Unveiling movement uncertainty for robust trajectory similarity analysis

Trajectory data analysis and mining require distance and similarity measures, and the quality of their results is directly related to those measures. Several similarity measures originally proposed for time-series were adapted to work with trajectory data, but these approaches were developed for well-behaved data that usually do not have the uncertainty and heterogeneity introduced by the sampling process to obtain trajectories. More recently, similarity measures were proposed specifically for trajectory data, but they rely on simplistic movement uncertainty representations, such as linear interpolation. In this article, we propose a new distance function, and a new similarity measure that uses an elliptical representation of trajectories, being more robust to the movement uncertainty caused by the sampling rate and the heterogeneity of this kind of data. Experiments using real data show that our proposal is more accurate and robust than related work.     

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.     

Vehicle trajectory modelling with consideration of distant neighbouring dependencies for destination prediction

Vehicle trajectory modelling is an essential foundation for urban intelligent services. In this paper, a novel method, Distant Neighbouring Dependencies (DND) model, has been proposed to transform vehicle trajectories into fixed-length vectors which are then applied to predict the final destination. This paper defines the problem of neighbouring and distant dependencies for the first time, and then puts forward a way to learn and memorize these two kinds of dependencies. Next, a destination prediction model is given based on the DND model. Finally, the proposed method is tested on real taxi trajectory datasets. Results show that our method can capture neighbouring and distant dependencies, and achieves a mean error of 1.08 km, which outperforms other existing models in destination prediction significantly.     

Attribute trajectory analysis: a framework to analyse attribute changes using trajectory analysis techniques

Trajectory analysis has attracted growing attention in the research field of geography. Beyond traditional moving object trajectories, another type of trajectory exists in which the coordinates are object attributes rather than geographical coordinates. In this paper, a framework to analyse these so-called attribute trajectories is proposed that uses four techniques typically employed in the analysis of moving object trajectories: the Reeb graph, the similarity matrix, the convoy and the mega-convoy. The Reeb graph provides the ability to visualise the temporal dynamics of attribute similarities. The similarity matrix is a supplement of the Reeb graph whose purpose is to visualise the pairwise similarities among the attributes. Moreover, the similarity matrix forms a basis for clustering. The convoy highlights objects whose attributes remain similar for a sufficiently long period. The mega-convoy reduces the number of convoys and reveals their evolutionary histories by merging overlapping convoys. A small real-world meteorological dataset is used as an example to illustrate the attribute trajectory analysis framework and the techniques. This paper aims to form a starting point for applying trajectory analysis techniques in many research fields.     

Assessing similarity matching for possible integration of feature classifications of geospatial data from official and informal sources

One difficulty in integrating geospatial data sets from different sources is variation in feature classification and semantic content of the data. One step towards achieving beneficial semantic interoperability is to assess the semantic similarity among objects that are categorised within data sets. This article focuses on measuring semantic and structural similarities between categories of formal data, such as Ordnance Survey (OS) cartographic data, and volunteered geographic information (VGI), such as that sourced from OpenStreetMap (OSM), with the intention of assessing possible integration. The model involves ‘tokenisation’ to search for common roots of words, and the feature classifications have been modelled as an XML schema labelled rooted tree for hierarchical analysis. The semantic similarity was measured using the WordNet::Similarity package, while the structural similarities between sub-trees of the source and target schemas have also been considered. Along with dictionary and structural matching, the data type of the category itself is a comparison variable. The overall similarity is based on a weighted combination of these three measures. The results reveal that the use of a generic similarity matching system leads to poor agreement between the semantics of OS and OSM data sets. It is concluded that a more rigorous peer-to-peer assessment of VGI data, increasing numbers and transparency of contributors, the initiation of more programs of quality testing and the development of more directed ontologies can improve spatial data integration.     

Constrained free space diagrams: a tool for trajectory analysis

Time plays an important role in the analysis of moving object data. For many applications it is not sufficient to only compare objects at exactly the same times, or to consider only the geometry of their trajectories. We show how to leverage between these two approaches by extending a tool from curve analysis, namely the free space diagram. Our approach also allows us to take further attributes of the objects like speed or direction into account. We demonstrate the usefulness of the new tool by applying it to the problem of detecting single file movement. A single file is a set of moving entities, which are following each other, one behind the other. Our algorithm is the first one developed for detecting such movement patterns. For this application, we analyse demonstrate the performance of our tool both theoretically experimentally.     

Why did a vehicle stop? A methodology for detection and classification of stops in vehicle trajectories

ABSTRACT

Trajectory data mining is a lively research field in the domain of spatio-temporal data mining. Trajectory pattern mining comprises a set of specific pattern mining methods, which are applied as consecutive steps on a trajectory with the goal to extract and classify re-occurring spatio-temporal patterns. Despite the common nature and frequent usage of such methods by the GIScience community, a methodological approach is missing so far, especially when it comes to the use of machine learning-based classification methods. The current work closes this gap by proposing and evaluating a machine learning-based 3-steps trajectory data mining methodology using the detection and classification of stop points in vehicle trajectories as example. The work describes in detail the applied methodologies with respect to the three mining steps ‘stop detection’, ‘feature extraction’ and ‘classification in traffic-relevant and non-traffic-relevant stops’ and evaluates six machine learning-based classification algorithms using a real-world dataset of 15,498 vehicle trajectories with 5,899 detected stops (thereof 2,032 manually classified). Due to its exemplary nature, the presented methodology is suited to act as blueprint for similar trajectory data mining problems.     

从大众旅游到乡村旅居:乡村区域旅游发展的新趋势——基于元方法的驱动力分析与旅居地假设

在流动性的总体框架中思考中国新兴的乡村旅居现象,界定乡村旅居的基本内涵,借助国外相关实证研究结果中的元数据和主要观点,分析和探讨了乡村旅居的若干属性,结果表明:①乡村旅居以乡村性所提供的核心价值为本源驱动,是乡村旅游发展的阶段性产物,其与各类现代乡村旅游活动共享了相同的3维驱动力空间.②在休闲时间和可支配收入既定的情况...     

Quantitative relationship between channels and bars in a tidal reach of the lower Yangtze River: Implications for river management

Deep-water navigation channels in the tidal reaches of the lower Yangtze River are affected by water and sediment fluxes that produce complex shoals and unstable channel conditions. The Fujiangsha reach is particularly difficult to manage, as it has many braided channels within the tidal fluctuation zone. In this study, hydrologic and topographic data from the Fujiangsha reach from 2012 to 2017 were used to examine the variations in deposition and erosion, flow diversion, shoals, and channel conditions. Since the Three Gorges Dam became operational and water storage was initiated, the Fujiangsha reach has shown an overall tendency toward erosion. Channels deeper than 10 m accounted for 83.7% of the total erosion of the Fujiangsha reach during 2012–2017. Moreover, the dominant channel-forming sediments have gradually changed from suspended sediments to a mixed load of suspended and bed-load sediments. Deposition volumes of these sediments has varied significantly among different channels, but has mainly occurred in the Fubei channel. Furthermore, periodic variations in the Jingjiang point bar have followed a deposition-erosion-deposition pattern, and the downstream Shuangjian shoal mid-channel bar has been scoured and shortened. Approximately 44.0% of the bed load from the upstream Fujiangsha reach is deposited within the 12.5-m deep Fubei channel. The increased erosion and river flow from the Jingjiang point bar and the Shuangjian shoal during the flood season constituted 59.3% and 40.7%, respectively, of the total amount of siltation in the Fubei channel.     

Towards a new methodological framework for the delimitation of rural and urban areas: a case study of Serbia

Abstract: Identification of urban and rural areas has been a widely present topic in the past decades, both in scientific research and in the policy and practice of spatial/regional development and territorial governance. The internationally accepted OECD definition does not produce appropriate results that are able to include the multidimensionality of these territories. In this context, the aim of this paper is the analysis and selection of relevant criteria and indicators of urbanity/rurality that may be significant for the establishment of a methodological framework for identifying urban and rural areas in Serbia. Multivariate analysis (PCA, FA and CA) was used to group local self-government units (LSGU) in Serbia that share similar characteristics. The research resulted in five types of areas which indicate that rural and urban areas in Serbia are very diverse in terms of physiogeographical, socio-economic and functional characteristics. The results of this paper offer a more detailed analysis based on scientifically and empirically selected indicators and can be applied in the practice of spatial and urban planning, and in the adaptation of strategic development documents at the regional or national level.     

Looking for a White Male Effect in Generation Z: Race,Gender, and Political Effects on Environmental Concern and Ambivalence

The “White male effect” has been presented in past literature as a way to explain the tendency for White males to have lower environmental concern and risk perceptions than female and non-White individuals. Recently, research has proposed the “White male effect” may be a “conservative White male effect,” due to findings that political ideology impacts environmental concern. This study used a sample of young college-educated adults from Generation Z to test whether the conservative White male effect is present for environmental concern and ambivalence toward a proenvironmental worldview in this younger generation. Online surveys were distributed to undergraduate students at a large northeastern university in spring of 2016. A total of 1,940 surveys were returned. Results showed a lack of a unique White male, or conservative White male, effect above and beyond differences explained by gender, Whiteness, and political affiliation. The implications of this effect’s absence are discussed.     

作为生态和环境保护手段的空间规划:联邦德国的经验及对中国的启示

联邦德国生态环境保护走过了一条污染-治理-预防的道路, 即由技术性和应激性转为政策性和预防性的环境保护。生态环境保护政策和措施由环保活动家,大企业,学术界,地方及联邦各级有关部门共同制定,并由一个国家级综合的监测体系监督执行。公众不仅有权力了解结果,而且也将参与政策措施的制订和监督。德国空间规划包含欧盟,联邦,州,区域,城镇和城市建设6个层面。空间规划,特别是生态环境规划已成为预防生态环境破坏的重要措施。然而,联邦德国生态环境规划实施也面临个人交通和小企业污染以及环保成本提高造成企业区位劣势所带来的挑战。这些经验教训对中国的生态环境保护目标,政策措施的完善及生态空间规划的制订和监督落实,环境评价,特别是规划本身的环境评价具有借鉴意义。具体包括4个方面: 1)生态环境保护政策实现从提高环保技术手段向预防污染产生转变; 2)保证生态环境保护政策及实施的有效性; 3)把空间规划作为实现区域经济和社会稳定可持续发展的手段,提高生态和环保目标的地位; 4)在规划的技术层面上关注居住,休闲,交通和自然保护区用地的增长。     

以防沙治沙为目标的土地利用方式调整——以内蒙古自治区多伦县为例

风沙现象的发生与作用力(风力)大小和下垫面特征密切相关,土地利用方式反下垫面的特性,从而影响风沙现象的发生和发展。本文以地处半干旱地区的内蒙古多伦县为例,在充分查明原有每个土地利用地块抗风蚀特性,和生态安全性的基础上,根据下列原则:(1)依照大的地貌类型或地貌区域的差异,进行宏观尺度上土地利用格局配置;(2)不再沙化条件下维持生态安全;和(3)充分考虑目前现实状况,进行以防沙治沙为目标的土地利用方式调整。调整结果反映在两县市的1∶250000土地利用图上。另外,对多伦县的土地利用格局也作了初步探讨。     

A comparison of scenario-based hybrid bilevel and multi-objective location-allocation models for earthquake emergency shelters: a case study in the central area of Beijing,China

The accurate location and allocation of disaster emergency shelters are key components of effective urban planning and emergency management. Various models have been developed to solve the location-allocation problem, but gaps remain with regard to model realism and associated applicability. For the available location and allocation models of earthquake emergency shelters, uncertainty with respect to earthquake hazard, population exposure, rate of damage to buildings and the effects of evacuee behavior are often neglected or oversimplified. Moreover, modifying the models can be an alternative means of improving the solution quality when the optimization algorithm has difficulty coping with a complex, high-dimensional problem. This article develops a scenario-based hybrid bilevel model that addresses the concerns related to high-dimensional complexity and provides a higher degree of realism by incorporating the uncertainties of population dynamics and earthquake damage scenarios into location-allocation problems for earthquake emergency shelters. A modified particle swarm optimization algorithm combined with a simulated annealing algorithm was applied to derive solutions using the hybrid bilevel model and a conventional multi-objective model, and the solutions obtained using the two models were then compared. The novel features of the study include the hybrid bilevel model that considers the dynamic number of evacuees and its implementation for earthquake emergency shelter location and allocation. The results show that the solutions significantly differ between daytime and nighttime. When applied to the multi-objective model, the optimization algorithm is time consuming and may only find the local optima and provide suboptimal solutions in the considered scenarios with more evacuees. By contrast, the hybrid bilevel model shows more desirable performance because it significantly reduces the dimensionality of the location-allocation problem based on a two-step-to-reach approach. The proposed hybrid bilevel model is proven to be useful for optimal shelter allocation, and the presented results can be used as a reference for balancing the interests of the government and residents during the planning of shelters in Beijing.