Extracting and analyzing semantic relatedness between cities using news articles

News articles capture a variety of topics about our society. They reflect not only the socioeconomic activities that happened in our physical world, but also some of the cultures, human interests, and public concerns that exist only in the perceptions of people. Cities are frequently mentioned in news articles, and two or more cities may co-occur in the same article. Such co-occurrence often suggests certain relatedness between the mentioned cities, and the relatedness may be under different topics depending on the contents of the news articles. We consider the relatedness under different topics as semantic relatedness. By reading news articles, one can grasp the general semantic relatedness between cities; yet, given hundreds of thousands of news articles, it is very difficult, if not impossible, for anyone to manually read them. This paper proposes a computational framework which can ‘read’ a large number of news articles and extract the semantic relatedness between cities. This framework is based on a natural language processing model and employs a machine learning process to identify the main topics of news articles. We describe the overall structure of this framework and its individual modules, and then apply it to an experimental dataset with more than 500,000 news articles covering the top 100 US cities spanning a 10-year period. We perform exploratory visualizations of the extracted semantic relatedness under different topics and over multiple years. We also analyze the impact of geographic distance on semantic relatedness and find varied distance decay effects. The proposed framework can be used to support large-scale content analysis in city network research.     

基于Solr的空间数据语义搜索研究

随着互联网技术的飞速发展,基于网络地图的空间数据搜索成为人们获取空间信息的重要手段。文章分析了当前地图搜索的不足和瓶颈,阐述了其在处理空间语义方面的缺陷,提出了一种基于Solr的空间数据语义搜索方案:将全文检索引擎Solr应用到空间数据搜索中;同时,引入自然语言处理和本体技术,实现基于自然语言查询的空间数据语义搜索。最后建立原型系统进行验证,证明了该方案的可行性和有效性。     

Exploration of spatiotemporal and semantic clusters of Twitter data using unsupervised neural networks

ABSTRACT

The investigation of human activity patterns from location-based social networks like Twitter is an established approach of how to infer relationships and latent information that characterize urban structures. Researchers from various disciplines have performed geospatial analysis on social media data despite the data’s high dimensionality, complexity and heterogeneity. However, user-generated datasets are of multi-scale nature, which results in limited applicability of commonly known geospatial analysis methods. Therefore in this paper, we propose a geographic, hierarchical self-organizing map (Geo-H-SOM) to analyze geospatial, temporal and semantic characteristics of georeferenced tweets. The results of our method, which we validate in a case study, demonstrate the ability to explore, abstract and cluster high-dimensional geospatial and semantic information from crowdsourced data.     

A method for assessing generalized data accuracy with linear object resolution verification

The article is composed of two sections. In the first section, the authors describe the application of minimum line dimensions which are dependent on line shape, width and the operational scale of the map. The proposed solutions are based on the Euclidean metric space, for which the minimum dimensions of Saliszczew’s elementary triangle (Elementary triangle – is the term pertaining to model, standard triangle of least dimensions securing recognizability of a line. Its dimensions depend on scale of the map and width of the line representing it. The use of a triangle in the simplification process is as follows: triangles with sides (sections) on an arbitrary line and bases (completing the sides) are compared with lengths of the shorter side and the base of the elementary triangle.) were adapted. The second part of the article describes an application of minimum line dimensions for verifying and assessing generalized data. The authors also propose a method for determining drawing line resolution to evaluate the accuracy of algorithm simplification. Taking advantage of the proposed method, well-known simplification algorithms were compared on the basis of qualitative and quantitative evaluation. Moreover, corresponding with the methods of simplified data accuracy assessment the authors have extended these solutions with the rejected data. This procedure has allowed the identification of map areas where graphic conflicts occurred.     

基于用户点击数据的细粒度图像识别方法概述

近年来,细粒度图像识别逐渐成为计算机视觉领域的研究热点.由于不同类别图像间的视觉差异小、语义鸿沟问题严重,传统的基于视觉特征的细粒度图像识别性能往往不尽人意.针对这些挑战,目前许多学者都在研究基于用户点击数据的图像识别.本文围绕点击数据在图像识别中数据预处理、特征提取和模型构建3大模块中的应用,总结了已有的基于点击数据的识别算法及最新的研究进展.     

旅游资源专题语义符号自动匹配

针对传统符号自动匹配过程中匹配对象单一且符号复用率较低的问题,该文面向旅游专题符号提出了一种基于语义的符号匹配方法,利用语义分析与语义推理,解决制图所需符号的语义信息归类问题;用所属类符号进行符号匹配,较好地实现了一种符号的多种应用场景。实验结果证明该方法对提高符号的复用率及使用的规范性具有积极意义。     

Resource use conflicts in Mabini and Tingloy,the Philippines

This paper presents the results of an analysis of resource use conflicts in areas near marine protected areas in Mabini–Tingloy, the Philippines. The author found large differences between groups of stakeholders in terms of perceived benefits and costs of conservation and tourism, and these inequalities have led to conflicts between various stakeholder groups. Marked by unequal power relationships, the conflicts place subsistence fishers as the weakest stakeholders. Fishers also have the lowest rates of knowledge of and participation in conservation activities. The study concludes that in order for conservation programs to be effectively transitioned onto the social and legal fabric of Mabini–Tingloy, resource use conflicts need immediate attention.     

基于语义分割深度学习的找矿靶区预测研究——以广东省阳江-茂名地区为例

找矿靶区预测需要综合考虑地质背景、地球化学数据、地球物理勘探数据、遥感数据等因素。随着人工智能时代的到来,靶区预测可以最大限度地利用计算机运算性能,通过特定的规则集成所有地学数据对各类矿种的找矿靶区进行预测,尽可能规避由于数据种类多、数据量大、方法复杂、主观性强造成的预测结果可靠性差等问题。本文以广东省阳江-茂名地区为例,融合地球化学、地层岩性、地质构造、地形地貌等数据,基于PSPNet、SegNet、UNet三种语义分割深度学习模型进行预测,结果表明PSPNet模型在预测精度方面优于SegNet及UNet模型,并预测出了55处铁矿、金矿、铜矿、高岭土矿找矿靶区,其中79.7%的已查明矿点位于预测靶区内,表明该方法在找矿靶区预测中具有较高的可行性,可以用于找矿勘查并圈定靶区。     

卷积神经网络和视觉注意力语义分割模型在高分辨率遥感影像分类中的性能分析

随着深度学习语义分割的快速发展,基于计算机视觉语义分割模型的高分辨率遥感影像分类方法也大量涌现。为系统定量地研究经典的和先进的视觉语义分割模型在遥感影像分类中的性能,在总结深度学习语义分割进展的基础上,选择9种基于卷积神经网络(CNN)和视觉注意力的语义分割算法,对米级和厘米级2个尺度的遥感数据集进行分析研究。在模型构建上基于计算机视觉通用的语义分割框架,训练时采用红绿蓝3波段遥感图像并基于ImageNet预训练权重进行迁移学习训练。研究结果表明：通用的语义分割模型通过常规训练设置进行训练能取得较好的遥感影像分类效果,部分地物的交并比(IoU)可以达到90%以上;基于视觉注意力的遥感影像分类模型的精度普遍高于基于CNN的模型,且MaskFormer能更有效地提取离散的地物信息;不同类别的精度最高值并不全在总体最优模型中,部分会存在于次优模型中;类似的地物在更高分辨率遥感数据集中可以获得更高的精度。     

基于图的语义室内导航模型构建研究

室内空间模型是室内导航的基础和关键所在,针对当前多数室内空间模型在建模过程中只考虑部分导航相关的影响因素,适用范围有限这一问题,结合室内导航特点,综合考虑用户室内移动特征、几何和语义信息表达、路径规划效率3个方面的建模影响因素,提出一种基于图的语义室内导航模型。基于图论的方法构建室内导航概念模型,然后在概念模型的基础上提出具体的几何图模型构建方法和语义信息表达方式,设计图模型中节点和边的数据结构,最后研究将该模型用于不同情景下室内路径规划的具体流程。