Zobraziť v EDS

Graph visualization in space and time

Uložené v:
Podrobná bibliografia
Názov: Graph visualization in space and time
Autori: Hadlak, Steffen
Prispievatelia: Schumann, Heidrun, Urban, Bodo, Kerren, Andreas
Rok vydania: 2014
Predmety: visualization, graph visualization, visual graph analysis, clustering, geo, class
Time: 006
Popis: The visual analysis of graphs plays an important role in many fields and includes a diversity of aspects such as the graphs' structure and associated attributes in their spatial and temporal context. Because of their increasing size, their visualization becomes more and more difficult and necessitates a multitude of different visualization techniques. This problem becomes even more severe as with a changing analysis focus on the graph, the analyst needs to flexibly switch between different visualizations at any time. This thesis aims at solving these three challenges. First, the handling of the diversity and emerging problems are discussed exemplary for two approaches each providing a multitude of differently suited tree visualizations. Here, a family of point-based tree layouts is introduced that consists of layouts with a similar layout scheme. And an implicit tree visualization design space is derived by identifying common design decisions. For a scalable analysis of large graphs, new reduction approaches are introduced. These approached are based on the one hand on clustering techniques abstracting either the structural or temporal aspect of the graphs. And on the other hand they rely on Degree-of-Interest functions to discern interesting nodes, edges and time points. Finally, to bring the different visualizations together and thus allow a flexible analysis, novel approaches for their combination and synchronization are introduced. These approaches include the in situ visualization that is based on portals to allow a local combination of visualizations and a novel abstract overview of all aspect allowing the synchronization of multiple visualizations. ; Die visuelle Analyse von Graphen spielt eine große Rolle in vielen Wissenschaftsgebieten. Sie umfasst eine Vielzahl verschiedener Aspekte, wie der Graphstruktur und damit verbundener Attribute in ihrem räumlichen und zeitlichen Kontext. Aufgrund der steigenden Größe dieser Graphen wird deren Darstellung immer problematischer und bedingt eine Unzahl .
Druh dokumentu: thesis
Jazyk: English
Relation: https://publica.fraunhofer.de/handle/publica/280368
Dostupnosť: https://publica.fraunhofer.de/handle/publica/280368
Rights: undefined
Prístupové číslo: edsbas.B5E1CB9F
Databáza: BASE
Popis
Abstrakt:The visual analysis of graphs plays an important role in many fields and includes a diversity of aspects such as the graphs' structure and associated attributes in their spatial and temporal context. Because of their increasing size, their visualization becomes more and more difficult and necessitates a multitude of different visualization techniques. This problem becomes even more severe as with a changing analysis focus on the graph, the analyst needs to flexibly switch between different visualizations at any time. This thesis aims at solving these three challenges. First, the handling of the diversity and emerging problems are discussed exemplary for two approaches each providing a multitude of differently suited tree visualizations. Here, a family of point-based tree layouts is introduced that consists of layouts with a similar layout scheme. And an implicit tree visualization design space is derived by identifying common design decisions. For a scalable analysis of large graphs, new reduction approaches are introduced. These approached are based on the one hand on clustering techniques abstracting either the structural or temporal aspect of the graphs. And on the other hand they rely on Degree-of-Interest functions to discern interesting nodes, edges and time points. Finally, to bring the different visualizations together and thus allow a flexible analysis, novel approaches for their combination and synchronization are introduced. These approaches include the in situ visualization that is based on portals to allow a local combination of visualizations and a novel abstract overview of all aspect allowing the synchronization of multiple visualizations. ; Die visuelle Analyse von Graphen spielt eine große Rolle in vielen Wissenschaftsgebieten. Sie umfasst eine Vielzahl verschiedener Aspekte, wie der Graphstruktur und damit verbundener Attribute in ihrem räumlichen und zeitlichen Kontext. Aufgrund der steigenden Größe dieser Graphen wird deren Darstellung immer problematischer und bedingt eine Unzahl .