This paper presents a machine learning method for resolving place references in text, i.e. linking character strings in documents to locations on the surface of the Earth. This is a fundamental task in the area of Geo...
详细信息
ISBN:
(纸本)9783642123252
This paper presents a machine learning method for resolving place references in text, i.e. linking character strings in documents to locations on the surface of the Earth. This is a fundamental task in the area of Geographic Information Retrieval, supporting access through geography to large document collections. The proposed method is an instance of stacked learning, in which a first learner based on a Hidden Markov Model is used to annotate place references, and then a second learner implementing a regression through a Support Vector Machine is used to rank the possible disabiguations for the references that were initially annotated. The proposed method was evaluated through gold-standard document collections in three different languages, having place references annotated by humans. Results show that the proposed method compares favorably against commercial state-of-the-art systems such as the Metacarta geo-tagger and Yahoo! Placemaker.
In recent years many Spatial Data Infrastructures (SDI) have been built or are under construction in several European countries and geographical data have been collected in many different ways, sometimes following tra...
详细信息
ISBN:
(纸本)9783642123252
In recent years many Spatial Data Infrastructures (SDI) have been built or are under construction in several European countries and geographical data have been collected in many different ways, sometimes following traditional approaches (like, remote sensing techniques of photogrammetry and topography) or more "up to date" methods (like, GPS or others). However, regardless of the used methods, the geometries resulting from the surveying process describe the geographic object according to the considered accuracy level;therefore, in some cases such geometries, usually modeled as surfaces, are collapsed to set of curves and/or points. In this paper we propose a methodology which aims to handle this collapsed behavior of surfaces by preserving the conceptual schema of the database, which means that we preserve the geometric types (i.e., the surface type) of the spatial attributes even if their values can collapse. Moreover, we extend the semantics of integrity constraints included in the conceptual model in order to handle during data validation the collapsed surfaces as much as possible as real surfaces.
The Semantic Web is an attempt to add meaningful annotations to Web resources, services and content that requires developing reference ontologies, which help to understand these annotations. The venue of the Web of Da...
详细信息
ISBN:
(纸本)9783642123252
The Semantic Web is an attempt to add meaningful annotations to Web resources, services and content that requires developing reference ontologies, which help to understand these annotations. The venue of the Web of Data makes the geographic information, which has become an important part of the current Web, widely usable. This paper demonstrates how the Geospatial Web might take advantage from the Semantic Web. The show case is a services catalog dedicated to support the visualization applications based on on-the-fly data integration. The presented infrastructure for improving the catalog functionality applies an administrative geography, i.e. an ontology of political organization of the territory, published as Linked Data. The principal advantage of this approach is reflected by enhancing the functionality of the user application.
Intersection computation is one of the fundamental operations of computational geometry. This paper presents an algorithm for intersection computation between two polygons (convex/nonconvex, with nonintersecting edges...
详细信息
ISBN:
(纸本)9783642123252
Intersection computation is one of the fundamental operations of computational geometry. This paper presents an algorithm for intersection computation between two polygons (convex/nonconvex, with nonintersecting edges, and with or without holes). The approach is based on the decomposed representation of polygons, alternate hierarchical decomposition (AHD), that decomposes the nonconvex polygon into its convex components (convex hulls) arranged hierarchically in a tree data structure called convex hull tree (CHT). The overall approach involves three operations (1) intersection between two convex objects (2) intersection between a convex and a CHT (nonconvex object) and, (3) intersection between two CHTs (two nonconvex objects). This gives for (1) the basic operation of intersection computation between two convex hulls, for (2) the CHT traversal with basic operation in (I) and, for (3) the CHT traversal with operation in (2). Only the basic operation of intersection of two convex hulls is geometric (for which well known algorithms exist) and the other operations are repeated application of this by traversing tree structures.
The general situation on geospatial information is one of fragmented data sets and sources, gaps in availability, lack of harmonization between data sets at different geographical scales, and duplication of informatio...
详细信息
ISBN:
(纸本)9783642123252
The general situation on geospatial information is one of fragmented data sets and sources, gaps in availability, lack of harmonization between data sets at different geographical scales, and duplication of information collections. Addressing these issues, providers of geospatial information in Europe have to deliver their contents relating to specifications emerging in for the context of INSPIRE (Infrastructure for Spatial Information in Europe). Schema mapping plays a critical role in this process. We suggest an approach that supports the data translation procedure using Web Service technology. Efficient and sufficiently loosely coupled components for rule management and translation execution were designed and implemented. We present them in this paper. Our solution guarantees extensibility in mapping rule structure and of translation operators. We allow users to customize geospatial information and thus enable flexible information exchange. We suggest and compare two options of using the developed software.
For an autonomous agent, performing a task in a spatio-temporal environment often requires interaction with other agents. Such interaction can be initiated by ad-hoc collaborative planning and decision-making, which t...
详细信息
ISBN:
(纸本)9783642123252
For an autonomous agent, performing a task in a spatio-temporal environment often requires interaction with other agents. Such interaction can be initiated by ad-hoc collaborative planning and decision-making, which then leads to physical support on site. On-site collaboration is important for a variety of operations, such as search-and-rescue or pick-up-and-delivery. Tasks are performed through sequences of actions, and agents perceive possibilities for these actions in terms of affordances from the environment. Agent collaboration therefore requires the communication of affordances between agents with different capabilities. This paper introduces a spatio-temporal model for the decentralized decision-making of autonomous agents regarding on-site collaboration. Based on Janelle's time-geographic perspective on communication modes, we demonstrate that different task situations lead to different spatio-temporal constraints on communication, involving both physical presence and telepresence. The application of such constraints leads to an optimized message distribution strategy and therefore efficient affordance communication with regard to maximizing support in performing a given task.
Positioning data sets gathered from GPS recordings of moving people or vehicles and usage logs of telecommunications networks are being increasingly used as a proxy to capture the mobility of people in a variety of pl...
详细信息
ISBN:
(纸本)9783642123252
Positioning data sets gathered from GPS recordings of moving people or vehicles and usage logs of telecommunications networks are being increasingly used as a proxy to capture the mobility of people in a variety of places. The purpose of use of these data sets is wide-ranging and requires the development of techniques for collaborative map construction, the analysis and modelling of human behaviour, and the provision of context-aware services and applications. However, the quality of these data sets is affected by several factors depending on the technology used to collect the position and on the particular scenario where it is collected. This paper aims at assessing the quality and suitability of GPS recordings used in analysing pedestrian movement in two different recreational applications. Therefore, we look at two positioning data sets collected by two distinct groups of pedestrians, and analyse their collective movement patterns in the applications of a mobile outdoor gaming and as well as a park recreational usage. Among other findings, we show that the different reading rates of the pedestrians' position lead to different levels of inaccuracy in the variables derived from it (e.g. velocity and bearing). This was significant in the case of bearing values that were calculated from GPS readings which, in turn, has shown a strong impact on the size of clusters of movement patterns.
Cloud Computing is one of the latest hypes in the mainstream IT world. In this context, Spatial Data Infrastructures (SDIs) have not been considered yet. This paper reviews this novel technology and identifies the par...
详细信息
ISBN:
(纸本)9783642123252
Cloud Computing is one of the latest hypes in the mainstream IT world. In this context, Spatial Data Infrastructures (SDIs) have not been considered yet. This paper reviews this novel technology and identifies the paradigm behind it with regard to SDIs. Concepts of SDIs are analyzed in respect to common gaps which can be solved by Cloud Computing technologies. A real world use case will be presented, which benefits largely from Cloud Computing as a proof-of-concept demonstration. This use case shows that SDI components can be integrated into the cloud as value-added services. Thereby SDI components are shifted from a Software as a Service cloud layer to the Platform as a Service cloud layer, which can be regarded as a future direction for SDIs to enable geospatial cloud interoperability.
High-resolution urban data at house level are essential for understanding the relationship between objects of the urban built environment (e.g. streets, housing types, public resources and open spaces). However, it is...
详细信息
ISBN:
(纸本)9783642123252
High-resolution urban data at house level are essential for understanding the relationship between objects of the urban built environment (e.g. streets, housing types, public resources and open spaces). However, it is rather difficult to analyze such data due to the huge amount of urban objects, their multidimensional character and the complex spatial relation between them. In this paper we propose a methodology for assessing the spatial relation between geo-referenced urban environmental variables, in order to identify typical or significant spatial configurations as well as to characterize their geographical distribution. Configuration in this sense refers to the unique combination of different urban environmental variables. We structure the analytic process by defining spatial configurations, multidimensional clustering of the individual configurations, and identifying emerging patterns of interesting configurations. This process is based on the tight combination of interactive visualization methods with automatic analysis techniques. We demonstrate the usefulness of the proposed methods and methodology in an application example on the relation between street network topology and distribution of land uses in a city.
暂无评论