Showing papers in "Information Visualization in 2004"

Dynamic query tools for time series data sets: timebox widgets for interactive exploration

Abstract: Timeboxes are rectangular widgets that can be used in direct-manipulation graphical user interfaces (GUIs) to specify query constraints on time series data sets. Timeboxes are used to specify simultaneously two sets of constraints: given a set of N time series profiles, a timebox covering time periods x1...x2 (x1

Mapping nominal values to numbers for effective visualization

Abstract: Data sets with a large numbers of nominal variables, including some with large number of distinct values, are becoming increasingly common and need to be explored. Unfortunately, most existing visual exploration tools are designed to handle numeric variables only. When importing data sets with nominal values into such visualization tools, most solutions to date are rather simplistic. Often, techniques that map nominal values to numbers do not assign order or spacing among the values in a manner that conveys semantic relationships. Moreover, displays designed for nominal variables usually cannot handle high cardinality variables well. This paper addresses the problem of how to display nominal variables in general-purpose visual exploration tools designed for numeric variables. Specifically, we investigate (1) how to assign order and spacing among the nominal values, and (2) how to reduce the number of distinct values to display. We propose a new technique, called the Distance-Quantification-Classing (DQC) approach, to preprocess nominal variables before being imported into a visual exploration tool. In the Distance Step, we identify a set of independent dimensions that can be used to calculate the distance between nominal values. In the Quantification Step, we use the independent dimensions and the distance information to assign order and spacing among the nominal values. In the Classing Step, we use results from the previous steps to determine which values within the domain of a variable are similar to each other and thus can be grouped together. Each step in the DQC approach can be accomplished by a variety of techniques. We extended the XmdvTool package to incorporate this approach. We evaluated our approach on several data sets using a variety of measures.

VISTA: validating and refining clusters via visualization

Abstract: Clustering is an important technique for understanding of large multi-dimensional datasets. Most of clustering research to date has been focused on developing automatic clustering algorithms and cluster validation methods. The automatic algorithms are known to work well in dealing with clusters of regular shapes, for example, compact spherical shapes, but may incur higher error rates when dealing with arbitrarily shaped clusters. Although some efforts have been devoted to addressing the problem of skewed datasets, the problem of handling clusters with irregular shapes is still in its infancy, especially in terms of dimensionality of the datasets and the precision of the clustering results considered. Not surprisingly, the statistical indices works ineffective in validating clusters of irregular shapes, too. In this paper, we address the problem of clustering and validating arbitrarily shaped clusters with a visual framework (VISTA). The main idea of the VISTA approach is to capitalize on the power of visualization and interactive feedbacks to encourage domain experts to participate in the clustering revision and clustering validation process. The VISTA system has two unique features. First, it implements a linear and reliable visualization model to interactively visualize multi-dimensional datasets in a 2D star-coordinate space. Second, it provides a rich set of user-friendly interactive rendering operations, allowing users to validate and refine the cluster structure based on their visual experience as well as their domain knowledge.

Visualization of high-dimensional data with relational perspective map

Abstract: This paper introduces a method called relational perspective map (RPM) to visualize distance information in high-dimensional spaces. Like conventional multidimensional scaling, the RPM algorithm aims to produce proximity preserving 2-dimensional (2-D) maps. The main idea of the RPM algorithm is to simulate a multiparticle system on a closed surface: whereas the repulsive forces between the particles reflect the distance information, the closed surface holds the whole system in balance and prevents the resulting map from degeneracy. A special feature of RPM algorithm is its ability to partition a complex dataset into pieces and map them onto a 2-D space without overlapping. Compared to other multidimensional scaling methods, RPM is able to reveal more local details of complex datasets. This paper demonstrates the properties of RPM maps with four examples and provides extensive comparison to other multidimensional scaling methods, such as Sammon Mapping and Curvilinear Principle Analysis.

Visualising changes in fund manager holdings in two and a half-dimensions

Abstract: We explore a multiple view, or overview and detail, method for visualising a high-dimensional portfolio holdings data set with attributes that change over time. The method employs techniques from multidimensional scaling and graph visualisation to find a two-dimensional mapping for high-dimensional data. In both the overview and detail views, time is mapped to the third dimension providing a two and a half-dimensional view of changes in the data. We demonstrate the utility of the paradigm with a prototype system for visualisation of movements within a large set of UK fund managers' stock portfolios.

A pivot-based routine for improved parent-finding in hybrid MDS

Abstract: The problem of exploring or visualising data of high dimensionality is central to many tools for information visualisation. Through representing a data set in terms of inter-object proximities, multidimensional scaling may be employed to generate a configuration of objects in low-dimensional space in such a way as to preserve high-dimensional relationships. An algorithm is presented here for a heuristic hybrid model for the generation of such configurations. Building on a model introduced in 2002, the algorithm functions by means of sampling, spring model and interpolation phases. The most computationally complex stage of the original algorithm involved the execution of a series of nearest-neighbour searches. In this paper, we describe how the complexity of this phase has been reduced by treating all high-dimensional relationships as a set of discretised distances to a constant number of randomly selected items: pivots. In improving this computational bottleneck, the algorithmic complexity is reduced from O(N√N) to O(N5/4). As well as documenting this improvement, the paper describes evaluation with a data set of 108,000 13-dimensional items and a set of 23,141 17-dimensional items. Results illustrate that the reduction in complexity is reflected in significantly improved run times and that no negative impact is made upon the quality of layout produced.

Design choices when architecting visualizations

Abstract: In this paper, we focus on some of the key design decisions we faced during the process of architecting a visualization system and present some possible choices, with their associated advantages and disadvantages. We frame this discussion within the context of Rivet, our general visualization environment designed for rapidly prototyping interactive, exploratory visualization tools for analysis. As we designed increasingly sophisticated visualizations, we needed to refine Rivet in order to be able to create these richer displays for larger and more complex data sets. The design decisions we discuss in this paper include the internal data model, data access, semantic meta-data information the visualization can use to create effective visual encodings, the need for data transformations in a visualization tool, modular objects for flexibility, and the tradeoff between simplicity and expressiveness when providing methods for creating visualizations.

Analyzing perceptual organization in information graphics

Abstract: We propose a new method for assessing the perceptual organization of information graphics, based on the premise that the visual structure of an image should match the structure of the data it is intended to convey. The core of our method is a new formal model of one type of perceptual structure, based on classical machine vision techniques for analyzing an image at multiple resolutions. The model takes as input an arbitrary grayscale image and returns a lattice structure describing the visual organization of the image. We show how this model captures several aspects of traditional design aesthetics, and we describe a software tool that implements the model to help designers analyze and refine visual displays. Our emphasis here is on demonstrating the model's potential as a design aid rather than as a description of human perception, but given its initial promise we propose a variety of ways in which the model could be extended and validated.

Compound brushing explained

Abstract: This paper proposes a conceptual model called compound brushing for modeling the brushing techniques used in dynamic data visualization. In this approach, brushing techniques are modeled as higraphs with five types of basic entities: data, selection, device, renderer, and transformation. Using this model, a flexible visual programming tool is designed not only to configure and control various common types of brushing techniques currently used in dynamic data visualization but also to investigate new brushing techniques.

Multiple foci visualisation of large hierarchies with FlexTree

Abstract: One of the main tasks in information visualisation research is creating visual tools to facilitate human understanding of large and complex information spaces. Hierarchies, being a good mechanism for organising such information, are ubiquitous. Although much research effort has been spent on finding useful representations for hierarchies, visualising large hierarchies is still a difficult topic. One of the difficulties is how to handle the ever increasing scale of hierarchies. Another is how to enable the user to focus on multiple selections of interest while maintaining context. This paper describes a hierarchy visualisation technique called FlexTree to address these problems. It contains some important features that have not been exploited so far. A profile or contour unique to the hierarchy being visualised can be viewed in a bar chart layout. A normalised view of a common attribute of all nodes can be selected by the user. Multiple foci are consistently accessible within a global context through interaction. Furthermore it can handle a large hierarchy that contains 10,000 nodes in a PC environment. This technique has been applied to visualise computer file system structures and decision trees from data mining results. The results from informal user evaluations against these two applications are also presented. User feedback suggests that FlexTree is suitable for visualising large decision trees.

The representation of neural data using visualization

Abstract: Currently, the focus of research within Information Visualization is steering towards genomic data visualization due to the level of activity that the Human Genome Project has generated. However, the Human Brain project, renowned within Neuroinformatics, is equally challenging and exciting. Its main aim is to increase current understanding of brain function such as memory, learning, attention, emotions and consciousness. It is understood that this task will require the 'integration of information from the level of the gene to the level of behaviour'. The work presented in this paper focuses on the visualization of neural data. More specifically, the data being analysed is multi-dimensional spike train data. Traditional methods, such as the 'raster plot' and the 'cross-correlogram', are still useful but they do not scale up for larger assemblies of neurons. In this paper, a new innovative method called the Tunnel is defined. Its design is based on the principles of Information Visualization; overview the data, zoom and filter data, data details on demand. The features of this visualization environment are described. This includes data filtering, navigation and a 'flat map' overview facility. Additionally, a 'coincidence overlay map' is presented. This map washes the Tunnel with colour, which encodes the coincidence of spikes.

Feel the information with VisPad: a large area vibrotactile device

Abstract: A new haptics design for visualizing data is constructed out of commodity massage pads and custom controllers and interfaces to a computer. It is an output device for information that can be transmitted to a user who sits on the pad. Two unique properties of the design are: (a) its large feedback area and (b) its passive nature, where unlike most current haptics devices, the user's hands are free to work on other things. To test how useful such a device is for visualizing data, we added the VisPad interface to our protein structure-alignment program (ProtAlign) and performed usability studies. The studies demonstrated that information could be perceived significantly faster utilizing our multi-modal presentation compared to vision-based graphical visualization alone.

Dynamical system visualization and analysis via performance maps

Abstract: Visualization techniques are common in the study of chaotic motion. These techniques range from simple time graphs and phase portraits to robust Julia sets, which are familiar to many as 'fractal images.' The utility of the Julia sets rests not in their considerable visual impact, but rather, in the color-coded information that they display about the dynamics of an iterated function. In this paper, a paradigm termed the performance map is presented, which is derived from the familiar Julia set. Performance maps are generated automatically for control or other dynamical system models over ranges of system parameters. The resulting visualizations require a minimum of a priori knowledge of the system under evaluation. By the use of color-coding, these images convey a wealth of information to the informed user about dynamic behaviors of a system that may be hidden from all but the expert analyst.

A Model of Multi-Scale Perceptual Organization in Information Graphics

Abstract: We propose a new method for assessing the perceptual organization of information graphics, based on the premise that the visual structure of an image should match the structure of the data it is intended to convey. The core of our method is a new formal model of one type of perceptual structure, based on classical machine vision techniques for analyzing an image at multiple resolutions. The model takes as input an arbitrary grayscale image and returns a lattice structure describing the visual organization of the image. We show how this model captures several aspects of traditional design aesthetics, and we describe a software tool that implements the model to help designers analyze and refine visual displays. Our emphasis here is on demonstrating the model's potential as a design aid rather than as a description of human perception, but given its initial promise we propose a variety of ways in which the model could be extended and validated.