SPP 1335 - Scalable Visual Analytics

The scatterplot matrix (SPLOM) is a well-established technique to visually explore high-dimensional data sets. It is characterized by the number of scatterplots (plots) of which it consists of. Unfortunately, this number quadratically grows with the number of the data set’s dimensions. Thus, an SPLOM scales very poorly. Consequently, the usefulness of SPLOMs is restricted to a small number of dimensions. For this, several approaches already exist to explore such ‘small’ SPLOMs. Those approaches address the scalability problem just indirectly and without solving it. Therefore, we introduce a new greedy approach to manage ‘large’ SPLOMs with more than 100 dimensions. We establish a combined visualization and interaction scheme that produces intuitively interpretable SPLOMs by combining known quality measures, a pre-process reordering and a perception-based abstraction. With this scheme, the user can interactively find large amounts of relevant plots in large SPLOMs.

Generation of synthetic datasets is a common practice in many research areas. Such data is often generated to meet specific needs or certain conditions that may not be easily found in the original, real data. The nature of the data varies according to the application area and includes text, graphs, social or weather data, besides many others. The common process to create such synthetic datasets is to implement small scripts or programs, restricted to small problems or to a specific application. In this paper we propose a framework designed to generate high dimensional datasets. Users can interactively create and navigate through multi dimensional datasets using a suitable graphical user-interface. The data creation is driven by statistical distributions based on few user-defined parameters. First, a grounding dataset is created according to given inputs, and then structures and trends are included in selected dimensions and orthogonal projection planes. Furthermore, our framework supports the creation of complex non-orthogonal trends and classified datasets. It can successfully be used to create synthetic datasets simulating important trends as multidimensional clusters, correlations and outliers.

In recent years diverse quality measures to support the exploration of high-dimensional data sets have been proposed. Such measures can be very useful to rank and select information-bearing projections of very high dimensional data, when the visual exploration of all possible projections becomes unfeasible. But even though a ranking of the low dimensional projections may support the user in the visual exploration task, different measures deliver different distances between the views that do not necessarily match the expectations of human perception. As an alternative solution, we propose a perception-based approach that, similar to the existing measures, can be used to select information bearing projections of the data. Specifically, we construct a perceptual embedding for the different projections based on the data from a psychophysics study and multi-dimensional scaling. This embedding together with a ranking function is then used to estimate the value of the projections for a specific user task in a perceptual sense.

In this paper we present a simple, yet effective method to map data set values of different distributions to a color map in order to reveal interesting structures. We make use of an ordering and a simple projection technique to transform the data set before color mapping. Our transformation yields convincing results for various distributions. It also removes the burden from the user to test several mappings beforehand. A simple angular interpolation technique allows to project the data values of the visualization as desired, interactively.

Visual exploration of multivariate data typically requires projection onto lower-dimensional representations. The number of possible representations grows rapidly with the number of dimensions, and manual exploration quickly becomes ineffective or even unfeasible. This paper proposes automatic analysis methods to extract potentially relevant visual structures from a set of candidate visualizations. Based on features, the visualizations are ranked in accordance with a specified user task. The user is provided with a manageable number of potentially useful candidate visualizations, which can be used as a starting point for interactive data analysis. This can effectively ease the task of finding truly useful visualizations and potentially speed up the data exploration task. In this paper, we present ranking measures for class-based as well as non class-based scatterplots and parallel coordinates visualizations. The proposed analysis methods are evaluated on different datasets.

Modern visualization methods are in need to cope with very highdimensional data. Efficient visual analytical techniques are required to extract the inherent information content. The large number of possible projections for each method, which usually grow quadratically or even exponentially with the number of dimensions, urges the necessity to employ automatic reduction techniques, automatic sorting or selecting the projections, based on their informationbearing content. Different quality measures have been successfully applied for several specified user tasks and established visualization techniques, like Scatterplots, Scatterplot Matrices or Parallel Coordinates. Many other popular visualization techniques exist, but due to the structural differences, the measures are not directly applicable to them and new approaches are needed. In this paper we propose new quality measures for three popular visualization methods: Radviz, Pixel-Oriented Displays and Table Lenses. Our experiments show that these measures efficiently guide the visual analysis task.

Concerning multi-dimensional data sets there exist a lot of visual-based as well as automatical techniques to detect inherent relations and characteristics. Due to the (increasing) size and complexity of such data, it is necessary to combine both approaches. In this article, we therefore present established visual-based and automatical data analysis approaches and we reveal modern methods to combine these approaches, with the goal to enhance the data analysis process. All explanations are supported by examples to ease the reader's understanding.

Parallel coordinates and scatterplot matrices are widely used to visualize multi-dimensional data sets. But these visualization techniques are insufficient when the number of dimensions grows. To solve this problem, different approaches to preselect the best views or dimensions have been proposed in the last years. However, there are still several shortcomings to these methods. In this paper we present three new methods to explore multivariate data sets: a parallel coordinates matrix, in analogy to the well-known scatterplot matrix, a classbased scatterplot matrix that aims at finding good projections for each class pair, and an importance aware algorithm to sort the dimensions of scatterplot and parallel coordinates matrices.

Visual exploration of multivariate data typically requires projection onto lower-dimensional representations. The number of possible representations grows rapidly with the number of dimensions, and manual exploration quickly becomes ineffective or even unfeasible. This paper proposes automatic analysis methods to extract potentially relevant visual structures from a set of candidate visualizations. Based on features, the visualizations are ranked in accordance with a specified user task. The user is provided with a manageable number of potentially useful candidate visualizations, which can be used as a starting point for interactive data analysis. This can effectively ease the task of finding truly useful visualizations and potentially speed up the data exploration task. In this paper, we present ranking measures for class-based as well as non class-based Scatterplots and Parallel Coordinates visualizations. The proposed analysis methods are evaluated on different datasets.