流形上的空间密度聚类算法研究

研究流形上的聚类分析，针对基于密度的空间聚类引入了流形概念，提出1种基于流形的密度聚类算法，该方法将流形的概念与聚类相结合，可以适用于样本为复杂分布的聚类。文中通过实例证明此算法的有效性。     

黄河三角洲*暴雨雷达回波特征及临近预报

本文利用1994－1998年东营站713数字化雷达回波资料结合高空、地面形势，对发生在黄河三角洲地区的33个暴雨日41个暴雨中尺度雷达回波系统特征及形成过程进行了总结，提出了暴雨临近预报的着眼点。在1999年的预报服务中，取得了良好的经济效益和社会效益。     

A brief catalogue of failures: Framing evaluation and learning in fisheries resource management

We propose a framework for enabling a systematic evaluation of a fisheries resource management system, which we define as a feed-back mechanism coupled to a fishery. The resource management system includes four basic functions: diagnostics, intervention, goal setting, and decision making. This model allows for the development of an evaluation framework for fisheries resource management by facilitating a typology of failures. We suggest that the potential for systemic and interdisciplinary learning will be significantly enhanced through the process of developing such a framework.     

从《徐霞客游记》看明末南方的社会经济生活——纪念徐霞客逝世350周年

本文以《徐霞客游记》为依据,对明末南方的社会经济生活状况进行了初步归纳和分析,以揭示徐霞客对我国人文地理学的突出贡献。     

空间智能:地理信息科学的新进展

在总结多年来研究GIS智能计算的理论与实践基础上,提出地理信息科学发展的新方向:空间智能.空间智能强调发现与应用空间模式,以增强GIS处理复杂数据和解决复杂问题的能力.空间智能主要的技术体系由空间分析、空间优化和空间模拟三大模块构成,其技术基础包括空间统计与索引、智能代理、高级启发式,以及数学规划等系列智能技术.由于空间智能融合了机器学习、统计分析和人工智能等多个学科理论,面向解决实际工程需求中大量存在的复杂时空问题,因此理论上具有广阔的发展空间,实践上也有重大的应用需求.随着空间智能体系的完善和技术的进一步成熟,它将在实际应用中具有巨大的价值.     

动态最小二乘支持向量机学习算法

针对大样本集的训练问题和动态训练样本的模型更新问题,提出了动态最小二乘支持向量机学习算法.该算法充分利用已建好的模型,逐渐加入新样本,并可删除位于任何位置的非支持向量,避免了矩阵求逆运算,保证了算法的高效率.大坝变形及电离层延迟两个时间序列的预报实例表明,该算法具有计算时间短、预报精度高的特点.     

Automated Kerogen Classification in Microscope Images of Dispersed Kerogen Preparation

We develop the classification part of a system that analyses transmitted light microscope images of dispersed kerogen preparation. The system automatically extracts kerogen pieces from the image and labels each piece as either inertinite or vitrinite. The image pre-processing analysis consists of background removal, identification of kerogen material, object segmentation, object extraction (individual images of pieces of kerogen) and feature calculation for each object. An expert palynologist was asked to label the objects into categories inertinite and vitrinite, which provided the ground truth for the classification experiment. Ten state-of-the-art classifiers and classifier ensembles were compared: Naïve Bayes, decision tree, nearest neighbour, the logistic classifier, multilayered perceptron (MLP), support vector machines (SVM), AdaBoost, Bagging, LogitBoost and Random Forest. The logistic classifier was singled out as the most accurate classifier, with an accuracy greater than 90. Using a 10 times 10-fold cross-validation provided within the Weka software, we found that the logistic classifier was significantly better than five classifiers (p<0.05) and indistinguishable from the other four classifiers. The initial set of 32 features was subsequently reduced to 6 features without compromising the classification accuracy. A further evaluation of the system alerted us to the possible sensitivity of the classification to the ground truth that might vary from one human expert to another. The analysis also revealed that the logistic classifier made most of the correct classifications with a high certainty.     

The impact of residential desegregation on social integration: Evidence from a South African neighbourhood

This paper analyses the potential for social integration in post-apartheid urban South Africa by examining the lives of those already living in desegregated spaces. The case study is a low-cost state-assisted housing project situated in the wealthy southern suburbs of Cape Town. In this social housing project, named Westlake village, coloured and Black African (alongside a handful of white and Indian) residents were awarded state housing in 1999 as replacement for their previous homes (informal and formal), which were demolished to make way for a mixed land-use development, of which their new homes form a small component. Westlake’s desegregation is found to extend beyond mere residential abode, affecting resident’s everyday lives to the extent that apartheid’s history and geography are superseded by other factors (such as proximity and affordability) in decision-making. Furthermore, integration at the everyday level of informal neighbourly mixing is prevalent. Although more formal cross-race friendships are rare, discussion reveals this as a consequence of Westlake’s specific socio-historic identity rather than racial divisions per se. Empirical evidence is used to propose a continuum of social integration experience. This continuum addresses the form of integration, for example greeting in the street, visiting homes, inter-marriage; and also the spaces of integration, for example physical space (shared neighbourhood), economic space (common employment-type), social space (cross-race friendship), political space (common involvement in civic organisations) and cultural space (shared sense of belonging).     

Tackling social exclusion in European neighbourhoods: experiences and lessons from the NEHOM project

Disadvantaged urban neighbourhoods with their complex social, economic and physical situations have increasingly become the focus of governmental policies in the EU. The emphasis has shifted from improving physical qualities to building opportunities for social groups in these areas. While physical upgrade is easier to achieve, at least in the short run, initiatives often fail in outcomes on communities and local participation. This paper aims to improve understanding on how to tackle area-based social exclusion and create socially coherent communities. Building on the results of the NEHOM project, the focus is on examining how various interventions have impacted local communities and their opportunities for better inclusion. A comparison between neighbourhoods shows that mixing social groups to a certain degree is likely to be a necessary step towards opening long-term opportunities for a disadvantaged neighbourhood. The planned initiatives should at the same time directly benefit local communities, and the involvement of local groups in the planning and implementation process helps to guarantee that the overall changes are accepted by the local community. However, the proposed guidelines do not provide a universal recipe for a successful renewal suiting each neighbourhood—the contextual matters should always be a starting point when planning an initiative.     

A safer city centre for all? Senses of `community safety' in Newcastle upon Tyne

In recent years, many city authorities in Europe and North America have sought to attract people back to city centres for leisure, shopping, business and residence. The planning measures commonly adopted take explicit account of issues of crime and safety. The concept of `community safety' as applied to the city centre is problematic, however, as users have diverse lifestyles, interests and values which impact on their own and others' safety. This paper reports on a study of the experiences and perceptions of safety of different groups of city centre users in Newcastle upon Tyne, England. While social identities and roles shaped the extent of concern and subsequent impacts on people's use of the city centre space, the research suggested that many concerns are genuinely shared. The paper investigates the congruence of a range of planning strategies with city centre users' safety concerns. Situational measures were viewed with scepticism, as fear centres on the presence and behaviour of others.