IEEE Transactions on Visualization and Computer Graphics · 2007 · 287 citations · 34 references
ComputingVisualizationData VisualizationInformation VisualizationVisual AnalyticsData AbstractionTemporal Data VisualizationTemporal VisualizationTime-varying Data VisualizationTemporal Data AbstractionVisual Analytics For Temporal Data
Time‑oriented data analysis requires appropriate methods, and integrating visual and analytical approaches is increasingly important across many domains. The study investigates how the time parameter uniquely shapes visually driven data analysis by exploring visualization, analysis, and user aspects, and by illustrating time characteristics in visual representations. The authors employ temporal data abstraction, principal component analysis, clustering, and event‑based visualization to support user‑centered analysis of large time‑oriented datasets. Their experience demonstrates that temporal abstraction, PCA, clustering, and event‑based visualization effectively support analysis of large time‑oriented data and adapt the visualization pipeline to user needs.
Providing appropriate methods to facilitate the analysis of time-oriented data is a key issue in many application domains. In this paper, we focus on the unique role of the parameter time in the context of visually driven data analysis.We will discuss three major aspects — visualization, analysis, and the user. It will be illustrated that it is necessary to consider the characteristics of time when generating visual representations.For that purpose we take a look at different types of time and present visual examples. Integrating visual and analytical methods has become an increasingly important issue. Therefore, we present our experiences in temporal data abstraction, principal component analysis, and clustering of larger volumes of time-oriented data. The third main aspect we discuss is supporting user-centered visual analysis.We describe event-based visualization as a promising means to adapt the visualization pipeline to needs and tasks of users.
34
A symbolic representation of time series, with implications for streaming algorithms
Jessica Lin, Eamonn Keogh, Stefano Lonardi et al. · 2003 · 1.8K citations
Experiencing SAX: a novel symbolic representation of time series
Jessica Lin, Eamonn Keogh, Wei Li et al. · Data Mining and Knowledge Discovery · 2007 · 1.6K citations
Computing, Data Science, Mathematics +12
Technometrics · 2003 · 916 citations