#### DMCA

## Visualizing High-Dimensional Data: Advances in the Past Decade

### Citations

3400 |
Principal Component Analysis
- Jolliffe
- 2002
(Show Context)
Citation Context ...ional one. It includes many classical methods, such as Principal component analysis (PCA), Multidimensional scaling (MDS), Linear discriminate analysis (LDA), and various factor analysis methods. PCA =-=[Jol05]-=- is designed to find an orthogonal linear transformation that maximizes the variance of the resulting embedding. PCA can be calculated by an eigendecomposition of the data’s covariance matrix or a sin... |

944 |
Readings in Information Visualization: Using Vision to Think
- Card, Mackinlay, et al.
- 1999
(Show Context)
Citation Context ...ying opportunities for future visualization research. Our contributions are as follows. First, we propose a categorization of recent advances based on the information visualization (InfoVis) pipeline =-=[CMS99]-=- enriched with customized action-driven classifications (Figure 2, Section 2). We further assess the amount of interplay between user interactions and pipeline-based categorization and put user intera... |

392 | Principal curves
- Hastie, Stuetzle
(Show Context)
Citation Context ...clustering algorithm followed by construction of a minimum spanning tree of the cluster centroids in order to determine possible trends in the data. These trends are then fitted with principle curves =-=[HS89]-=- which go through the medial-axis of the data. HDViz [GBPW10], on the other hand, approximates a topological segmentation (for more details, see Section 3.5) and constructs an inverse linear regressio... |

340 |
A projection pursuit algorithm for exploratory data analysis,”
- Friedman, Tukey
- 1974
(Show Context)
Citation Context ...ned Subspaces. Instead of clustering the dimensions, which essentially creates axis-aligned linear subspaces, identifying non-axis-aligned subspaces is a more flexible alternative. Projection Pursuit =-=[FT74]-=- is one of the earliest works aimed at automatically identifying the interesting non-axis-aligned subspaces. Projections are considered to be more interesting when they deviate more from a normal dist... |

326 | Information visualization and visual data mining - KEIM - 2002 |

310 |
The use of faces to represent points in k-dimensional space graphically
- Chernoff
- 1973
(Show Context)
Citation Context ... PCP [CMR07] adopts a row-column 2D configuration instead of the 1D linear layout of the traditional PCP for simultaneous visualization of multiple time steps and variables. 4.2 Glyphs Chernoff faces =-=[Che73]-=- are one of the first attempts to map a high-dimensional data point into a single glyph. The system works by mapping different facial features to separate dimensions. In a few recent works, glyphs hav... |

167 | High-dimensional data analysis: the curses and blessing of dimensionality
- Donoho
- 2000
(Show Context)
Citation Context ... the design process. We now discuss the challenges addressed by the techniques surveyed in the paper, and those that remain to be tackled. Our discussion is partially inspired by Donoho’s AMS lecture =-=[Don00]-=- where he discusses the curses and blessings of dimensionality when it comes to highdimensional data analysis. Data analysis, falls under the data transformation stage within our categorization. Some ... |

161 | Entropy-based subspace clustering for mining numerical data
- Cheng, Fu, et al.
- 1999
(Show Context)
Citation Context ...5. S. Liu, D. Maljovec, B. Wang, P.-T Bremer & V. Pascucci / Visualizing High-Dimensional Data:Advances in the Past Decade lower-dimensional structures to be discovered. These methods, such as ENCLUS =-=[CFZ99]-=-, originate from the data mining and knowledge discovery community. They introduce some very interesting exploration strategies for high-dimensional datasets, and can be particularly effective when th... |

149 | Computational Topology, An Introduction - Edelsbrunner, Harer - 2010 |

130 | Hierarchical Morse-Smale complexes for piecewise linear 2-manifolds - Edelsbrunner, Harer, et al. - 2003 |

124 |
and Partha Niyogi. Laplacian eigenmaps for dimensionality reduction and data representation
- Belkin
(Show Context)
Citation Context ...der either the metric or non-metric setting. The graph-based techniques are designed to handle metric inputs, such as Isomap [TDSL00], Local Linear Embedding (LLE) [RS00], and Laplacian Eigenmap (LE) =-=[BN03]-=-, where a neighborhood graph is used to capture local distance proximities and to build a data-driven model of the space. The other group of techniques address non-metric problems commonly referred to... |

119 | Topology and data
- Carlsson
(Show Context)
Citation Context ...atesc© The Eurographics Association 2015. S. Liu, D. Maljovec, B. Wang, P.-T Bremer & V. Pascucci / Visualizing High-Dimensional Data:Advances in the Past Decade free summary of high-dimensional data =-=[Car09]-=-. Furthermore, we connect advances in high-dimensional data visualization with volume rendering and machine learning (Section 7). Finally, we reflect on our categorization with respect to actionable t... |

114 | Rolling the dice: Multidimensional visual exploration using scatterplot matrix navigation
- Elmqvist, Dragicevic, et al.
- 2008
(Show Context)
Citation Context ... Value & Relation Dispaly[YHW∗07] Hierarchy Based Dimension Hierarchy [WPWR03],sTopology-based Hierarchy [HW10, OHWS13], Others[ERHH11] Animation GGobi[SLBC03], TripAdvisorND [NM13], Rolling the Dice =-=[EDF08]-=- Evaluation Scatterplot Guideline [SMT13], PCPs Effectiveness, [HVW10], Animation [HR07] Continuous Visual Representation Continuous Scatterplot[BW08],sContinuous Parallel Coordiante [HW09, LT11], Spl... |

114 | Visualization Techniques for Mining Large Databases: A Comparison,” - Keim, Kriegel - 1996 |

112 | Animated transitions in statistical data graphics
- Heer, Robertson
- 2007
(Show Context)
Citation Context ...based Hierarchy [HW10, OHWS13], Others[ERHH11] Animation GGobi[SLBC03], TripAdvisorND [NM13], Rolling the Dice [EDF08] Evaluation Scatterplot Guideline [SMT13], PCPs Effectiveness, [HVW10], Animation =-=[HR07]-=- Continuous Visual Representation Continuous Scatterplot[BW08],sContinuous Parallel Coordiante [HW09, LT11], Splatterplots[MG13] Accurate Color Blending Hue-Preserving Blending [KGZ∗12], Weaving vs. B... |

107 | Parallel Coordinates: Visual Multidimensional Geometry and Its Applications. - Inselberg - 2009 |

102 | Barcodes: the persistent topology of data
- Ghrist
(Show Context)
Citation Context ...data. 2D Scalar functionsReeb Graph/Contour Tree/Merge TreesMorse-Smale ComplexsFigure 3: Contour- and gradient-based topological structure of a 2D scalar function. Other Topological Features. Ghrist =-=[Ghr08]-=- and Carlsson [Car09] both offer several applications of TDA and in particular highlight the topological theory used in a study of statistics of natural images [LPM03]. Mapper [SMC07] decomposes data ... |

90 | A taxonomy of clutter reduction for information visualisation.
- Ellis, Dix
- 2007
(Show Context)
Citation Context ...tive exploration. A number of surveys have focused on different aspects of high-dimensional data visualization, such as parallel coordinates [Ins09, HW13], quality measures [BTK11], clutter reduction =-=[ED07]-=-, visual data mining [HG02, Kei02, DOL03], and interactive techniques [BCS96]. High-dimensional aspects of scientific data have also been investigated within the surveys [BH07,KH13]. The surveys [WB94... |

86 | From visual data exploration to visual data mining: a survey - Oliveira, Levkowitz - 2003 |

86 |
Top Scientific Visualization Research Problems
- JOHNSON
(Show Context)
Citation Context ...ining to uncertainty is becoming increasingly available and important. The addition of uncertainty information within visualizations has been deemed a top research problem in scientific visualization =-=[Joh04]-=-, due to the greater availability of this information from simulation and quantification, and the importance of understanding data quality, confidence, and error issues when interpreting scientific re... |

80 | Circle Segments: A Technique for Visually Exploring Large Multidimensional Data Sets,”
- Ankerst, Keim, et al.
- 1996
(Show Context)
Citation Context ...ta is sorted and colored by relevance such that the data most related to the query appears in the center of the image, and the data spirals outward as it loses relevance to the query. Circle segments =-=[AKpK96]-=- arrange multidimensional data in a radial fashion with equal size sectors being carved out for each dimension. The pixel concept can be applied to bar charts to create pixel bar charts [KHL∗01]. Pixe... |

76 | V.: A Topological Hierarchy for Functions on Triangulated Surfaces - BREMER, HAMANN, et al. |

67 | Revealing structure within clustered parallel coordinates displays
- Johansson, Ljung, et al.
- 2005
(Show Context)
Citation Context ...Parallel Coordinate[JJ09], Radial Layout[LT13], Hybrid Construction [YGX∗09, CvW11] Illustrative Rendering Illustrative PCP[MM08],sIlluminated 3D scatterplot[SW09], PCP density based transfer function=-=[JLJC05]-=- Subspace Clustering Dimension Space Explorations[TFH11, YRWG13], Subset of Dimension[TMF∗12], Non-Axis-Parallel Subspace [Vid11, AWD12] Topological Data Analysis Morse-Smale Complex [GBPW10, CL11], R... |

63 | Persistent homology - a survey - Edelsbrunner, Harer - 2008 |

60 | Sparse multidimensional scaling using landmark points
- Silva, Tenenbaum
- 2004
(Show Context)
Citation Context ...ion View Transformation Visual Mapping Transformed Data Visual Structure Views User U se rsIn te ra ct io ns Dimension Reductionslinear projection[KC03],snon-linear DR[WM04], Control Points Projection=-=[DST04]-=-, Distance Metric[LMZ∗14],sPrecision Measures[LV09]D at asTr an sf or m at io n V is ua l M ap pi ng V ie wsT ra ns fo rm at io n Axis Based Scatterplot Matrix[WAG06], Parallel Coordinate[JJ09], Radia... |

54 | Uncovering clusters in crowded parallel coordinates visualizations
- Artero, Oliveira, et al.
- 2004
(Show Context)
Citation Context ...ically identify interesting patterns in PCPs or scatterplots. In this section, we discuss the image space based quality measures that are applied in the screen space. Arterode et al. propose a method =-=[AdOL04]-=- for uncovering clusters and reducing clutter by analyzing the density or frequency of the plot. Image processing based techniques such as grayscale manipulation and thresholding are used to achieve t... |

54 | DNA visual and analytic data mining,” - Hoffman, Grinstein, et al. - 1997 |

48 | A.: Visualizing scalar volumetric data with uncertainty - DJURCILOV, KIM, et al. |

44 | Topology-based simplification for feature extraction from 3d scalar fields. - Gyulassy, Natarajan, et al. - 2005 |

43 | Structure-based brushes: A mechanism for navigating hierarchically organized data and information spaces
- Fua, Ward, et al.
(Show Context)
Citation Context ...ed on either persistence, cluster size, or cluster stability, thus adjusting the placement of features in the topological landscape. Other Hierarchical Structures. In the structure-based brushes work =-=[FWR00]-=-, a data hierarchy is constructed to be visualized by both a PCP and a treemap [Shn92], allowing users to navigate among different levels-of-detail and select the feature(s) of interest. The structure... |

41 | A practical approach to Morse-Smale complex computation: Scalability and generality. - GYULASSY, BREMER, et al. - 2008 |

38 | Parallel Sets: Visual Analysis of Categorical Data”,
- Bendix, Kosara, et al.
- 2005
(Show Context)
Citation Context ... numerical values [RRB∗04] (e.g. as implemented in the XmdvTool [War94]). Through such a mapping, each axis is used more efficiently and the spacing becomes more meaningful. In the Parallel Sets work =-=[BKH05]-=-, the authors introduce a new visual representation that adapts the notion of parallel coordinates but replaces the data points with a frequencybased visual representation that is designed for nominal... |

36 | Uncertainty-aware exploration of continuous parameter spaces using multivariate prediction
- Berger, Piringer, et al.
- 2011
(Show Context)
Citation Context ...ata and the model, and computes sensitivity information on the model. The software allows for adding more model parameters to refine their regression to an acceptable level of accuracy. Berger et al. =-=[BPFG11]-=- utilize two different types of regression models (SVR and nearest neighbor regression) to analyze a trade-off study in performance car engine design. Utilizing the predictive power of the regression,... |

34 | Star coordinates: A multi-dimensional visualization technique with uniform treatment of dimensions.
- Kandogan
- 2000
(Show Context)
Citation Context ...ents. For the PCP case, a 3D visualization is presented, where either the edges are stacked as curves or the points on the axes are stacked vertically as dots. Radial Layout. The star coordinate plot =-=[Kan00]-=-, also referred to as a bi-plot [HGM∗97], is a generalization of the axis-aligned bivariate scatterplot. The star coordinate axes represent the unit basis vectors of an affine projection. The user is ... |

33 | Continuous scatterplots
- Bachthaler, Weiskopf
- 2008
(Show Context)
Citation Context ...[SLBC03], TripAdvisorND [NM13], Rolling the Dice [EDF08] Evaluation Scatterplot Guideline [SMT13], PCPs Effectiveness, [HVW10], Animation [HR07] Continuous Visual Representation Continuous Scatterplot=-=[BW08]-=-,sContinuous Parallel Coordiante [HW09, LT11], Splatterplots[MG13] Accurate Color Blending Hue-Preserving Blending [KGZ∗12], Weaving vs. Blending [HSKIH07] Image Space Metrics Clutter Reduction [AdOL0... |

33 |
Interactive dimensionality reduction through user-defined combinations of quality metrics
- Johansson, Johansson
(Show Context)
Citation Context ...ection[DST04], Distance Metric[LMZ∗14],sPrecision Measures[LV09]D at asTr an sf or m at io n V is ua l M ap pi ng V ie wsT ra ns fo rm at io n Axis Based Scatterplot Matrix[WAG06], Parallel Coordinate=-=[JJ09]-=-, Radial Layout[LT13], Hybrid Construction [YGX∗09, CvW11] Illustrative Rendering Illustrative PCP[MM08],sIlluminated 3D scatterplot[SW09], PCP density based transfer function[JLJC05] Subspace Cluster... |

30 | Visual exploration of high dimensional scalar functions
- GERBER, BREMER, et al.
- 2010
(Show Context)
Citation Context ...s for understanding sensitivity information are also discussed. Structural Summaries. Researchers have also used regression to summarize data as in the works by Reddy et al. [RPH08] and Gerber et al. =-=[GBPW10]-=-. Both methods summarize the structures of the data via skeleton representations. Reddy et al. [RPH08] use a clustering algorithm followed by construction of a minimum spanning tree of the cluster cen... |

29 |
Coordinating computational and visual approaches for interactive feature selection and multivariate clustering. Information Visualization
- Guo
- 2003
(Show Context)
Citation Context ...h as outliers, shape, trend, and density. In addition, they improve the computational efficiency by using graphtheoretic measures. Scagnostics is also extended to handle time series data [DAW13]. Guo =-=[Guo03]-=- introduces an interactive feature selection method for finding interesting plots by evaluating the maximum conditional entropy of all possible axis-parallel scatterplots. The rank by feature framewor... |

28 | Describing shapes by geometricaltopological properties of real functions. - Biasotti, Floriani, et al. - 2008 |

28 | A survey of visualizations for high-dimensional data mining. Information visualization in data mining and knowledge discovery - Hoffman, Grinstein - 2002 |

27 | Quality metrics in highdimensional data visualization: An overview and systematization
- Bertini, Tatu, et al.
- 2011
(Show Context)
Citation Context ...itative analysis to interactive exploration. A number of surveys have focused on different aspects of high-dimensional data visualization, such as parallel coordinates [Ins09, HW13], quality measures =-=[BTK11]-=-, clutter reduction [ED07], visual data mining [HG02, Kei02, DOL03], and interactive techniques [BCS96]. High-dimensional aspects of scientific data have also been investigated within the surveys [BH0... |

27 | iPCA: An interactive system for PCA-based visual analytics - Jeong, Ziemkiewicz, et al. - 2009 |

26 | A framework for uncertainty-aware visual analytics
- Correa, Chan, et al.
- 2009
(Show Context)
Citation Context ...ves around sampled data points and representing the information in terms of glyph shape, sensitivity information can be visually encoded into scatterplots [CCM09, CCM10, GWRR11, CCM13]. Correa et al. =-=[CCM09]-=- aimed at incorporating uncertainty information into PCA projections and k-means clustering and accomplished this goal by augmenting scatterplots with tornado plots. Together these glyphs encode uncer... |

25 | MoleView: An attribute and structure-based semantic lens for large element-based plots
- Hurter, Ersoy, et al.
(Show Context)
Citation Context ...94] for visualizing large tables. Such a magic lens based approach permits fast exploration of an area of interest without presenting all the details, therefore, reduces clutter in the view. MoleView =-=[HTE11]-=-, for visualizing scatterplots and graphs, adopts a semantic lens for allowing users to focus on the area of interest and keep the infocused data unchanged while simplifying or deforming the rest of d... |

25 | Parallel coordinates - Inselberg, Dimsdale - 1991 |

24 | Pargnostics: Screen-space metrics for parallel coordinates
- Dasgupta, Kosara
(Show Context)
Citation Context ... Coordiante [HW09, LT11], Splatterplots[MG13] Accurate Color Blending Hue-Preserving Blending [KGZ∗12], Weaving vs. Blending [HSKIH07] Image Space Metrics Clutter Reduction [AdOL04, JC08], Pargnostics=-=[DK10]-=-, Pixnostic[SSK06] Figure 2: Categorization based on transformation steps within the information visualization pipeline, with customized actiondriven subcategories. goals, the attributes consist of in... |

24 | Interactive visual analysis of multi-faceted scientific data - Kehrer |

23 | T.: An Interactive 3D Integration of Parallel Coordinates and Star Glyphs
- FANEA, CARPENDALE, et al.
(Show Context)
Citation Context ...ives the user the ability to create new configurations by drawing and linking axes in either scatterplot or PCP style. Proposed by Fanea et al., the integration of parallel coordinate and star glyphs =-=[FCI05]-=- provides a way to “unfold” the overlapped values in the PCP axis in 3D space. In this work [FCI05], each axis in the PCP is replaced with a star glyph that represents the values across all points, an... |

23 | Intelligent visual analytics queries - Hao, Dayal, et al. - 2007 |

23 |
Weaving versus blending: a quantitative assessment of the information carrying capacities of two alternative methods for conveying multivariate data with color.
- Hagh-Shenas, Interrante, et al.
- 2006
(Show Context)
Citation Context ...ous Visual Representation Continuous Scatterplot[BW08],sContinuous Parallel Coordiante [HW09, LT11], Splatterplots[MG13] Accurate Color Blending Hue-Preserving Blending [KGZ∗12], Weaving vs. Blending =-=[HSKIH07]-=- Image Space Metrics Clutter Reduction [AdOL04, JC08], Pargnostics[DK10], Pixnostic[SSK06] Figure 2: Categorization based on transformation steps within the information visualization pipeline, with cu... |

22 | Persistent cohomology and circular coordinates, in:
- Silva, Vejdemo-Johansson
- 2009
(Show Context)
Citation Context ...tract salient features in a study of diabetes by correctly classifying normal patients and patients with two causes of diabetes. Wang et al. [WSPVJ11] utilize TDA techniques developed by Silva et al. =-=[dSMVJ09]-=- to recover important structures in high-dimensional data containing non-trivial topology. Specifically, they are interested in high-dimensional branching and circular structures. The circle-valued co... |

22 | L.: Visualization of labeled data using linear transformations
- Koren, Carmel
(Show Context)
Citation Context ...vances in the Past Decade Source Data DatasTransformation View Transformation Visual Mapping Transformed Data Visual Structure Views User U se rsIn te ra ct io ns Dimension Reductionslinear projection=-=[KC03]-=-,snon-linear DR[WM04], Control Points Projection[DST04], Distance Metric[LMZ∗14],sPrecision Measures[LV09]D at asTr an sf or m at io n V is ua l M ap pi ng V ie wsT ra ns fo rm at io n Axis Based Scat... |

22 |
Ankerst M.: ‘Recursive Pattern: A Technique for Visualizing Very Large
- Keim, Kriegel
- 1995
(Show Context)
Citation Context ...-filling curves in order to fill a 2D plane in a more sensible fashion than a comparative treemap layout. The Value and Relation (VaR) displays [YPS∗04, YHW∗07] combine the recursive pattern displays =-=[KKA95]-=- with MDS in order to lay out the separate subwindows such that similar dimensions are placed closer together. A latter iteration [YHW∗07] enhances the work by providing more robust visualizations inc... |

21 |
Flexible linked axes for multivariate data visualization
- Claessen, Wijk
(Show Context)
Citation Context ...ds can also be combined to create new visualizations. The scattering points in parallel coordinate work [YGX∗09] (Figure 4) embeds a MDS plot between a pair of PCP axes. The flexible linked axes work =-=[CvW11]-=- is a generalization of the PCP and the SPLOM. The tool gives the user the ability to create new configurations by drawing and linking axes in either scatterplot or PCP style. Proposed by Fanea et al.... |

21 | Pixel Bar Charts: A New Technique for Visualizing Large Multi-Attribute Data Sets without Aggregation. - Keim, Hao, et al. - 2001 |

20 | Subspace selection for clustering high-dimensional data - Baumgartner, Plant, et al. - 2004 |

18 | Dis-function: Learning distance functions interactively
- Brown, Liu, et al.
- 2012
(Show Context)
Citation Context ...ce Metric. For a given dimension reduction algorithm, a suitable distance metric is essential for the computation outcome as it is more likely to reveal important structural information. Brown et al. =-=[BLBC12]-=- introduce the distance function learning concept, where a new distance metric is calculated from the manipulation of point layouts by an expert user. In [Gle13], the author attempts to associate a li... |

18 | Evaluation of cluster identification performance for different pcp variants
- Holten, Wijk
(Show Context)
Citation Context ...[WPWR03],sTopology-based Hierarchy [HW10, OHWS13], Others[ERHH11] Animation GGobi[SLBC03], TripAdvisorND [NM13], Rolling the Dice [EDF08] Evaluation Scatterplot Guideline [SMT13], PCPs Effectiveness, =-=[HVW10]-=-, Animation [HR07] Continuous Visual Representation Continuous Scatterplot[BW08],sContinuous Parallel Coordiante [HW09, LT11], Splatterplots[MG13] Accurate Color Blending Hue-Preserving Blending [KGZ∗... |

18 | Continuous Parallel Coordinates,”
- Heinrich, Weiskopf
- 2009
(Show Context)
Citation Context ...s scatterplot. The follow-up work [BW09] introduces an adaptive rendering extension for continuous scatterplots increasing the rendering efficiency. This concept is extended to create continuous PCPs =-=[HW09]-=- based on the point and line duality between scatterplots and parallel coordinates. The authors propose a mathematical model that maps density from a continuous scatterplot [BW08] to parallel coordina... |

18 | Local affine multidimensional projection - Joia, Coimbra, et al. |

15 | H.: DICON: Interactive visual analysis of multidimensional clusters
- CAO, GOTZ, et al.
(Show Context)
Citation Context ...ion of each partial derivative, since all line segments are normalized in length. The methods described above all deal with encoding extra information per data point into glyphs, but the DICON system =-=[CGSQ11]-=- attempts to show the trend of data within a collection of data points by visually encoding statistical information about the set of points being represented. DICON uses dynamic icons based on treemap... |

15 |
Axen U. Computing contour trees in all dimensions. Comput Geometry
- Carr, Snoeyink
(Show Context)
Citation Context ...he development of compact and effective methods for modeling and visualizing scientific data, especially in high dimensions (i.e., [NLC11, SMC07]). Efficient algorithms for computing the contour tree =-=[CSA03]-=- and Reeb graph [PSBM07] in arbitrary dimensions have been developed. A generalization of the contour tree has been introduced by Carr et al. [CD14, DCK∗12] called the joint contour net (JCN), which a... |

14 |
H.-P.: VisDB: Database exploration using multidimensional visualization
- KEIM, KRIEGEL
- 1994
(Show Context)
Citation Context ...on encoding data values as individual pixels and creating separate displays, or subwindows, for each dimension. Some of the earliest works in this area date back to the mid 1990s [KK94,AKpK96]. VisDB =-=[KK94]-=- visualizes database queries by creating a 2D image for each dimension involved in the query and mapping individual values of a dimension to pixels. The mapped data is sorted and colored by relevance ... |

11 | Efficient and adaptive rendering of 2D continuous scatterplots
- Bachthaler, Weiskopf
(Show Context)
Citation Context ...onal cost, many applications prefer a continuous representation. The work of Bachthaler and Weiskopf [BW08] presents a mathematical model for constructing a continuous scatterplot. The follow-up work =-=[BW09]-=- introduces an adaptive rendering extension for continuous scatterplots increasing the rendering efficiency. This concept is extended to create continuous PCPs [HW09] based on the point and line duali... |

11 |
A.: Stacking graphic elements to avoid overplotting
- Dang, Wilkinson, et al.
- 2010
(Show Context)
Citation Context ...g improvements exist for PCPs. Progressive PCPs [RZH12] demonstrate the power of a progressive refinement scheme for enhancing the ability of PCPs to handle large datasets. In the work of Dang et al. =-=[DWA10]-=-, density is expressed by stacking overlapping elements. For the PCP case, a 3D visualization is presented, where either the edges are stacked as curves or the points on the axes are stacked verticall... |

11 | Angular Histograms: Frequency-Based Visualizations for Large, High Dimensional Data”, - Geng, Peng, et al. - 2011 |

10 |
Visual Pattern Discovery using Random Projections
- Anand, Wilkinson, et al.
- 2012
(Show Context)
Citation Context ...ed by the same linear subspace. For very high-dimensional data, the subspace finding algorithms typically have a relatively high computational complexity. By utilizing random projection, Anand et al. =-=[AWD12]-=- introduce an efficient subspace finding algorithm for data with thousands of dimensions. It generates a set of candidate subspaces through random projections and presents the top-scoring subspaces in... |

10 |
Towards robust topology of sparsely sampled data
- Correa, Lindstrom
- 2011
(Show Context)
Citation Context ...loud data. It creates a hierarchical segmentation of the data by clustering points based on their monotonic flow behavior, and designs new visual metaphors based on such a segmentation. Correa et al. =-=[CL11]-=- suggest that by considering a different type of neighborhood structure, we can improve the accuracy in the extracted topology compared to those obtained within HDViz. Reeb Graphs and Contour Trees. T... |

10 |
Explainers: Expert explorations with crafted projections
- Gleicher
(Show Context)
Citation Context ... structural information. Brown et al. [BLBC12] introduce the distance function learning concept, where a new distance metric is calculated from the manipulation of point layouts by an expert user. In =-=[Gle13]-=-, the author attempts to associate a linear basis with a certain meaningful concept constructed based on user-defined examples. Machine learning techniques can then be employed to find a set of simple... |

10 | LineUp: Visual Analysis of Multi-Attribute Rankings. - Gratzl, Lex, et al. - 2013 |

10 |
Y.: Topological landscape ensembles for visualization of scalar-valued functions
- HARVEY, WANG
(Show Context)
Citation Context ... a metaphor for visually mapping the contour tree of high-dimensional functions to a 2D terrain where the relative size, volume, and nesting of the topological features are preserved. Harvey and Wang =-=[HW10]-=- have extended this work by computing all possible planar landscapes and they are able to preserve exactly the volumes of the high-dimensional features in the areas of the terrain. In addition, the wo... |

9 | A survey on Multivariate Data visualization - Chan - 2006 |

9 | Design and evaluation of tiled parallel coordinate visualization of multichannel EEG data
- Caat, M, et al.
- 2007
(Show Context)
Citation Context ... derive from the the well-known visual mappings. Angular histograms [GPL∗11] introduced a novel visual encoding that improves the scalability of PCPs by overcome the overplotting issue. The tiled PCP =-=[CMR07]-=- adopts a row-column 2D configuration instead of the 1D linear layout of the traditional PCP for simultaneous visualization of multiple time steps and variables. 4.2 Glyphs Chernoff faces [Che73] are ... |

9 | Pairwise display of high-dimensional information via eulerian tours and hamiltonian decompositions
- Hurley, Oldford
(Show Context)
Citation Context ...ch as clustering and correlation. Hurley et al. utilize Eulerian tours and Hamiltonian decompositions of complete graphs, which represent the relationship between the dimensions, in their recent work =-=[HO10]-=- to address the axis ordering challenge. Clutter reduction is another important aspect in PCPs, especially for large point counts. Peng et al. [PWR04] were able to reduce clutter for both SPLOMs and P... |

9 | A screen space quality method for data abstraction
- Johansson, Cooper
- 2008
(Show Context)
Citation Context ...cessing based techniques such as grayscale manipulation and thresholding are used to achieve the desired visualization. Johansson et al. introduce a screen space quality measure for clutter reduction =-=[JC08]-=- to address the challenge of very large datasets. The metric is based on distance transformation, and the computation is carried out on the GPU for interactive performance. Pargnostics [DK10], a portm... |

9 | C.: A radial focus+context visualization for multi-dimensional functions
- JAYARAMAN, NORTH
(Show Context)
Citation Context ...ion of the dimensional anchor layout. DataMeadow [EST07] introduces a radial visual encoding named DataRoses, which is represented as a PCP laid out radially as opposed to linearly. Lastly, PolarEyez =-=[JN02]-=- introduces a focus+context visualization where the highdimensional function parameter space is encoded in a radial fashion around a user-controlled focal point. Data near the focal point is represent... |

8 | Improving the visual analysis of high-dimensional datasets using quality measures - Albuquerque, Eisemann, et al. - 2010 |

8 | Visualizing High-Dimensional Structures by Dimension Ordering and Filtering using Subspace Analysis”, Computer Graphics Forum
- Roerdink
(Show Context)
Citation Context ...sified datasets. For unlabeled data, the Hough space measure is used, and for labeled data, a similarity measure and overlap measures are adopted. Ferdosi et al. introduce a dimension ordering method =-=[FR11]-=- that is applicable for both PCPs and SPLOMs utilizing the subspace analysis method from their earlier work [FBT∗10] discussed in the Section 3.3. Johansson and Johansson [JJ09] propose an interactive... |

7 | An information-aware framework for exploring multivariate data sets
- Biswas, Dutta, et al.
(Show Context)
Citation Context ...JGK10]. The work presented by Tam et al. [TFA∗11] studies facial dynamics utilizing the analysis of time-series data in parameter space. Datasets with spatial information such as multivariate volumes =-=[BDSW13]-=- or multi-spectral images [LAK∗11] are very common in scientific visualization, and numerous methods have been introduced within the scientific visualization domain, see [BH07, KH13] for comprehensive... |

7 | Pointwise local pattern exploration for sensitivity analysis
- Guo, Ward, et al.
- 2011
(Show Context)
Citation Context ...nt has been extended in their later work [CCM10] with the introduction of the flow-based scatterplot (FBS) that highlights functional relationships between inputs and outputs. The works by Guo et al. =-=[GWRR11]-=- and Chan et al. [CCM13] attempt to provide more than a single partial derivative information into their scatterplots by experimenting with different glyph shapes such as star plots among others. [GWR... |

7 | Scalable multivariate volume visualization and analysis based on dimension projection and parallel coordinates. Visualization and Computer Graphics
- Guo, Xiao, et al.
(Show Context)
Citation Context ...l coordinates work [YGX∗09] is adopted c© The Eurographics Association 2015. S. Liu, D. Maljovec, B. Wang, P.-T Bremer & V. Pascucci / Visualizing High-Dimensional Data:Advances in the Past Decade by =-=[GXY12]-=- as a design space for multivariate volume transfer functions. In the work of Liu et al. [LWT∗14a], dynamic projection and subspace analysis are utilized for exploring the high-dimensional parameter s... |

7 | State of the art of parallel coordinates - Heinrich, Weiskopf - 2013 |

6 |
Timeseer: Scagnostics for high-dimensional time series
- Dang, Anand, et al.
(Show Context)
Citation Context ...roperties such as outliers, shape, trend, and density. In addition, they improve the computational efficiency by using graphtheoretic measures. Scagnostics is also extended to handle time series data =-=[DAW13]-=-. Guo [Guo03] introduces an interactive feature selection method for finding interesting plots by evaluating the maximum conditional entropy of all possible axis-parallel scatterplots. The rank by fea... |

6 |
TSIGAS P.: DataMeadow: a visual canvas for analysis of large-scale multivariate data
- ELMQVIST, STASKO
(Show Context)
Citation Context ...then displayed where the sum of the spring forces equals zero. Albuquerque et al. [AEL∗10] devise a RadViz quality measure allowing automatic optimization of the dimensional anchor layout. DataMeadow =-=[EST07]-=- introduces a radial visual encoding named DataRoses, which is represented as a PCP laid out radially as opposed to linearly. Lastly, PolarEyez [JN02] introduces a focus+context visualization where th... |

6 | Finding and visualizing relevant subspaces for clustering high-dimensional astronomical data using connected morphological operators - FERDOSI, BUDDELMEIJER, et al. |

5 |
The generalized sensitivity scatterplot
- Chan, Correa, et al.
(Show Context)
Citation Context ...&sContour Tree[PSBM07], Topological Features[WSPVJ11] Regression Analysis Optimization &sDesign Steering [BPFG11, DW13], Structural Summaries [PBK10, GBPW10] Glyphs Per-Element Glyphs [CCM10, GWRR11] =-=[CCM13]-=-, Multi-Object Glyphss[War08, CGSQ11] Pixel-Oriented Jigsaw Map, Pixel Bar Charts [KHL01], Value & Relation Dispaly[YHW∗07] Hierarchy Based Dimension Hierarchy [WPWR03],sTopology-based Hierarchy [HW10... |

4 | H.: Visualization of multi-variate scientific data. EuroGraphics State of the Art Reports (STARs - BÜRGER, HAUSER - 2007 |

4 |
R.: Gplom: The generalized plot matrix for visualizing multidimensional multivariate data
- IM, MCGUFFIN, et al.
(Show Context)
Citation Context ... nominal data. The Conjunctive Visual Form [Wea09] allows users to rapidly query nominal values with certain conjunctive relationships through simple interactions. The GPLOM (Generalized Plot Matrix) =-=[IML13]-=- extends the Scatterplot Matrix (SPLOM) to handle nominal data. Spatiotemporal Data. Some recent advances focus on developing visual encoding that capture the spatiotemporal aspects of high-dimensiona... |

3 |
K.-L.: Flow-based scatterplots for sensitivity analysis
- CHAN, CORREA, et al.
(Show Context)
Citation Context ...ogether these glyphs encode uncertainty and partial derivative information. The idea of mapping sensitivity information to a line segment through each data point has been extended in their later work =-=[CCM10]-=- with the introduction of the flow-based scatterplot (FBS) that highlights functional relationships between inputs and outputs. The works by Guo et al. [GWRR11] and Chan et al. [CCM13] attempt to prov... |

3 | H.: Structural decomposition trees
- ENGEL, ROSENBAUM, et al.
(Show Context)
Citation Context ...yphss[War08, CGSQ11] Pixel-Oriented Jigsaw Map, Pixel Bar Charts [KHL01], Value & Relation Dispaly[YHW∗07] Hierarchy Based Dimension Hierarchy [WPWR03],sTopology-based Hierarchy [HW10, OHWS13], Others=-=[ERHH11]-=- Animation GGobi[SLBC03], TripAdvisorND [NM13], Rolling the Dice [EDF08] Evaluation Scatterplot Guideline [SMT13], PCPs Effectiveness, [HVW10], Animation [HR07] Continuous Visual Representation Contin... |

3 | Semantics of Directly Manipulating Spatializations - Hu, Bradel, et al. |

2 | STASZCZAK A.: Visualizing nuclear scission through a multifield extension of topological analysis - DUKE, CARR, et al. |

2 | M.: Domino: Extracting, comparing, and manipulating subsets across multiple tabular datasets - GRATZL, GEHLENBORG, et al. |

1 |
Interactive highc© The Eurographics Association 2015
- BUJA, COOK, et al.
- 1996
(Show Context)
Citation Context ...igh-dimensional data visualization, such as parallel coordinates [Ins09, HW13], quality measures [BTK11], clutter reduction [ED07], visual data mining [HG02, Kei02, DOL03], and interactive techniques =-=[BCS96]-=-. High-dimensional aspects of scientific data have also been investigated within the surveys [BH07,KH13]. The surveys [WB94,Cha06,Mun14] focus on the various aspects of visual encoding techniques for ... |

1 | B.: Geometry–preserving topological landscapes - BEKETAYEV, MOROZOV, et al. |

1 | D.: Joint contour nets - CARR, DUKE |

1 | B.: Topology exploration with hierarchical landscapes - DEMIR, BEKETAYEV, et al. |

1 | R.: Progressive high-quality response surfaces for visually guided sensitivity analysis
- DEMIR, WESTERMANN
(Show Context)
Citation Context ... The software then relies heavily on user interaction to study the sensitivities with respect to each input parameter and steers the computation toward the user-defined optimal solution. Demir et al. =-=[DW13]-=- improve the effectiveness of GPMs by utilizing a block-wise matrix inversion scheme that can be implemented on the GPU, greatly increasing efficiency. In addition, their method involves progressive r... |

1 | X.: Interactive local clustering operations for high dimensional data in parallel coordinates
- GUO, XIAO, et al.
(Show Context)
Citation Context ...PdSABD∗12], inverse projection extrapolation is used for generating synthetic multidimensional data out of existing projections for parameter space exploration. In the Local Clustering Operation work =-=[GXWY10]-=-, the visual structure is modified in PCPs through user-guided deformation operators. Finally, Liu et al. [LWBP14] allow for direct manipulation of the dimension reduction embedding to resolve structu... |

1 | K.: A data-driven approach to hue-preserving color-blending - KUHNE, GIESEN, et al. |