平行坐标轴动态排列的地理空间多维数据可视分析

目的 平行坐标是经典的多维数据可视化方法,但在用于地理空间多维数据分析时,往往存在空间位置信息缺失和空间关联分析不确定等问题。对此,本文设计了一种有效关联平行坐标和地图的地理空间多维数据可视分析方法。方法 根据多维属性信息对地理空间位置进行聚类分析,引入Voronoi图和颜色明暗映射对地理空间各类区域进行显著标识,利用平行坐标呈现地理空间多维属性信息,引入互信息度量地理空间聚类与属性类别的相关性,动态地确定平行坐标轴排列顺序,进一步计算属性轴与地图之间数据线的绑定位置,对数据线的布局进行优化处理,降低地图与平行坐标系间数据线分布的紊乱程度。结果 有效集成上述可视化设计及数据分析方法,设计与实现一种基于平行坐标轴动态排列的地理空间多维数据可视化分析系统,提供便捷的用户交互模式,通过2组具有明显地理空间多维属性特征的数据进行测试,验证了本文可视分析方法的有效性和实用性。结论 本文提出的可视分析方法和工具可以帮助用户快速分析地理空间多维属性存在的空间分布特征及其关联模式,为地理空间多维数据的探索提供了有效手段。     

鸟类卫星跟踪数据可视分析方法研究—以朱鹮为例

目的 鸟类跟踪技术的成熟发展使得鸟类专家可以轻松获得大量鸟类运动数据。然而，数据规模的增加使得传统方法难以有效完成数据检索和分析。研究如何辅助专家有效地分析这些数据，挖掘其中的有用信息，具有很强的实用价值。本文基于国家Ⅰ级重点保护物种朱鹮的卫星跟踪数据，从鸟类专家对数据分析的需求出发，提出了一种运动轨迹的可视分析方法。方法 基于二维地图进行多视图协同展示的交互布局方式，以及聚类分析方法等对朱鹮运动轨迹进行可视分析，挖掘朱鹮的生活状态和习性。在以上工作的基础上，设计实现了一个朱鹮运动轨迹可视分析系统。结果 本文提出的可视分析方法，允许用户从时空维度和时期（繁殖期、游荡期、越冬期）、状态（夜宿、觅食）等具有生态学意义的维度观察朱鹮运动轨迹，对运动数据进行统计分析，了解朱鹮运动行为。与现有朱鹮数据分析方法相比，本文提出的可视分析方法能够同时从多个不同维度对运动数据进行分析，针对朱鹮的生活状态和生活习性进行更深入的分析挖掘。结论 案例分析表明，基于本文提出的方法，鸟类专家可以从多个角度对朱鹮运动轨迹数据进行综合分析，达到对鸟类习性和状态进行研究挖掘的目的，并能够为其他鸟类跟踪数据分析工作提供思路和方法。     

可视数据清洗综述

目的 数据清洗是一个长期存在并困扰人们的问题,随着可视化技术的发展,可视数据清洗必将成为数据清洗的重要方法之一.阐述数据的主要质量问题和可视数据清洗的过程,回顾可视数据清洗的研究现状(包括数据质量问题的来源、分类以及可视数据清洗方法),并根据已有文献总结可视数据清洗面临的主要挑战和机遇.方法 由于数据清洗的方法和策略与具体的数据质量问题相关,因此本文以不同的数据质量问题为线索来归纳和评述可视数据清洗的方法和策略.结果 根据数据质量问题的不同,将可视清洗方法归纳为直接可视清洗、可视缺失数据、可视不确定数据、可视数据转换和数据清洗资源共享等,并依据不同的数据质量问题归纳总结出相应问题所面临的挑战和可进一步研究的方向.结论 对可视数据清洗的归纳、总结和展望,并指出在数据清洗领域中可视数据清洗将会是未来最有前景的研究方向之一.     

城市道路交通数据可视分析综述

目的 交通是困扰现代大都市的世界性难题.近年来,可视分析技术在分析和利用交通大数据中扮演了越来越重要的角色,成为一项重要的智能交通技术.本文将全面回顾自信息可视化和可视分析兴起以来城市交通数据可视分析领域的研究现状.方法 从道路交通流量分析和其他交通问题分析两个方面,按照数据的类型及问题的分类探讨交通领域的可视化技术和可视分析系统,简单回顾近年来出现的研究新趋势.结果 早期研究注重对道路流量的可视化展示方案,主要方法有箭头图、马赛克图和轨迹墙等.随着可视分析手段的丰富,对城市道路交通流量的分析层次上升到交通事件层面,但是交通事件的定义仅局限于交通拥堵.应用可视分析的其他交通问题领域包括公共交通、交通事故和人群出行行为等.近年出现了挖掘和利用交通轨迹或交通事件的社会属性或称环境上下文信息的研究新趋势.结论 从对交通流量的可视化到交通事件的可视分析,从面向道路交通状况到与交通相关的其他社会性问题,从单纯反映路况的交通数据到富含社会性语义的多源数据,从传统的PC端可视化和交互范式到新型的可视化展示介质,交通数据可视化领域的研究在深度和广度上都得到大大拓展,未来该领域的研究趋势也体现于其中.     

降维空间视觉认知增强的多维时变数据可视分析方法

针对多维时序数据可视分析过程中降维算法表现出的局限性,提出一种降维空间视觉认知增强的多维时序数据可视分析方法.在多维标度算法的基础上,通过正交变换使不同时间步投影点的偏移最小化,帮助用户对感兴趣的时间模式进行有效的视觉认知及追踪;为避免投影点之间的相互遮挡,引入六边形对投影空间进行划分,增强用户对降维空间特征的视觉认知和交互;进而引入层次聚类方法对投影点进行聚类分析,帮助用户快速感知多维数据之间的关联关系;最后设计面向聚类特征时序演变的分组动画策略,突出相邻时间聚类特征的演化特点和时序模式.集成上述可视化方法,开发面向多维时序数据可视分析原型系统,通过经济统计数据、空气质量监测数据的实例分析,进一步验证该系统的有效性和实用性.     

面向火电控制系统辨识的循环神经网络可视分析

针对火电控制过程产生的数据连续性强、复杂度高,循环神经网络模型行为与实际控制过程难以建立语义关联,不能直观地进行模型的调试、优化和语义上的分析等问题,将可视分析技术引入面向系统辨识的循环神经网络建模过程中,提出可视分析系统iaRNN.首先,通过可视化隐藏单元激活值分布与覆盖范围设计模型评估组合视图,支持内外结合多方面评价模型性能;然后,从时序关系演变和敏感性分析等角度设计可视化视图,以支持探索模型对控制参数的响应行为;最后,基于序列符号化和聚类分析提出了一种用于探索强时序依赖的实值时间序列与隐藏单元关联模式的可视化方法.使用电厂真实数据进行案例分析,验证了iaRNN在辅助用户理解模型工作机理和诊断模型缺陷方面的有效性.     

MAP-Vis:基于MAP模型的时空点状大数据可视化方案

目的 对于大数据挖掘，可视分析是一种非常重要的研究手段，有助于快速、直观地理解分析大数据蕴含的价值信息。但因其海量、时空、高维等特征，大数据可视化存在内存消耗大、渲染延迟高、可视效果差等问题。针对上述问题，以海量时空点数据为例，采用预处理可视化方案，设计并实现了一套高可扩展的分布式可视分析框架。方法 借鉴瓦片金字塔模型提出一种多维度聚合金字塔模型（MAP），将瓦片金字塔的2D空间层级聚合扩展到时间/空间/属性多维度，同时支持时间、空间、属性的多维层级聚合。进而以Spark集群作为并行预处理工具，以HBase分布式数据库持久化存储MAP模型数据，实现了一套开源的分布式可视化框架（MAP-Vis）。结果 以纽约出租车数据集为例，本研究实验证明能够支持时间/空间/属性多尺度、多维度联动的交互式可视化，同时具有高可扩展的预处理能力和存储能力。结论 在分布式处理能力支持下，系统能实现亚秒级的查询响应，达到良好的交互式可视化效果，证明MAP-Vis是一种有效的大数据交互式可视化方案。     

城市交通事故的局部相关性可视分析方法

交通事故数据蕴含有交通事故规律,如交通事故与天气、时间、道路等因素的关 联规律,值得深入挖掘。虽然天气、时间、道路等因素对交通事故均有影响,但对不同区域交 通事故的影响不尽相同,即具有局部相关性。挖掘局部相关性能更好地揭示这些因素与交通事 故之间的相关性。为此提出一套分析挖掘交通事故数据中所蕴含的局部相关性的方法。首先基 于交通事故数据提取事故多发路段,每个事故多发路段包含有位置、时间以及相关的交通事故 信息;然后提出一套聚类支持的局部相关性可视分析方法分析事故多发路段：①以待分析因素 直方图(如天气直方图、时间直方图)刻画事故多发路段;②基于直方图相似性对事故多发路段 进行聚类分析;③在多关联视图支持的交互环境中进一步观察、分析聚类结果以挖掘待分析因 素与交通事故之间的局部相关性。通过分析安徽省合肥市 2015-2018 年交通事故接警数据,取 得了一些有意义的分析结果,验证了该方法的有效性。     

面向公交站点优化的多源数据可视分析方法

“公交+共享单车”模式已经成为城市出行的主要方式,公交站点设置的合理与否直接影响公交服务水平,如何评估站点设置的合理性及如何优化,成为城市规划的研究热点.共享单车产生的GPS数据可以反映人口分布、出行模式、城市热点等规律.基于上述背景,本文探索了一种通过共享单车、城市兴趣点等多源数据,帮助交通规划人员理解站点周围环境并对站点进行优化的解决思路,设计了一种可缩放的蜂窝状视图来显示兴趣点的空间分布,设计了一种径向布局的分层雷达图来分析人流的时间序列信息,提出了基于多源数据集的公交站点优化可视分析模型,并在此基础上设计实现了一个可视分析系统VisB4B.该系统以上海市公交线路站点数据、城市兴趣点数据、摩拜共享单车数据等为数据源,通过公交线路变化实例评估、交通可视化领域和交通规划领域专家评估等方法,验证了系统的有效性与可用性.     

多尺度条形池化与通道注意力的图像语义分割

目的 针对自然场景下图像语义分割易受物体自身形状多样性、距离和光照等因素影响的问题,本文提出一种新的基于条形池化与通道注意力机制的双分支语义分割网络(strip pooling and channel attention net,SPCANet)。方法 SPCANet从空间与内容两方面对图像特征进行抽取。首先,空间感知子网引入1维膨胀卷积与多尺度思想对条形池化技术进行优化改进,进一步在编码阶段增大水平与竖直方向上的感受野;其次,为了提升模型的内容感知能力,将在ImageNet数据集上预训练好的VGG16(Visual Geometry Group 16-layer network)作为内容感知子网,以辅助空间感知子网优化语义分割的嵌入特征,改善空间感知子网造成的图像细节信息缺失问题。此外,使用二阶通道注意力进一步优化网络中间层与高层的特征选择,并在一定程度上缓解光照产生的色差对分割结果的影响。结果 使用Cityscapes作为实验数据,将本文方法与其他基于深度神经网络的分割方法进行对比,并从可视化效果和评测指标两方面进行分析。SPCANet在目标分割指标mIoU(mean intersection over union)上提升了1.2%。结论 提出的双分支语义分割网络利用改进的条形池化技术、内容感知辅助网络和通道注意力机制对图像语义分割进行优化,对实验结果的提升起到了积极作用。     

Time and Location Aware Points of Interest Recommendation in Location-Based Social Networks

The wide spread of location-based social networks brings about a huge volume of user check-in data, which facilitates the recommendation of points of interest (POIs). Recent advances on distributed representation shed light on learning low dimensional dense vectors to alleviate the data sparsity problem. Current studies on representation learning for POI recommendation embed both users and POIs in a common latent space, and users’ preference is inferred based on the distance/similarity between a user and a POI. Such an approach is not in accordance with the semantics of users and POIs as they are inherently different objects. In this paper, we present a novel translation-based, time and location aware (TransTL) representation, which models the spatial and temporal information as a relationship connecting users and POIs. Our model generalizes the recent advances in knowledge graph embedding. The basic idea is that the embedding of a <time, location> pair corresponds to a translation from embeddings of users to POIs. Since the POI embedding should be close to the user embedding plus the relationship vector, the recommendation can be performed by selecting the top-k POIs similar to the translated POI, which are all of the same type of objects. We conduct extensive experiments on two real-world datasets. The results demonstrate that our TransTL model achieves the state-of-the-art performance. It is also much more robust to data sparsity than the baselines.     

Assessing the influence of point-of-interest features on the classification of place categories

Points of interest (POIs) digitally represent real-world amenities as point locations. POI categories (e.g. restaurant, hotel, museum etc.) play a prominent role in several location-based applications such as social media, navigation, recommender systems, geographic information retrieval tools, and travel-related services. The majority of user queries in these applications center around POI categories. For instance, people often search for the closest pub or the best value-for-money hotel in an area. To provide valid answers to such queries, accurate and consistent information on POI categories is an essential requirement. Nevertheless, category-based annotations of POIs are often missing. The task of annotating unlabeled POIs in terms of their categories — known as POI classification — is commonly achieved by means of machine learning (ML) models, often referred to as classifiers. Central to this task is the extraction of known features from pre-labeled POIs in order to train the classifiers and, then, use the trained models to categorize unlabeled POIs. However, the set of features used in this process can heavily influence the classification results. Research on defining the influence of different features on the categorization of POIs is currently lacking. This paper contributes a study of feature importance for the classification of unlabeled POIs into categories. We define five feature sets that address operation based, review-based, topic-based, neighborhood-based, and visual attributes of POIs. Contrary to existing studies that predominantly use multi-class classification approaches, and in order to assess and rank the influence of POI features on the categorization task, we propose both a multi-class and a binary classification approach. These, respectively, predict the place category among a specified set of POI categories, or indicate whether a POI belongs to a certain category. Using POI data from Amsterdam and Athens to implement and evaluate our study approach, we show that operation based features, such as opening or visiting hours throughout the day, are the most important place category predictors. Moreover, we demonstrate that the use of feature combinations, as opposed to the use of individual features, improves the classification performance by an average of 15%, in terms of F1-score.     

基于时空循环神经网络的下一个兴趣点推荐方法

下一个兴趣点推荐已经成为基于位置的社交网络(location-based social networks,LBSNs)中一个重要任务。现有的模型没有深入考虑相邻签到兴趣点之间的转移时空信息,无法对用户访问下一个兴趣点的长短时间偏好和远近距离偏好进行有效建模。本文通过对循环神经网络(recurrent neural network, RNN)进行扩展,提出一个新的基于会话的时空循环神经网络模型(sesson-based spatial-temporal recurrent neural network, SST-RNN)用于下一个兴趣点推荐。该模型通过设置时间转移矩阵和空间转移矩阵分别对用户的时间和空间偏好信息进行建模,综合考虑连续签到兴趣点的序列信息、时空信息以及用户偏好进行下一个兴趣点推荐。通过在2个真实公开的数据集上进行实验,结果显示本文提出的SST-RNN模型的推荐效果比主流的推荐模型有显著提升。在Foursquare和CA数据集上,ACC@5评价指标分别提升了36.38%和13.81%,MAP评价指标分别提升了30.72%和17.26%。     

Place niche and its regional variability: Measuring spatial context patterns for points of interest with representation learning

In the built environment, places such as retail outlets and public sites are embedded in the spatial context formed by neighboring places. We define the sets of these symbiotic places in the proximity of a focal place as the place's “place niche”, which conceptually represents the features of the local environment. While current literature has focused on pairwise spatial colocation patterns, we represent the niche as an integrated feature for each type of place, and quantify the niches' variation across cities. Here, with point of interest (POI) data as an approximation of places in cities, we propose representation learning models to explore place niche patterns. The models generate two main outputs: first, distributed representations for place niche by POI category (e.g. Restaurant, Museum, Park) in a latent vector space, where close vectors represent similar niches; and second, conditional probabilities of POI appearance of each place type in the proximity of a focal POI. With a case study using Yelp data in four U.S. cities, we reveal spatial context patterns and find that some POI categories have more unique surroundings than others. We also demonstrate that niche patterns are strong indicators of the function of POI categories in Phoenix and Las Vegas, but not in Pittsburgh and Cleveland. Moreover, we find that niche patterns of more commercialized categories tend to have less regional variation than others, and the city-level niche-pattern changes for POI categories are generally similar only between certain city pairs. By exploring patterns for place niche, we not only produce geographical knowledge for business location choice and urban policymaking, but also demonstrate the potential and limitations of using spatial context patterns for GIScience tasks such as information retrieval and place recommendation.     

Point of interest mining with proper semantic annotation

Mining geo-tagged social photo media has received large amounts of attention from researchers recently. Points of interest (POI) mining from a collection of geo-tagged photos is one of these problems. POI mining refers to the processes of pattern recognition (namely clustering), extraction and semantic annotation. However, based on unsupervised clustering methods, many POIs might not be mined. Additionally, there is a great challenge for the proper semantic annotation to data clusters after clustering. In practice, there are many applications which require the accuracy of semantic annotation and high quality of pattern recognition such as POI recommendation. In this paper, we study POI mining from a collection of geo-tagged photos in combination with proper semantic annotation by using additional POI information from high coverage external POI databases. We propose a novel POI mining framework by using two-level clustering, random walk and constrained clustering. In random walk clustering step, we separate a large-scale collection of geo-tagged photos into many clusters. In the constrained clustering step, we continue to divide the clusters that include many POIs into many sub-clusters, where the geo-tagged photos in a sub-cluster associate with a particular POI. Experimental results on two datasets of geo-tagged Flickr photos of two cities in California, USA have shown that the proposed method substantially outperforms existing approaches that are adapted to handle the problem.     

Risky behaviour at traffic signals: a traffic engineer's view

Abstract

Road accidents are reasonably predictable from a knowledge of traffic behaviour, although individual accident involvement is far less predictable. How do individuals perceive the relationship between their own involvement and objective accident risk? This question is explored in relation to Danish case studies of drivers' behaviour at traffic lights and different categories of pedestrians' ‘jay-walking’. On this evidence, it seems unlikely that road users perceive accidents as random negative outcomes of everyday risk taking. Thus it also appears improbable that overall traffic accident risk in any society is a major function of deliberate risk taking by its individual road users.     

Reverse direction-based surrounder queries for mobile recommendations

This paper proposes a new spatial query called a reverse direction-based surrounder (RDBS) query, which retrieves a user who is seeing a point of interest (POI) as one of their direction-based surrounders (DBSs). According to a user, one POI can be dominated by a second POI if the POIs are directionally close and the first POI is farther from the user than the second is. Two POIs are directionally close if their included angle with respect to the user is smaller than an angular threshold ??. If a POI cannot be dominated by another POI, it is a DBS of the user. We also propose an extended query called competitor RDBS query. POIs that share the same RDBSs with another POI are defined as competitors of that POI. We design algorithms to answer the RDBS queries and competitor queries. The experimental results show that the proposed algorithms can answer the queries efficiently.     

融合全局和局部特征的下一个兴趣点推荐方法

随着海量移动数据的积累,下一个兴趣点推荐已成为基于位置的社交网络中的一项重要任务.目前,主流方法倾向于从用户近期的签到序列中捕捉局部动态偏好,但忽略了历史移动数据蕴含的全局静态信息,从而阻碍了对用户偏好的进一步挖掘,影响了推荐的准确性.为此,提出一种基于全局和局部特征融合的下一个兴趣点推荐方法.该方法利用签到序列中的顺序依赖和全局静态信息中用户与兴趣点之间、连续签到之间隐藏的关联关系建模用户移动行为.首先,引入两类全局静态信息,即User-POI关联路径和POI-POI关联路径,学习用户的全局静态偏好和连续签到之间的全局依赖关系.具体地,利用交互数据以及地理信息构建异构信息网络,设计关联关系表示学习方法,利用相关度引导的路径采样策略以及层级注意力机制获取全局静态特征.然后,基于两类全局静态特征更新签到序列中的兴趣点表示,并采用位置与时间间隔感知的自注意力机制来捕捉用户签到序列中签到之间的局部顺序依赖,进而评估用户访问兴趣点概率,实现下一个兴趣点推荐.最后,在两个真实数据集上进行了实验比较与分析,验证了所提方法能够有效提升下一个兴趣点推荐的准确性.此外,案例分析表明,建模显式路径有助于提...     

Exploring point-of-interest data from social media for artificial surface validation with decision trees

Artificial surfaces represent one of the key land cover types, and validation is an indispensable component of land cover mapping that ensures data quality. Traditionally, validation has been carried out by confronting the produced land cover map with reference data, which is collected through field surveys or image interpretation. However, this approach has limitations, including high costs in terms of money and time. Recently, geo-tagged photos from social media have been used as reference data. This procedure has lower costs, but the process of interpreting geo-tagged photos is still time-consuming. In fact, social media point of interest (POI) data, including geo-tagged photos, may contain useful textual information for land cover validation. However, this kind of special textual data has seldom been analysed or used to support land cover validation. This paper examines the potential of textual information from social media POIs as a new reference source to assist in artificial surface validation without photo recognition and proposes a validation framework using modified decision trees. First, POI datasets are classified semantically to divide POIs into the standard taxonomy of land cover maps. Then, a decision tree model is built and trained to classify POIs automatically. To eliminate the effects of spatial heterogeneity on POI classification, the shortest distances between each POI and both roads and villages serve as two factors in the modified decision tree model. Finally, a data transformation based on a majority vote algorithm is then performed to convert the classified points into raster form for the purposes of applying confusion matrix methods to the land cover map. Using Beijing as a study area, social media POIs from Sina Weibo were collected to validate artificial surfaces in GlobeLand30 in 2010. A classification accuracy of 80.68% was achieved through our modified decision tree method. Compared with a classification method without spatial heterogeneity, the accuracy is 10% greater. This result indicates that our modified decision tree method displays considerable skill in classifying POIs with high spatial heterogeneity. In addition, a high validation accuracy of 92.76% was achieved, which is relatively close to the official result of 86.7%. These preliminary results indicate that social media POI datasets are valuable ancillary data for land cover validation, and our proposed validation framework provides opportunities for land cover validation with low costs in terms of money and time.