Zhao et al. win the Kostas Pantazos Memorial Award for their paper "MAVis: Machine learning Aided Multi-Model Framework for Time Series Visual Analytics" in VDA 2016. [Certificate]


XmdvTool is a public-domain software package for the interactive visual exploration of multivariate data sets. It is available on all major platforms such as UNIX, LINUX, MAC and Windows. XmdvTool is developed using Qt and Eclipse CDT. It supports five methods for displaying flat form data and hierarchically clustered data:

  1. Scatterplots
  2. Star Glyphs
  3. Parallel Coordinates
  4. Dimensional Stacking
  5. Pixel-oriented Display

XmdvTool also supports a variety of interaction modes and tools, including brushing in screen, data, and structure spaces, zooming, panning, and distortion techniques, and the masking and reordering of dimensions. Univariate display and graphical summarization, via tree-maps and modified Tukey box plots, are also supported. Finally, color themes and user customizable color assignments permit tailoring of the aesthetics to the users.

XmdvTool has been applied to a wide range of application areas, some of which are highlighted in our Case Studies. Some of these domains include remote sensing, financial, geochemical, census, and simulation data. We are always looking for new applications, so if you've had some success with the system in your domain, we'd love to hear from you. See our contact page and join our user group if you'd like to contribute something or get further information.

You can learn more details via the slides "XMDV Project Overview: 1997 to 2007 and Beyond".


1. Model-Driven Visual Analytics on Streams (NSF REPORT ): This project is supported by NSF under grant IIS-1117139. click to show/hide details

The objective of this proposed research is to design, develop, and assess visual analytics technology to support risk assessment and monitoring in an environment characterized by a) high-speed streaming data as well as vast archives of historical data, b) numerous competing or complementary models for capturing patterns of interest, and c) significant societal importance for achieving decisions swiftly. Our target applications are financial risk and fraud analysis, though the resulting technology should be broadly applicable across other domains and problems.

2. Managing Discoveries in Visual Analytics ( NSF REPORT ): This project is supported by NSF under grant IIS-0812027. Visit project webpage . click to show/hide details

The goal of this project is to develop technology in support of the visual analytics process. The complex process of analysis in domains from scientific discovery to homeland security consists of cycles of hypothesis generation, evidence gathering, evidence organization, and hypothesis resolution. The developed discovery management technology provides support, both visually and computationally, not only for all analysis stages in isolation, but also for tight integration among them. The computational infrastructure enables analysts to capture, visualize, manage, analyze, and interactively explore patterns and discoveries ("nuggets") of the visual analytics process. Tools for the modeling and management of nuggets and their complex interrelationships form the foundation of the infrastructure. Methods for nugget generation include explicit identification and confirmation by user, implicit capture based on analysis of user logs, and automated discovery using statistical and data mining techniques. Computational and interactive visual methods enable analysts to efficiently validate, annotate, classify, organize, and purge nuggets over time. Visual representations of hypotheses, evidence, and nuggets help analysts explore their data, manage their discoveries, and organize their reasoning processes. The resulting technology enables analysts from diverse domains ranging from biomedical discovery to homeland security to visually explore data, to form hypotheses, and to swiftly manage their discoveries as the exploration process proceeds. Project insights are infused back into an educational agenda using a rich repertoire of mechanisms, ranging from special-topics courses to undergraduate and K-12 project-based student activities.

3. Interactive Stream Views: Visual Analysis of Streaming Data (NSF REPORT ): This project is supported by NSF under grant CCF-0811510. click to show/hide details

Visualization is a critical component for data analysis and decision-making in a wide range of application areas, both for its ability to provide rich overviews and to permit users to rapidly uncover patterns and outliers. While significant research in information visualization has focused on supporting the process of scanning static data sets in search of patterns, applying visualization to the analysis of continuously streaming data remains a largely untapped opportunity. However, domains of significant societal impact, such as scientific discovery, homeland security, and health care, routinely have to process digital data streams of ever increasing scale and complexity in real-time, making the advancement of information visualization to effectively support such visual stream analysis of paramount importance. To address this problem, the investigators are developing a computational infrastructure, called Interactive Stream Views (ISV), to visualize, manage, analyze, and interactively explore real-time data streams. This research breaks new ground in the visualization of and interactions on high-volume streaming data taking screen, computation, and perceptual resource constraints into account for load control and multiresolution abstraction. In ISV, analysts express their interests as queries, either by selecting features in data views or by the explicit invocation of feature-extraction processes. Customized displays supported by powerful interactions present the results of these queries, highlighting their attributes and abstractions, while also linking them to their corresponding data. ISV enables specialists from diverse domains, such as vital sign monitoring and tactical movement tracking, to visually monitor and explore their data, increasing their effectiveness in making real-time decisions in areas of critical need and high impact.

4. Quality Space Visualization (NSF REPORT ): This project is supported by NSF under grant IIS-0414380. click to show/hide details

Visualization has been identified as a critical component in the process of interactive exploration and mining of complex data repositories. This project focuses on the issue of quality at all stages of the visual exploration process. Types of quality considered include quality of the data itself, including reliability, age and completeness; quality of the transformation of the data into aggregated data abstraction; quality of data querying process by controlling of quality-of-service of retrieved data; and quality of mapping of data attributes to graphical objects and their screen layout resulting in different perceptible structures and various degrees of clutter. To achieve a ground-breaking holistic approach towards handling quality across the visual exploration pipeline, this project develops at each stage: (1) Metrics and models for measuring and capturing quality; (2) Algorithms for quality optimization based on selected quality metrics; (3) Visualizations to convey quality information for both data and structure spaces; and (4) Interactive tools to enable the user to control the optimization processes and specify preferences when trade-offs exist. Intellectual merit involves the definition, calculation, optimization, and visual presentation of quality metrics and attributes of both the information content and the structure space at all stages of the visualization pipeline. The expected results will have an impact in the application domains that routinely perform exploratory data analysis. The resulting tools enable effective visual exploration by explicitly exposing and integrating the quality of the data, which, while often ignored in existing tools, can have a tremendous impact on the decision-making process..

The XmdvTool project has been supported by NSF under prior grants IIS-0119276, IIS-9732897 and IRIS-9729878.