In the text document visualization community, statistical analysis tools (e.g., principal component analysis and multidimensional scaling) and neurocomputation models (e.g., self-organizing feature maps) have been wid...
详细信息
In the text document visualization community, statistical analysis tools (e.g., principal component analysis and multidimensional scaling) and neurocomputation models (e.g., self-organizing feature maps) have been widely used for dimensionality reduction. Often the resulting dimensionality is set to two, as this facilitates plotting the results. The validity and effectiveness of these approaches largely depend on the specific data sets used and semantics of the targeted applications. To date, there has been little evaluation to assess and compare dimensionality reduction methods and dimensionality reduction processes, either numerically or empirically. The focus of this paper is to propose a mechanism for comparing and evaluating the effectiveness of dimensionality reduction techniques in the visual exploration of text document archives. We use multivariate visualization techniques and interactive visual exploration to study three problems: (a) Which dimensionality reduction technique best preserves the interrelationships within a set of text documents; (b) What is the sensitivity of the results to the number of output dimensions; (c) Can we automatically remove redundant or unimportant words from the vector extracted from the documents while still preserving the majority of information, and thus make dimensionality reduction more efficient. To study each problem, we generate supplemental dimensions based on several dimensionality reduction algorithms and parameters controlling these algorithms. We then visually analyze and explore the characteristics of the reduced dimensional spaces as implemented within a linked, multiview multidimensional visual exploration tool, XmdvTool. We compare the derived dimensions to features known to be present in the original data. Quantitative measures are also used in identifying the quality of results using different numbers of output dimensions.
Retail space management is one of the more crucial challenges faced by retailers today with an ever ever- expanding volume of data to which they must refer when making decisions. Problems have emerged that are intract...
详细信息
Retail space management is one of the more crucial challenges faced by retailers today with an ever ever- expanding volume of data to which they must refer when making decisions. Problems have emerged that are intractable using traditional means but for which interactive information visualization shows much promise. These problems or tasks are exploratory in nature and use temporal multivariate data. Department stores must maximize and optimize return on allocated retail space. Although product sales are readily available, the missing link for most retailers is a precise understanding of each store's layout in relation to its capacity and performance. This paper introduces a novel approach Visual Space Management (VSM) demonstrated with a multiple-linked view application (VisMT) that explores retail data related to space performance. VisMT integrates familiar information visualization representations and a 3D interactive layout of store floor plans with retail data sources. Parallel coordinates plot serves as a multivariate visual control panel in the coordinated system. Seasonally retail data analysis is performed simultaneously in linked views through time. Visual inquiry methods are supported for conditioned temporal multivariate data.
multipleviews have been put forward as an alternative to assist exploration of evolving phenomena or associations between distinct data sets or distinct presentations of a single data set. Coordinating between views ...
multipleviews have been put forward as an alternative to assist exploration of evolving phenomena or associations between distinct data sets or distinct presentations of a single data set. Coordinating between views is a challenge that must be met to improve visualization support for exploratory tasks. This is particularly true for high-dimensional data, such as document collections. We introduce a coordination framework for multipleviews of document collections created using projections and point placement visualizations. Coordination can occur between different views of a single data set or between views of multiple data sets. multiple coordinations are also admitted. Three new types of coordination are presented to illustrate the framework; these have been implemented in a multipurpose multi-dimensional visualization system called PEx (Projection Explorer).
Geovisualization (GeoViz) is an intrinsically complex process. The analyst needs to look at data from various perspectives and at various scales, from "seeing the whole" to "attending to particulars &qu...
详细信息
Geovisualization (GeoViz) is an intrinsically complex process. The analyst needs to look at data from various perspectives and at various scales, from "seeing the whole" to "attending to particulars " (Andrienko and Andrienko 2006). The analyst is also supposed to "see in relation", i.e. make numerous comparisons. This inherent complexity is multiplied by the complexity of the data that is explored and analyzed. The complex, multivariate data structure and heterogeneous components of most contemporary datasets necessitate a combined use of multiple techniques and approaches. There is no single visualization method capable to show "the whole". The analyst has to decompose this whole into views, examine these views and then try to synthesize the whole picture from the partial views. Also, because of large data volumes, we must use methods capable of simultaneously providing an overall view and exposing various "particulars". Looking for "particulars" requires therefore different techniques than "seeing the whole". Some existing visualization tools such as GeoVista and CommonGIS have successfully demonstrated the advantage of multiple-linked views and the use of information visualization (InfoViz) methods such as Parallel Coordinates and Heat maps to explore spatial multivariate data. GeoViz tools support interactive visual representation and analysis of spatio-temporal data, enabling analysts to explore geospatial and multivariate data from multiple perspectives. GeoViz is differentiated from GIS because it focuses on exploratory visual analysis rather than the pre-defined mapping. GeoViz research focuses particular attention on integrating cartographic approaches with interactive visual representations from information visualization, analytical data dissemination and visual analytics.
This paper introduces an interactive visualization interface with a machine learning consensus analysis that enables the researchers to explore the impact of atmospheric and socioeconomic factors on COVID-19 clinical ...
详细信息
ISBN:
(纸本)9781665480468
This paper introduces an interactive visualization interface with a machine learning consensus analysis that enables the researchers to explore the impact of atmospheric and socioeconomic factors on COVID-19 clinical severity by employing multiple Recurrent Graph Neural Networks. We designed and implemented a visualization interface that leverages coordinated multi-views to support exploratory and predictive analysis of hospitalizations and other socio-geographic variables at multiple dimensions, simultaneously. By harnessing the strength of geometric deep learning, we build a consensus machine learning model to include knowledge from county-level records and investigate the complex interrelationships between global infectious disease, environment, and social justice. Additionally, we make use of unique NASA satellite-based observations which are not broadly used in the context of climate justice applications. Our current interactive interface focus on three US states (California, Pennsylvania, and Texas) to demonstrate its scientific value and presented three case studies to make qualitative evaluations.
In this paper, we extend our generic ldquoGeoAnalyticsrdquo visualization (GAV) component toolkit, based on the principles behind Visual Analytics (VA), to also support time-oriented, geographically referenced and mul...
详细信息
ISBN:
(纸本)9781424423798
In this paper, we extend our generic ldquoGeoAnalyticsrdquo visualization (GAV) component toolkit, based on the principles behind Visual Analytics (VA), to also support time-oriented, geographically referenced and multivariate attribute volumetric data. GAV includes components that support a mixture of technologies from the three data visualization fields: information visualization (InfoVis), geovisualization (GeoVis) and scientific visualization (SciVis). Our research concentrates on visual user interface (VUI) techniques through dynamic and direct data manipulation that permit the visual analytical process to become more interactive and focused. This paper encourages synergies between well-known information- and volume data visualization methods applied in a multiple-linked and coordinatedviews interface. We address challenges for improved data interaction techniques with volumetric data and the need for immediate response. Varieties of explorative data analysis (EDA) tasks and the possibility to view the information simultaneously from different perspectives and scenarios are discussed. The effectiveness of our geovisual analytics framework is demonstrated in a tailor-made volume data explorer (VDE) application that integrates InfoVis, GeoVis and SciVis visualization methods assembled from GAV components. VDE facilitates dynamic exploration and correlation of temporal ocean space temperature and salinity data supplied in a NetCDF format from NOAA. This real-world phenomenon that corresponds to a huge volumetric data set comprises more than 31 million values for a time period of 12 months in 1994.
暂无评论