IEEE VIS Publication Dataset

nSpace2 is an innovative visual analytics tool that was the primary platform used to search, evaluate, and organize the data in the VAST 2011 Mini Challenge #3 dataset. nSpace2 is a web-based tool that is designed to facilitate the back-and-forth flow of the multiple steps of an analysis process, including search, data triage, organization, sense-making, and reporting. This paper describes how nSpace2 was used to assist every step of the analysis process for this VAST challenge.

To make informed decisions, an expert has to reason with multi-dimensional, heterogeneous data and analysis results of these. Items in such datasets are typically represented by features. However, as argued in cognitive science, features do not yield an optimal space for human reasoning. In fact, humans tend to organize complex information in terms of prototypes or known cases rather than in absolute terms. When confronted with unknown data items, humans assess them in terms of similarity to these prototypical elements. Interestingly, an analogues similarity-to-prototype approach, where prototypes are taken from the data, has been successfully applied in machine learning. Combining such a machine learning approach with human prototypical reasoning in a Visual Analytics context requires to integrate similarity-based classification with interactive visualizations. To that end, the data prototypes should be visually represented to trigger direct associations to cases familiar to the domain experts. In this paper, we propose a set of highly interactive visualizations to explore data and classification results in terms of dissimilarities to visually represented prototypes. We argue that this approach not only supports human reasoning processes, but is also suitable to enhance understanding of heterogeneous data. The proposed framework is applied to a risk assessment case study in Forensic Psychiatry.

Traditionally, the visual analysis of hierarchies, respectively, trees, is conducted by focusing on one given hierarchy. However, in many research areas multiple, differing hierarchies need to be analyzed simultaneously in a comparative way - in particular to highlight differences between them, which sometimes can be subtle. A prominent example is the analysis of so-called phylogenetic trees in biology, reflecting hierarchical evolutionary relationships among a set of organisms. Typically, the analysis considers multiple phylogenetic trees, either to account for statistical significance or for differences in derivation of such evolutionary hierarchies; for example, based on different input data, such as the 16S ribosomal RNA and protein sequences of highly conserved enzymes. The simultaneous analysis of a collection of such trees leads to more insight into the evolutionary process. We introduce a novel visual analytics approach for the comparison of multiple hierarchies focusing on both global and local structures. A new tree comparison score has been elaborated for the identification of interesting patterns. We developed a set of linked hierarchy views showing the results of automatic tree comparison on various levels of details. This combined approach offers detailed assessment of local and global tree similarities. The approach was developed in close cooperation with experts from the evolutionary biology domain. We apply it to a phylogenetic data set on bacterial ancestry, demonstrating its application benefit.

This article describes our analytic process and experience of using the Jigsaw system in working on the VAST 2011 Mini Challenge 3. We describe how we extracted and worked with entities from the documents, and how Jigsaw's computational analysis capabilities and visualizations scaffolded the investigation. Based on our experiences, we discuss desirable features that would enhance the analytic power of Jigsaw.

KD-photomap is a web-based visual analytics system for browsing collections of geotagged Flickr photographs in search of interesting pictures, places, and events. Spatial filtering of the data is performed through zooming, moving or searching along the map. Temporal filtering is possible through defining time windows using interactive histograms and calendar controls. Information about the number and spatiotemporal distribution of photos captured in an explored area is continuously provided using various visual cues.

The microblog challenge presented an opportunity to use commercial software for visual analysis. An epidemic outbreak occurred in the city of Vastopolis, requiring visualizations of symptoms and their spread over time. Using these tools, analysts could successfully identify the outbreak's origin and pattern of dispersion. The maps used to analyze the data and present the results provided clear, easily understood representations, and presented a logical explanation of a complex progression of events.

MobileAnalymator (Mobile Analysis Animator) is a visual analytic system designed to analyze geospatial-temporal data on mobile devices. The system is an Internet based application that allows analysts to work in flexile enviornments at anytime. Its client side is developed by Adobe Flash to animate and interact with data. The server side uses Java and MySQL to query, compute, and serve data. The analyst can run the analytical task from a tablet (or computer) with Internet connection. MobileAnalymator adopted spatial and temporal autocorrelations in the interface design and integrated tangible interaction in the navigation to support analysis process.

Tabular data are pervasive. Although tables often describe multivariate data without explicit network semantics, it may be advantageous to explore the data modeled as a graph or network for analysis. Even when a given table design conveys some static network semantics, analysts may want to look at multiple networks from different perspectives, at different levels of abstraction, and with different edge semantics. We present a system called Ploceus that offers a general approach for performing multi-dimensional and multi-level network-based visual analysis on multivariate tabular data. Powered by an underlying relational algebraic framework, Ploceus supports flexible construction and transformation of networks through a direct manipulation interface, and integrates dynamic network manipulation with visual exploration for a seamless analytic experience.

In visual analytics, sensemaking is facilitated through interactive visual exploration of data. Throughout this dynamic process, users combine their domain knowledge with the dataset to create insight. Therefore, visual analytic tools exist that aid sensemaking by providing various interaction techniques that focus on allowing users to change the visual representation through adjusting parameters of the underlying statistical model. However, we postulate that the process of sensemaking is not focused on a series of parameter adjustments, but instead, a series of perceived connections and patterns within the data. Thus, how can models for visual analytic tools be designed, so that users can express their reasoning on observations (the data), instead of directly on the model or tunable parameters? Observation level (and thus “observation”) in this paper refers to the data points within a visualization. In this paper, we explore two possible observation-level interactions, namely exploratory and expressive, within the context of three statistical methods, Probabilistic Principal Component Analysis (PPCA), Multidimensional Scaling (MDS), and Generative Topographic Mapping (GTM). We discuss the importance of these two types of observation level interactions, in terms of how they occur within the sensemaking process. Further, we present use cases for GTM, MDS, and PPCA, illustrating how observation level interaction can be incorporated into visual analytic tools.

This article describes “Obvious”: a meta-toolkit that abstracts and encapsulates information visualization toolkits implemented in the Java language. It intends to unify their use and postpone the choice of which concrete toolkit(s) to use later-on in the development of visual analytics applications. We also report on the lessons we have learned when wrapping popular toolkits with Obvious, namely Prefuse, the InfoVis Toolkit, partly Improvise, JUNG and other data management libraries. We show several examples on the uses of Obvious, how the different toolkits can be combined, for instance sharing their data models. We also show how Weka and Rapid-Miner, two popular machine-learning toolkits, have been wrapped with Obvious and can be used directly with all the other wrapped toolkits. We expect Obvious to start a co-evolution process: Obvious is meant to evolve when more components of Information Visualization systems will become consensual. It is also designed to help information visualization systems adhere to the best practices to provide a higher level of interoperability and leverage the domain of visual analytics.

The study of complex activities such as scientific production and software development often require modeling connections among heterogeneous entities including people, institutions and artifacts. Despite numerous advances in algorithms and visualization techniques for understanding such social networks, the process of constructing network models and performing exploratory analysis remains difficult and time-consuming. In this paper we present Orion, a system for interactive modeling, transformation and visualization of network data. Orion's interface enables the rapid manipulation of large graphs-including the specification of complex linking relationships-using simple drag-and-drop operations with desired node types. Orion maps these user interactions to statements in a declarative workflow language that incorporates both relational operators (e.g., selection, aggregation and joins) and network analytics (e.g., centrality measures). We demonstrate how these features enable analysts to flexibly construct and compare networks in domains such as online health communities, academic collaboration and distributed software development.

Scalable and effective analysis of large text corpora remains a challenging problem as our ability to collect textual data continues to increase at an exponential rate. To help users make sense of large text corpora, we present a novel visual analytics system, Parallel-Topics, which integrates a state-of-the-art probabilistic topic model Latent Dirichlet Allocation (LDA) with interactive visualization. To describe a corpus of documents, ParallelTopics first extracts a set of semantically meaningful topics using LDA. Unlike most traditional clustering techniques in which a document is assigned to a specific cluster, the LDA model accounts for different topical aspects of each individual document. This permits effective full text analysis of larger documents that may contain multiple topics. To highlight this property of the model, ParallelTopics utilizes the parallel coordinate metaphor to present the probabilistic distribution of a document across topics. Such representation allows the users to discover single-topic vs. multi-topic documents and the relative importance of each topic to a document of interest. In addition, since most text corpora are inherently temporal, ParallelTopics also depicts the topic evolution over time. We have applied ParallelTopics to exploring and analyzing several text corpora, including the scientific proposals awarded by the National Science Foundation and the publications in the VAST community over the years. To demonstrate the efficacy of ParallelTopics, we conducted several expert evaluations, the results of which are reported in this paper.

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.

We present a visual analysis tool for mining correlations in county-level, multidimensional gun/homicide data. The tool uses 2D pexels, heatmaps, linked-views, dynamic queries and details-on-demand to analyze annual county-level data on firearm homicide rates and gun availability, as well as various socio-demographic measures. A statistical significance filter was implemented as a visual means to validate exploratory hypotheses. Results from expert evaluations indicate that our methods outperform typical graphical techniques used by statisticians, such as bar graphs, scatterplots and residual plots, to show spatial and temporal relationships. Our visualization has the potential to convey the impact of gun availability on firearm homicides to the public health arena and the general public.

Sensitivity analysis is a powerful method for discovering the significant factors that contribute to targets and understanding the interaction between variables in multivariate datasets. A number of sensitivity analysis methods fall into the class of local analysis, in which the sensitivity is defined as the partial derivatives of a target variable with respect to a group of independent variables. Incorporating sensitivity analysis in visual analytic tools is essential for multivariate phenomena analysis. However, most current multivariate visualization techniques do not allow users to explore local patterns individually for understanding the sensitivity from a pointwise view. In this paper, we present a novel pointwise local pattern exploration system for visual sensitivity analysis. Using this system, analysts are able to explore local patterns and the sensitivity at individual data points, which reveals the relationships between a focal point and its neighbors. During exploration, users are able to interactively change the derivative coefficients to perform sensitivity analysis based on different requirements as well as their domain knowledge. Each local pattern is assigned an outlier factor, so that users can quickly identify anomalous local patterns that do not conform with the global pattern. Users can also compare the local pattern with the global pattern both visually and statistically. Finally, the local pattern is integrated into the original attribute space using color mapping and jittering, which reveals the distribution of the partial derivatives. Case studies with real datasets are used to investigate the effectiveness of the visualizations and interactions.

Graph rewriting systems are easily described and explained. They can be seen as a game where one iterates transformation rules on an initial graph, until some condition is met. A rule describes a local pattern (i.e. a subgraph) that must be identified in a graph and specifies how to transform this subgraph. The graph rewriting formalism is at the same time extremely rich and complex, making the study of a model expressed in terms of graph rewriting quite challenging. For instance, predicting whether rules can be applied in any order is often difficult. When modelling complex systems, graphical formalisms have clear advantages: they are more intuitive and make it easier to visualize a system and convey intuitions about it. This work focuses on the design of an interactive visual graph rewriting system which supports graphical manipulations and computation to reason and simulate on a system. PORGY has been designed based on regular exchanges with graph rewriting systems experts and users over the past three years. The design choices relied on a careful methodology inspired from Munzner's nested process model for visualization design and validation [4].

It is a laborious process to quantify relationship patterns within a feature-rich archive. For example, understanding the degree of neuroanatomical similarity between the scanned subjects of a Magnetic Resonance Imaging (MRI) repository is a nontrivial task. In this work we present a Coordinated Multiple View (CMV) system for visually analyzing collections of feature-rich datasets. A query-based user interface operates on a feature-respective data scheme, and is geared towards domain experts that are non-specialists in informatics and analytics. We employ multi-dimensional scaling (MDS) to project feature surface representations into three-dimensions, where proximity in location is proportional to the feature similarity. Through query feedback and environment navigation, the user groups clusters that exhibit probable trends across feature and attribute. The system provides supervised classification methods for determining attribute classes within the user selected groups. Finally, using visual or analytical feature-wise exploration the user determines intra-group feature commonality.

Chi showed how to treat visualization programing models abstractly. This provided a firm theoretical basis for the data-state model of visualization. However, Chi's models did not look deeper into fine-grained program properties, such as execution semantics. We present conditionally deterministic and resource bounded semantics for the data flow model of visualization based on E-FRP. These semantics are used in the Stencil system to move between data state and data flow execution, build task-based parallelism, and build complex analysis chains for dynamic data. This initial work also shows promise for other complex operators, compilation techniques to enable efficient use of time and space, and mixing task and data parallelism.

Diagnosing a large-scale sensor network is a crucial but challenging task. Particular challenges include the resource and bandwidth constraints on sensor nodes, the spatiotemporally dynamic network behaviors, and the lack of accurate models to understand such behaviors in a hostile environment. In this paper, we present the Sensor Anomaly Visualization Engine (SAVE), a system that fully leverages the power of both visualization and anomaly detection analytics to guide the user to quickly and accurately diagnose sensor network failures and faults. SAVE combines customized visualizations over separate sensor data facets as multiple coordinated views. Temporal expansion model, correlation graph and dynamic projection views are proposed to effectively interpret the topological, correlational and dimensional sensor data dynamics and their anomalies. Through a case study with real-world sensor network system and administrators, we demonstrate that SAVE is able to help better locate the system problem and further identify the root cause of major sensor network failure scenarios.

We presented Scatterblogs, a system for microblog analysis that seamlessly integrates search backend and visual frontend. It provides powerful, automatic algorithms for detecting spatio-temporal `anomalies' within blog entries as well as corresponding visual representations and interaction facilities for inspecting anomalies or exploiting them in further analytic steps. Apart from that, we consider the system's combinatoric facilities for building complex hypotheses from temporal, spatial, and content-related aspects an important feature. This was the key for creating a cross-checked analysis for MC1.