Improving the visual analysis of high-dimensional datasets using quality measures

Albuquerque, Georgia; Eisemann, Martin; Lehmann, Dirk J.; Theisel, Holger; Magnor, Marcus

doi:10.1109/vast.2010.5652433

Cited by 60 publications

(35 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their findings showed that experts were more consistent in their positive and negative ratings. Judging the value or quality of a visualization of dimensionally-reduced data should occur regardless of task, and analysts can additionally leverage automated quality metrics based on human perception [1,4]. We did not seek out novice analysts, though the domain experts we interviewed varied in terms of their perceived understanding of dimensionality reduction; furthermore, we sought to identify and characterize experts' tasks and activities in naturalistic settings, rather than in a controlled lab study.…”

Section: Related Workmentioning

confidence: 99%

Visualizing dimensionally-reduced data

Brehmer¹,

Sedlmair²,

Ingram³

et al. 2014

Proceedings of the Fifth Workshop on Beyond Time and Errors: Novel Evaluation Methods for Visualization

View full text Add to dashboard Cite

We characterize five task sequences related to visualizing dimensionally-reduced data, drawing from data collected from interviews with ten data analysts spanning six application domains, and from our understanding of the technique literature. Our characterization of visualization task sequences for dimensionallyreduced data fills a gap created by the abundance of proposed techniques and tools that combine high-dimensional data analysis, dimensionality reduction, and visualization, and is intended to be used in the design and evaluation of future techniques and tools. We discuss implications for the evaluation of existing work practices, for the design of controlled experiments, and for the analysis of post-deployment field observations.

show abstract

Section: Related Workmentioning

confidence: 99%

Visualizing dimensionally-reduced data

Brehmer¹,

Sedlmair²,

Ingram³

et al. 2014

Proceedings of the Fifth Workshop on Beyond Time and Errors: Novel Evaluation Methods for Visualization

View full text Add to dashboard Cite

show abstract

“…Their main objective is to rank a group of views according to their potential relevance. Quality metrics that can be used for evaluating performance views are metrics that are designed for pixel-based visualization techniques, for example, the NoiseDissimilarity measure [25], or the entropy and standard deviation that are used in the Pixnostics approach [26]. Whereas the Noise-Dissimilarity evaluates the mappings based on their dissimilarity to a noise function, Pixnostics evaluates them based on entropy or standard deviation.…”

Section: Methods For Automatic Analysismentioning

confidence: 99%

“…These views are then analyzed for relevance with the NoiseDissimilarity method [25]. It evaluates the visual quality of an image based on a measure (the Noise-Dissimilarity measure NDM(g, g)) that quantifies the dissimilarity between the original image (with its gray values g) and the corresponding noise image (with its gray values g).…”

Section: Identifying Potentially Relevant Viewsmentioning

confidence: 99%

Separating the wheat from the chaff

Rüden

Hermanns

Behrisch

et al. 2015

Proceedings of the 2nd Workshop on Visual Performance Analysis

View full text Add to dashboard Cite

Performance-analysis tools are indispensable for understanding and optimizing the behavior of parallel programs running on increasingly powerful supercomputers. However, with size and complexity of hardware and software on the rise, performance data sets are becoming so voluminous that their analysis poses serious challenges. In particular, the search space that must be traversed and the number of individual performance views that must be explored to identify phenomena of interest becomes too large. To mitigate this problem, we use visual analytics. Specifically, we accelerate the analysis of performance profiles by automatically identifying (1) relevant and (2) similar data subsets and their performance views. We focus on views of the virtual-process topology, showing that their relevance can be well captured with visual-quality metrics and that they can be further assigned to topical groups according to their visual features. A case study demonstrates that our approach helps reduce the search space by up to 80%.

show abstract

“…Albuquerque et. al [4] describe quality metrics for multivariate visualization techniques like scatterplot matrices and parallel coordinates in relation to the related tasks of analyzing clusters and separating labeled classes. In these approaches 2-D projections are ranked and visually analyzed.…”

Section: Featuresmentioning

confidence: 99%

Visual pattern discovery using random projections

Anand

Wilkinson

Dang

2012

2012 IEEE Conference on Visual Analytics Science and Technology (VAST)

View full text Add to dashboard Cite

An essential element of exploratory data analysis is the use of revealing low-dimensional projections of high-dimensional data. Projection Pursuit has been an effective method for finding interesting low-dimensional projections of multidimensional spaces by optimizing a score function called a projection pursuit index. However, the technique is not scalable to high-dimensional spaces. Here, we introduce a novel method for discovering noteworthy views of high-dimensional data spaces by using binning and random projections. We define score functions, akin to projection pursuit indices, that characterize visual patterns of the low-dimensional projections that constitute feature subspaces. We also describe an analytic, multivariate visualization platform based on this algorithm that is scalable to extremely large problems.

show abstract

Improving the visual analysis of high-dimensional datasets using quality measures

Cited by 60 publications

References 19 publications

Visualizing dimensionally-reduced data

Visualizing dimensionally-reduced data

Separating the wheat from the chaff

Visual pattern discovery using random projections

Contact Info

Product

Resources

About