灾害预警平台多源信息多层次精细化编码系统研究

由于我国各类灾害频繁发生, 防灾减灾迫切需要建立一个覆盖全国、 畅通有效的灾害预警信息综合发布平台。通过分析对比国内外有关灾害预警信息编码, 设计适合我国国情, 并与国际通用警报协议接轨的灾害预警平台多源信息多层次精细化编码系统, 有效地解决预警信息的地理编码、 信息编码和共享规范问题, 为我国建立覆盖全国、 畅通有效的灾害预警信息综合发布平台提供技术支撑。     

参与性方法在社区科技互助组织发展中的作用研究

参与性作为一种思想，强调了发挥每个群体的潜力、自主决策与合作；参与性作为一种方法，强调了创造参与的条件的一切手段和措施。参与性途径自90年代引进中国以来，在很多发展项目中广泛应用。参与性到底有什么贡献？根据参与性科技扶贫示范研究项目的实践，从参与性途径在社区科技互助组织发展过程中的作用、影响参与性发挥作用的因素以及不同群体对参与性的认同和体会等方面，对参与性途径进行了深入分析。     

Quantifying the UK’s incentives for low carbon investment

The UK climate change programme has introduced a range of instruments to foster investment in low carbon technologies and markets. We estimate the total value of these interventions, in terms of the redirection of financial flows and directly foregone tax income, to be about £1.3 billion per year (c. Euro or US$ 2 billion per year), as from 2002 to 2003 when the renewable obligation certificates (ROCs) first take effect. About 20% of this consists of direct expenditure, the remaining 80% is in the form of indirect expenditures contained within sectors (ROCs, the energy efficiency commitments), and foregone tax revenues. Most of the energy-efficiency investment is estimated to recoup expenditure within normal life-cycles and may thus be considered profitable; the profitability of the supply-side interventions is predicated mostly upon expected cost reductions associated with the build up of the associated industries.     

Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment

Current disaster management procedures to cope with human and economic losses and to manage a disaster’s aftermath suffer from a number of shortcomings like high temporal lags or limited temporal and spatial resolution. This paper presents an approach to analyze social media posts to assess the footprint of and the damage caused by natural disasters through combining machine-learning techniques (Latent Dirichlet Allocation) for semantic information extraction with spatial and temporal analysis (local spatial autocorrelation) for hot spot detection. Our results demonstrate that earthquake footprints can be reliably and accurately identified in our use case. More, a number of relevant semantic topics can be automatically identified without a priori knowledge, revealing clearly differing temporal and spatial signatures. Furthermore, we are able to generate a damage map that indicates where significant losses have occurred. The validation of our results using statistical measures, complemented by the official earthquake footprint by US Geological Survey and the results of the HAZUS loss model, shows that our approach produces valid and reliable outputs. Thus, our approach may improve current disaster management procedures through generating a new and unseen information layer in near real time.     

基于多模态的音乐推荐系统

使用传统协同过滤的方式进行推荐往往会忽视音乐底层特征.通过将音乐的音频特征与歌词信息进行多模态融合,并将融合后的特征信息作为协同过滤推荐的补充,提出了一种基于多模态的音乐推荐系统.主要探讨了音频特征与歌词信息的提取,并在提取歌词信息时利用LDA主题模型进行特征降维.针对多模态融合问题,使用一种特征级联早融合法（EFFC）融合方式,并将多模态融合后的结果与单模态结果进行了比较.对于结果的推荐,以多模态特征信息为依据建立用户兴趣模型,并将该模型通过LSTM神经网络,以过滤与优化协同推荐的用户组.结果表明,基于多模态的音乐推荐系统将推荐结果的误差项平方和（SSE）由传统的2.009降至0.388 6,验证了该方法的有效性.     

Description and characterization of place properties using topic modeling on georeferenced tags

ABSTRACT

User-Generated Content (UGC) provides a potential data source which can help us to better describe and understand how places are conceptualized, and in turn better represent the places in Geographic Information Science (GIScience). In this article, we aim at aggregating the shared meanings associated with places and linking these to a conceptual model of place. Our focus is on the metadata of Flickr images, in the form of locations and tags. We use topic modeling to identify regions associated with shared meanings. We choose a grid approach and generate topics associated with one or more cells using Latent Dirichlet Allocation. We analyze the sensitivity of our results to both grid resolution and the chosen number of topics using a range of measures including corpus distance and the coherence value. Using a resolution of 500 m and with 40 topics, we are able to generate meaningful topics which characterize places in London based on 954 unique tags associated with around 300,000 images and more than 7000 individuals.     

融合主题语义特征的高分辨率遥感影像建筑物自动化识别

建筑物提取是高分辨率遥感影像解译领域的一项重要工作,由于遥感技术的宏观性、实时性和周期性特点,基于遥感影像的建筑物识别对于城市管理与国土规划等领域具有非常大的应用潜力.本文介绍了一种基于影像主题语义特征建模的高分辨率遥感影像建筑物提取方法并通过具体的影像场景加以实践应用,该方法首先对影像进行对象级的分割,然后利用LDA...     

《中国岩溶》网络影响特征及其分析

为能比较确切地了解《中国岩溶》的网络影响力和明确今后办刊的努力方向,以中国知网( CNKI)中心网站2005年1月1日— 2007年3月15日的日志记录资料为依据,运用CNKI所提供的期刊文献评价统计分析系统软件对《中国岩溶》的网络传播特征进行了统计分析。结果表明, 1982— 1998年,由于论文的时效性等原因, 《中国岩溶》被访问和下载量比较小, 1982— 1993年所出版的论文平均每篇受访、下载率不足0. 7和0. 4次, 1994— 1998年为20. 1和7. 1次,属《中国岩溶》论文被访问下载量基本无升幅和小额度升幅时段; 1999年以后,由于能够主动地根据国家社会经济发展需要,及时调整选题并加强生态环境、水资源开发、环境地质等研究领域的组稿力度,被访问下载量明显提高,平均每篇被访问、下载率分别达78. 9次和34. 8次,为《中国岩溶》论文被访问下载的高额度升幅时段。当前《中国岩溶》网络传播存在的主要问题是国外网络传播能力比较小等,亟待通过不断加强海外宣传及规范中英文摘要的编写等手段加以解决。      

江苏及其邻区地震应急宣传及效果

通过对江苏及其邻区１０ 多年来发生的典型地震事件及地震谣传的社会反应和各地应急宣传方案的对比, 研究防震减灾宣传的效果及应急宣传措施, 提出防震减灾应急宣传的对策。     

四川邛海国家湿地公园宣教中心布展设计

宣教中心是集主体化、系统化和集中化为一体的综合型宣教场所,是国家湿地公园宣教工作的亮点。阐述了四川邛海国家湿地公园宣教中心的布展设计原则、设计内容与表现形式。围绕“湖的自白”“水之密语”“鸟儿的鸣响”“鱼的呢喃”“植物悄悄话”“外来的‘朋友’不友善”“人类有话说”和“保护邛海,我们在行动”8个主题,以32个故事单元为节点,采取动静结合、互动体验的表现形式开展宣教布展,系统完整地展现邛海国家湿地公园的特色,以期为同类湿地公园的科普宣教布展设计提供借鉴参考。