An Information-Aware Framework for Exploring Multivariate Data Sets

Abstract

Information theory provides a theoretical framework for measuring information content for an observed variable, and has attracted much attention from visualization researchers for its ability to quantify saliency and similarity among variables. In this paper, we present a new approach towards building an exploration framework based on information theory to guide the users through the multivariate data exploration process. In our framework, we compute the total entropy of the multivariate data set and identify the contribution of individual variables to the total entropy. The variables are classified into groups based on a novel graph model where a node represents a variable and the links encode the mutual information shared between the variables. The variables inside the groups are analyzed for their representativeness and an information based importance is assigned. We exploit specific information metrics to analyze the relationship between the variables and use the metrics to choose isocontours of selected variables. For a chosen group of points, parallel coordinates plots (PCP) are used to show the states of the variables and provide an interface for the user to select values of interest. Experiments with different data sets reveal the effectiveness of our proposed framework in depicting the interesting regions of the data sets taking into account the interaction among the variables.

Supporting correlation analysis on scientific datasets in parallel and distributed settings

“…(3) We show that in an environment where data is stored on geographically distributed repositories, our method is able to speed up the correlation analysis process compared to a simple method that does not use any indexing. (4) We show that if correlation analysis is performed over samples, and not the entire dataset, what kind of speedup we can achieve and how much accuracy is lost.…”

“…Much of the existing work, especially in data visualization, has focused on individual variable analysis. However, more recently, several efforts [4,26] have focused on studying the relationship among multiple variables and making interesting scientific discoveries based on such analysis. This paper focuses on the problem of correlation analysis on massive scientific datasets in parallel and distributed settings.…”

Visual Correlation Analysis of Numerical and Categorical Data on the Correlation Map

“…Chen et al [4] and Sukharev et al [28] utilize visualization techniques to show correlations in time-varying multivariate climate datasets with 3D spatial references. More recently, also for time-varying multivariate data, Biswas et al [3] used mutual information and information overlap as correlation. They utilized our layout optimization technique [33] to construct a complete connected graph for all variables.…”

FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis

“…Jänicke et al [26] extract local flow patterns as nodes in graph, and their transitions as edges where users can track features over time. There are some work visualizing the attribute relationship of scalar field using graph-like form [40,3].…”