Combining automated analysis and visualization techniques for effective exploration of high-dimensional data

Abstract

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 uoJeasible. 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 u ed as a starting point for interactive data analysis. This can effectively t:ase the task of finding truly useful visualizations and potcntially 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.

Towards Perceptual Optimization of the Visual Design of Scatterplots

“…They used weight functions to preserve as many important structures as possible for exploration, along with quality metrics for class separation, outliers, and correlation in the data space -but not in the image space as in our approach. Tatu et al [27] used quality metrics in the image space for scatterplots and parallel coordinates to rank 2D projections of a multivariate dataset with the aim of speeding up data exploration, rather than optimizing the plot design.…”

Projection inspector: Assessment and synthesis of multidimensional projections

“…Rank-byFeature [2] is an interactive framework that allows users to select interesting dimensions according to distinct rank criteria, producing a set of scatter plots from user selections. Tatu et al [15] automate the ranking process to generate scatter plots (and Parallel Coordinates) of classified and unclassified data according to data correlation and cluster separation. Their goal was to aid and potentially speed up the visual exploration process for different visualization techniques.…”

An Affordance-Based Framework for Human Computation and Human-Computer Collaboration

“…For some tasks such as image labeling [21,33,59,62,73,74], visual search [6,10], and query validation [48,80], the systems presented rely heavily on the users' visual perceptive abilities, with the machine serving only as a facilitator between the human and the data. For other tasks such as exploring high-dimensional datasets [68,83], classification [4,51], and dimension reduction [28,36], machine affordances (which will be discussed at length in Section 5) are combined with human visual processing to achieve superior results.…”

“…In Visual Analytics, we have seen this affordance leveraged to help analysts direct their attention for natural disaster prediction [66] (see Fig. 2c) as well as propose candidate visualizations for exploring high-dimensional data [68]. It has also been used to help analysts see dissimilarity to existing datapoints [50], where confirmation or other bias may come into play.…”

“…The study of general human-computer collaboration offers a plethora of examples of successful human/machine teams [15,23,37,39,41,46,50,65,66,68,83]. Developments in supervised machine learning in the visualization community present several vetted techniques for human intervention into computationally complex tasks [3,4,12,18,28,29,36,47,51,57].…”