MARC: a robust method for multiple-aspect trajectory classification via space,time, and semantic embeddings

ABSTRACT

The increasing popularity of Location-Based Social Networks (LBSNs) and the semantic enrichment of mobility data in several contexts in the last years has led to the generation of large volumes of trajectory data. In contrast to GPS-based trajectories, LBSN and context-aware trajectories are more complex data, having several semantic textual dimensions besides space and time, which may reveal interesting mobility patterns. For instance, people may visit different places or perform different activities depending on the weather conditions. These new semantically rich data, known as multiple-aspect trajectories, pose new challenges in trajectory classification, which is the problem that we address in this paper. Existing methods for trajectory classification cannot deal with the complexity of heterogeneous data dimensions or the sequential aspect that characterizes movement. In this paper we propose MARC, an approach based on attribute embedding and Recurrent Neural Networks (RNNs) for classifying multiple-aspect trajectories, that tackles all trajectory properties: space, time, semantics, and sequence. We highlight that MARC exhibits good performance especially when trajectories are described by several textual/categorical attributes. Experiments performed over four publicly available datasets considering the Trajectory-User Linking (TUL) problem show that MARC outperformed all competitors, with respect to accuracy, precision, recall, and F1-score.     

Identifying primary public transit corridors using multi-source big transit data

ABSTRACT

Effective public transit planning needs to address realistic travel demands, which can be illustrated by corridors across major residential areas and activity centers. It is vital to identify public transit corridors that contain the most significant transit travel demand patterns. We propose a two-stage approach to discover primary public transit corridors at high spatio-temporal resolutions using massive real-world smart card and bus trajectory data, which manifest rich transit demand patterns over space and time. The first stage was to reconstruct chained trips for individual passengers using multi-source massive public transit data. In the second stage, a shared-flow clustering algorithm was developed to identify public transit corridors based on reconstructed individual transit trips. The proposed approach was evaluated using transit data collected in Shenzhen, China. Experimental results demonstrated that the proposed approach is a practical tool for extracting time-varying corridors for many potential applications, such as transit planning and management.     

基于手机数据的北京市城市与近郊交互模式挖掘

在城镇化进程中,城市与近郊之间通过职住、货运、游憩等活动产生越来越紧密的交互联系,对于这些交互联系的准确识别和定量刻画,是理解城乡空间关系的重要手段,也能为城市的资源有效配置与合理规划提供重要的现状信息。本文通过对全北京在一日之内的手机信令数据所反映的人群移动轨迹的深入分析,融合城市的POI信息形成顾及人类活动时空信息的空间交互类型推断。以北京市为例,对城市中心与近郊之间远距离的强交互进行定性、定量和定位的探索。本文发现了北京市多尺度下空间交互模式和距离衰减规律,判断了城乡异常交互类型,对比了城乡之间和城市内部的交互模式的异同,以及基于交互类型视角提取了城乡异常交互的空间特征。研究认为,基于手机信令数据,利用停留点提取和高斯核密度估计的空间交互类型推断有效地发现了北京市周末的远距离出行类型特点,提取了其空间交互强度和空间特征,揭示了基于人类活动的北京市周末城乡交互模式。     

点模式条件下的犯罪嫌疑人时空同现模式挖掘与分析

现有时空同现模式挖掘方法因其在空间和时间频繁阈值等参数值的设定上存在困难且缺乏客观依据的问题而难以被应用到犯罪地理研究中。为此,本文通过引入时空状态同现模式和最小时空参与率等概念对现有挖掘方法进行了重新建模,并结合广义Grubbs异常值检验提出了一种点模式分布下的犯罪嫌疑人时空同现模式挖掘框架。基于该框架对中国某省部分犯罪嫌疑人的真实移动轨迹数据的实验分析结果表明,本文所提出的方法能够有效地挖掘出嫌疑人间显著的时空同现模式,且这些模式的时空分布特征不仅与犯罪活动易发生在非农业生产区这一共识基本相符,还与日常活动理论的基本观点相适应。本文拓展了时空同现模式挖掘在犯罪地理研究中的应用,研究成果对公安机关等执法部门在重点监控某些犯罪嫌疑人以及合理分配和部署警力资源方面具有重要意义。     

基于变化轨迹分析方法的生态用地流失空间关联研究

针对现有研究割裂了生态用地流失这一基本变化过程的不足,本文基于变化轨迹分析方法,从过程完整性角度探求了京津冀城市群地区生态用地流失的空间关联特征。结果表明：① 京津冀城市群地区土地利用变化主要表现为林地、草地、水域和耕地的流失,流失面积的40%转为人工表面;② 林地、草地和水域流失的空间自相关性随空间尺度增大而增强,7 km×7 km空间尺度上3种生态用地流失空间正相关性较强,且随距离阈值增加而降低;③ 距离阈值为10 km时,林地、草地流失高发区集中分布在京津冀西北部地区,水域流失高发区集中分布在东部渤海湾附近,生态环境保护应从京津冀协同发展角度,打破区域发展不均衡,促进京津冀城市群全面发展。     

Integration of nighttime light remote sensing images and taxi GPS tracking data for population surface enhancement

The population distribution grid at fine scales better reflects the distribution of residents and plays an important role in investigating urban systems. The recent years have witnessed a growing trend of applying the nighttime light data to the estimation of population at micro levels. However, using the nighttime light data alone to estimate population may cause the overestimation problem due to excessively high light radiance in specific types of areas such as commercial zones and transportation hubs. In dealing with this issue, this study used taxi trajectory data that delineate people’s movements, and explored the utility of integrating the nighttime light and taxi trajectory data in the estimation of population in Shanghai at the spatial resolution of 500 m. First, the initial population distribution grid was generated based on the NPP-VIIRS nighttime light data. Then, a calibration grid was created with taxi trajectory data, whereby the initial population grid was optimized. The accuracy of the resultant population grid was assessed by comparing it with the refined survey data. The result indicates that the final population distribution grid performed better than the initial population grid, which reflects the effectiveness of the proposed calibration process.     

城市创意产业空间动态集聚演化的计算与可视优化方法

基于人文地理视角下的城市创意产业图像可视化分析对城市深层次空间综合和区域创新发展具有重大意义。但Swarm群智能动态时空建模难以满足创意产业空间集聚的可视化发展。本文研究目标是,从城市区域创意产业空间聚类影响因素指标出发,创新性地提出区域空间动态集聚轨迹算法（Density-Based Interest Spatial Clustering of Path,DBICP）,并与计算机浏览器共建聚类可视化图像,为城市管理提供决策依据。首先,根据影响因素指标体系,利用2014—2018年空间卡口流量数据和产业指标数据进行预处理,构建空间标准聚类算法DBSCAN。然后,对其进行聚类密度分级优化形成全新DBICP算法并得出初步轨迹图像。最后,通过源码转译实现了浏览器界面下空间动态集聚轨迹图像的输出。结果表明：以上海市为例,普陀区、浦东新区、徐汇地区的创意产业空间分布形成了3种不同的聚类模式,并相应提出了分摊、均布、虹吸的管控策略。此方法克服了传统图像的聚类分级和轨迹测量的缺失,可以有效地从指标数据中发现图像轨迹聚类信息,体现了地理信息科学和人文社会学科的交叉融合。也为大数据动态图像的集聚方法提供了全新视角和借鉴价值。     

基于粒子滤波的行车轨迹路网匹配方法

行车轨迹是一种时间序列的地理空间位置采样数据,而传统的轨迹—路网匹配方法主要以全局或局部寻优的方式建立轨迹—路网匹配关系,影响了时空场景中数据的匹配计算过程的相对独立性。针对这个问题,本文基于粒子滤波（Particle Filter,PF）原理建立行车轨迹与道路网络之间的匹配关系。首先,沿轨迹中车辆运动方向在道路网络中搜索邻近道路节点,在与道路节点拓扑邻接的道路弧段上初始化随机生成粒子,根据轨迹中车辆运动模型将粒子沿所在道路弧段移动;然后,基于PF原理计算各时刻粒子运动状态及与行车轨迹采样点之间的距离误差,根据高斯概率密度函数计算粒子权重并利用随机重采样方法进行粒子重采样,迭代更新粒子运动状态;最后,计算与搜索到的道路节点拓扑邻接的每条道路弧段中累计粒子权重,通过各道路弧段累计权重计算轨迹—路网匹配关系。以行车轨迹进行实验表明,利用本文方法可以通过粒子时空变化反映采样点的移动,行车轨迹—路网匹配结果的正确率大于85%,能够实现行车轨迹和路网的准确匹配。     

基于交通轨迹数据的三维动态噪声地图

噪声信息具有空间传播和随距离衰减变化的特征,采用三维动态可视化形式表达噪声地图可以体现该特征。本文针对噪声的空间分布与强度变化提出一种噪声地图表达的方法,基于Bertin符号参量分析,以具有高度可变的方柱并配以深浅变化的颜色作为噪声符号,动态传递噪声信息。为进行多尺度地图展示,在不同地图等级下设有相应细节层次的符号尺寸和定位排列方式。噪声地图以Web端Mapbox为展示平台,基于交通噪声模型和GPS轨迹数据,对上海黄浦区某区域一时间段内的噪声情况进行模拟表达,实现噪声数据的立体动态化显示。三维动态的表达扩展了噪声数据的表现维度,多维度、多参量的立体动态符号不仅可准确刻画噪声的分布,而且从视觉观感上提高了受众的兴趣度和专注度,这为研究噪声的热点分布、传递趋势等空间规律提供了可视化参考。     

粗精匹配结合的矢量道路辅助惯性导航算法

针对无源环境下无法采用卫星导航定位方式对惯性导航系统的累积误差进行修正的问题,提出一种采用高精度的矢量道路数据进行粗精匹配的导航校正算法。该方法首先通过分析惯导轨迹的特征标示点以及外接矩形,剔除明显的误匹配道路和冗余道路,获取待匹配道路集合;进而,结合ICCP算法具有匹配精度较高,匹配结果较稳定的优点,完成惯导轨迹位置误差的补偿和校正;最后,根据匹配方差和历史匹配轨迹对匹配结果的准确性进行分析和判断。仿真实验结果表明,该算法能够提高惯性导航定位误差的校正精度,减少在复杂道路交叉口等情况的误匹配。