-XGIS supporting decision making with knowledge-based techniques

The concept of the King George Island Expert GIS (KGI-XGIS) is introduced. KGI-XGIS is a combination of a rule-based expert system and a GIS meant to form an intelligent spatial decision support system. The system provides the spatial knowledge necessary for the environmental impact assessment process as dictated by the ‘Madrid Protocol’ for King George Island (South Shetland Islands, Antarctica). It also serves as information system to the scientific user community. Topographic maps, remote sensing data, thematic maps based on field surveys and other digital data form the input data to the GIS. Given the sparseness of the available data these must be combined and used in the most efficient way. Therefore expert knowledge of different domains will be coded into a rule-based expert system which is coupled to the GIS. To handle the expert knowledge and the spatial data of different types and different quality the KGI-XGIS incorporates knowledge-based techniques and fuzzy reasoning. The selection of a camp site on the ice free area of Fildes Peninsula and data quality management are used as two examples to demonstrate the capabilities of the system.     

The role of spatial effects in the empirical analysis of regional concentration

 Economists have recently devoted an increasing attention to the issue of spatial concentration of economic activities. However, surprisingly enough, most of the empirical work is still based on the computation of very basic statistical measures in which the geographical characteristics of data play no role. By making use of a series of empirical examples we show that spatial concentration consists of two different features that are rarely kept as separate in the statistical analysis: an a-spatial concept of variability which is invariant to permutations, and the concept of polarization that refers to the geographical position of observations. Received: 8 August 2000 / Accepted: 20 June 2001     

Unconditional and conditional competing risk models of activity duration and activity sequencing decisions: An empirical comparison

 This paper reports the results of an empirical comparison of various types of competing risk models in predicting the timing and duration of activities. In particular, three types of models are compared: a non-competing risk model, an unconditional competing risk model, and a conditional competing risk model. The models are applied to an activity diary, collected in the Netherlands. The results of the comparison indicate that the conditional competing risk model performs best, indicating that the choice and timing of activities depends on the nature and duration of the activity conducted previously. The specific structure of these dependent transition probabilities are discussed in detail. Several socio-demographic variables are found to be significantly related to the transition probabilities. Received: 19 July 2001 / Accepted: 25 January 2002     

专题地图制图决策系统规则库的设计

在分析已有的专题地图制图决策支持系统的有关理论的基础上,总结相关制图知识,提出规则库设计的方法并设计部分规则实例,最后对规则库如何映射到关系数据库做了一些探讨,并建立了模型。     

On the Use of Weighted Linear Combination Method in GIS: Common and Best Practice Approaches

The weighted linear combination (WLC) technique is a decision rule for deriving composite maps using GIS. It is one of the most often used decision models in GIS. The method, however, is frequently applied without full understanding of the assumptions underling this approach. In many case studies, the WLC model has been applied incorrectly and with dubious results because analysts (decision makers) have ignored or been unaware of the assumptions. This paper provides a critical overview of the current practice with respect to GIS/WLC and suggests the best practice approach.     

Towards a conjoint-based, context-dependent model of task allocation in activity settings: Some numerical experiments

 None of the currently developed activity-based models of transport demand explicitly models task allocation among household members. To fill this gap, the present paper suggests to complement activity-based models of activity scheduling with a context-dependent model of task allocation. That is, it is assumed that the allocation of tasks within households is partly based on such contextual variables as the amount of time a member has to spend on mandatory activities and car availability. In particular, the paper advocates a conjoint-based approach, based on an assignment task as opposed to the traditional ranking, rating or choice response formats. By definition, an assignment task involves a combinatorial explosion of choice alternatives, implying that additional operational decisions to estimate the context-dependent model are required. This study presents the results of various numerical experiments, conducted to better understand the impacts of those decisions on the degree of bias in the parameter estimates of the choice model. The results of these simulations indicate that under particular assumptions, the development and estimation of a conjoint-based, context-dependent model of task allocation within households is feasible. Received: March 1999 / Accepted: June 2001     

Modeling pedestrian shopping behavior using principles of bounded rationality: model comparison and validation

Models of geographical choice behavior have been dominantly based on rational choice models, which assume that decision makers are utility-maximizers. Rational choice models may be less appropriate as behavioral models when modeling decisions in complex environments in which decision makers may simplify the decision problem using heuristics. Pedestrian behavior in shopping streets is an example. We therefore propose a modeling framework for pedestrian shopping behavior incorporating principles of bounded rationality. We extend three classical heuristic rules (conjunctive, disjunctive and lexicographic rule) by introducing threshold heterogeneity. The proposed models are implemented using data on pedestrian behavior in Wang Fujing Street, the city center of Beijing, China. The models are estimated and compared with multinomial logit models and mixed logit models. Results show that the heuristic models are the best for all the decisions that are modeled. Validation tests are carried out through multi-agent simulation by comparing simulated spatio-temporal agent behavior with the observed pedestrian behavior. The predictions of heuristic models are slightly better than those of the multinomial logit models.     

Comparative performance of per-pixel classifiers using ers-1 sar data for classification of rice crop

Three-date ERS-1 SAR data acquired on August 24, September 28 and November 2, 1995, was used to classify rice crop in a predominant rice growing region of West Bengal. India, Artificial neural network, maximum likelihood, decision rute and K-Means clustering classifiers were used. Classification accuracy was evaluated from the error matrix of same set of training and validating pixels. Rice classification accuracy improved significantly using neural network classifier. The decision rule based classifier performed equally good for most of the sites, indicating the feasibility of deriving a common rule based algorithm for large area application. Law aecuracy was observed for maximum likelihood classifier.     

Radar speckle reduction and derived texture measures for land cover/use classification: a case study

This study examined the appropriateness of radar speckle reduction for deriving texture measures for land cover/use classifications. Radarsat-2 C-band quad-polarised data were obtained for Washington, DC, USA. Polarisation signatures were extracted for multiple image components, classified with a maximum-likelihood decision rule and thematic accuracies determined. Initial classifications using original and despeckled scenes showed despeckled radar to have better overall thematic accuracies. However, when variance texture measures were extracted for several window sizes from the original and despeckled imagery and classified, the accuracy for the radar data was decreased when despeckled prior to texture extraction. The highest classification accuracy obtained for the extracted variance texture measure from the original radar was 72%, which was reduced to 69% when this measure was extracted from a 5 × 5 despeckled image. These results suggest that it may be better to use despeckled radar as original data and extract texture measures from the original imagery.     

Enhancing a GIS Cellular Automata Model of Land Use Change: Bayesian Networks, Influence Diagrams and Causality

Cellular Automata (CA) models at present do not adequately take into account the relationship and interactions between variables. However, land use change is influenced by multiple variables and their relationships. The objective of this study is to develop a novel CA model within a geographic information system (GIS) that consists of Bayesian Network (BN) and Influence Diagram (ID) sub‐models. Further, the proposed model is intended to simplify the definition of parameter values, transition rules and model structure. Multiple GIS layers provide inputs and the CA defines the transition rules by running the two sub‐models. In the BN sub‐model, land use drivers are encoded with conditional probabilities extracted from historical data to represent inter‐dependencies between the drivers. Using the ID sub‐model, the decision of changing from one land use state to another is made based on utility theory. The model was applied to simulate future land use changes in the Greater Vancouver Regional District (GVRD), Canada from 2001 to 2031. The results indicate that the model is able to detect spatio‐temporal drivers and generate various scenarios of land use change making it a useful tool for exploring complex planning scenarios.     

Spatial Prediction of Landslide Hazard Using Logistic Regression and ROC Analysis

An empirical modeling of road related and non‐road related landslide hazard for a large geographical area using logistic regression in tandem with signal detection theory is presented. This modeling was developed using geographic information system (GIS) and remote sensing data, and was implemented on the Clearwater National Forest in central Idaho. The approach is based on explicit and quantitative environmental correlations between observed landslide occurrences, climate, parent material, and environmental attributes while the receiver operating characteristic (ROC) curves are used as a measure of performance of a predictive rule. The modeling results suggest that development of two independent models for road related and non‐road related landslide hazard was necessary because spatial prediction and predictor variables were different for these models. The probabilistic models of landslide potential may be used as a decision support tool in forest planning involving the maintenance, obliteration or development of new forest roads in steep mountainous terrain.     

A rule-based parameter aided with object-based classification approach for extraction of building and roads from WorldView-2 images

Roads and buildings constitute a significant proportion of urban areas. Considerable amount of research has been done on the road and building extraction from remotely sensed imagery. However, a few of them have been concentrating on using only spectral information. This study presents a comparison between three object-based models for urban features’ classification, specifically roads and buildings, from WorldView-2 satellite imagery. The three applied algorithms are support vector machines (SVMs), nearest neighbour (NN) and proposed rule-based system. The results indicated that the proposed rules in this study, despite the spectral complexity of land cover types, performed a satisfactory output with an overall accuracy of 92.92%. The advantages offered by the proposed rules were not provided by other two applied algorithms and it revealed the highest accuracy compared to SVM and NN. The overall accuracy for SVM was 76.76%, which is almost similar to the result achieved by NN (77.3%).     

遥感卫星数据产品分类分级规则研究

随着遥感卫星应用的发展,多源、多时相、多尺度以及不同类型遥感卫星的数据综合集成应用以及与地面观测信息集成,对遥感信息产品进行深度开发利用正在成为遥感应用的重要趋势。目前不同国家和地区、不同系列的遥感卫星数据产品分别采用不同的分类分级方案,难以适应多源、多系列地理空间信息整合应用的需求。本文从遥感应用对遥感卫星数据产品分类分级的需求出发,分析了目前主要遥感卫星的产品系列及其数据产品分类分级规则,参考了正在研究的相关国际标准,遵循系统性、科学性、完整性、兼容性、可操作性和可扩充性原则,研究提出了中国遥感卫星数据产品分类分级的规则。该规则以卫星载荷采用的遥感探测光谱特征及其数据获取方式作为分类依据,以卫星遥感数据的处理水平作为分级依据,建立统一的遥感卫星数据产品的分类分级体系。该规则与正在研究制订的相关国际标准保持一致,不但覆盖目前广泛应用的各类遥感卫星数据产品,而且能方便地建立与现有遥感卫星数据产品分类分级方案的映射关系,并且对未来的数据产品的分类分级留有比较充分的可扩充性,为遥感卫星数据产品分类分级指标体系的研究和相关国家标准的研制提供了依据。     

多光谱遥感图像土地利用分类区域多中心方法

针对遥感图像土地利用一种类别由多种地物组成,存在难以求取类别光谱特征多元分布模型的问题,分析了多光谱遥感图像土地利用的光谱特征和区域多中心特征,提出了一种光谱信息和区域信息基于规则的区域多中心分类方法,以类别的类内中心集合表征类别模式,以区域为分类单元,以区域单元含类别类内中心数和区域单元中属于某种类别的像元占单元总像元的百分比为分类准则;采用类内中心表征类别模式和基于规则的分类方法,较好地解决了土地利用类别由多种地物组成、类别模式不满足多元正态分布的问题,由于类别区域单元多中心特性差异大,分类规则的建立及训练样本的选择易于实现。实验表明:该方法能提高分类精度4%—6%。     

知识与规则驱动的国土资源空间数据整合方法研究

本文根据GIS领域知识与规则研究的现状和趋势,结合国土资源行业空间数据的现状和要求,研究了国土资源空间数据知识与规则的研究方法与应用模式,提出了通过提取国土资源空间数据知识与规则,利用语义和组件实现规则的驱动,解决异构国土资源空间数据转换和同构空间数据检查入库自动化难题的国土资源空间数据整合方法。然后以面向地籍、土地利用现状的专题空间数据和面向地籍管理的基础空间数据的知识与规则提取、语义及规则驱动的语义和组件驱动的实现为实例进行了阐述。     

Spatial decision support system for home-delivered services

 We present a spatial decision support system for the non-profit sector, designed to assist planning in the area of home-delivered services such as meals on wheels. Using data collected from existing programs, current and forecasted demographic data, and a set of algorithmic tools, we provide a system for evaluating current meals on wheels facilities, and for making incremental facility location decisions that satisfy coverage and equity requirements. Received: 27 September 2000 / Accepted: 22 March 2001     

土壤遥感分类识别推理决策器的设计

介绍了干旱区土壤遥感分类识别推理决策器的设计原理与实现方法。在用TM遥感图像对土壤类型进行非监督分类的基础上，建立了正向推理与逆向推理相结合的推理机制，对土壤类型进行分类识别决策。用知识表示的产生式规则与框架式规则相结合的数据结构表示土壤学专家的土壤分类识别知识。用像结构模式建立了土壤分类识别的规则，构造了土壤分类判决树，并用典型像例模式进行了各类型土壤判据文件的组织。用该方法对新疆天山北麓阜康试验区的土壤分类识别进行了试验研究。结果表明，该方法分类精度可靠，为干旱区土壤分类识别开辟了一条新的途径。     

基于知识的空间决策支持模型集成

提出通过黑板集成模型,设计并实现了一个以模糊逻辑为基础的空间决策支持系统。该系统以产生式规则表达知识,采用逆向推理,使之成为兼具地理信息系统、专家系统,应用模型的集成化空间决策支持系统。使用该系统建立了重庆市区投资环境。使用该系统建立了重庆市区投资环境评价信息系统。     

近代回归分析在交通调查分析建模中的应用

本文以出行发生量模型的建立为例,较为系统地讨论了近代回归分析中的自变量选择及回归诊断方法在交通调查分析建模中的应用。分析了在获取调查数据后,如何借助回归自变量选择方法来选择最佳自变量子集,以确定简捷的回归模型;文中应用回归诊断方法,讨论了修正回归模型、探测错误的调查数据的方法,从而为建立简捷、高精度的交通模型打下了基础。最后,作者提出了应用自变量选择及回归诊断方法建立出行发行量模型的一般步骤。