Mastering the Information Age Solving Problems with Visual Analytics

Book Keim, D. A., Kohlhammer, J., Ellis, G., & Mansmann, F. (Eds, 2010). Mastering the information age-solving problems with visual analytics. Eurographics Association. Visual Analytics "Visual analytics combines automated analysis techniques with interactive visualizations for an effective understanding, reasoning and decision making on the basis of very large and complex data sets" Creating a tool and technique to enable people to: Synthesis information and derive insights from massive, dynamic ambiguous, and often conflicting data Detect the expected and discover the unexpected Provide timely defensible and understandable assessments Communicate these assessments effectively for action Data Management "One of the most exciting opportunities of the emerging Information Age is to extract useful findings from the immense wealth of data and information acquired, computed, and stored by modern information systems." Obstacles: Heterogeneity of Data Sources Different Data Types Data Streams Working Under Pressure Time Consuming Activities Issues obstructing Data Management and Visual Analytics Dynamicity Standards User Interaction Life Cycle Data Mining Examples of areas in which the visual analytics approach has been used together with Knowledge Discovery and Data Mining Bioinformatics Climate Change Pattern Identification Spatio-temperal Data Mining Research and Commercial Systems in Data Mining and Visualization: Statistical and mathematical tools (R, matlab) Specific algorithmic tools (Graphviz or Pajek) Visual Analytics Libraries (BirdEye) Visual Data Mining Tools (KNIME, Weka) Web tools and packages (MayEyes) Scientific Visualization Tools (Globus Toolkit) Combined Methods (JUNG, HCE) Computational Information Design Five categories of Grand Challenges: Analytical Reasoning Visual Representation and Interaction Techniques Data Representations and Transformation Production, Presentation and Dissemination Moving Research into Practice Space and Time "Maps not only help people to orient themselves in geographical space but also to gain an understanding of events and evolving phenomena and to make discoveries – indeed, much map use can be considered (geo)visual analysis." Specifics of Time and Space Dependencies between observations Uncertainty Scale Time State of the Art Representation of Space Representation of Time Interactive Methods of Visual Exploration Effectiveness of Visual Techniques Dealing with large data sets Collaborative Visualization Fundamental and Theoretical Research Next Steps Develop approaches to support analysts in finding satisfactory scales of analysis, exploring and establishing scale dependency, verifying discovered patterns and relationships at dierent scales and with dierent aggregations, and understanding dependencies between phenomena operating at dierent scales in time and space. Develop scalable visual analytics solutions to enable integrated processing and analysis of multiple diverse types of spatial, temporal, and spatiotemporal data and information, including measured data, model outputs, and action plans from diverse ocial and more uncertain community contributed sources. Improve the understanding of human perceptual and cognitive processes in dealing with spatial and temporal information and visual displays of and interaction with such information. On this basis, develop appropriate design rules and guidelines for interactive displays of spatial and temporal information. Develop effective solutions for training both specialist and non-specialist users interested in undertaking spatio-temporal analysis. Develop a new generation of lightweight accessible dynamic visual analytics tools to support a range of personal and professional spatio-temporal analysts in the best possible way. Implement tools for spatio-temporal visual analytics in the way that allows rapid and easy deployment or online use through the Web. Make the tools compliant with the existing and emerging standards, interoperable and combinable; enable integration of the tools into user’s existing workflows. Infrastructure Perception and Cognitive Aspects State of the Art Psychology of Perception and Cognition Distributed Congition Problem Solving Interaction User Evaluation Challenges General Public need tools to understand data in their own way Applying Psychological Theory to Real Applications Understanding the Analytical Process The need for design guidelines Defining the language of visual analytics Evaluation of Novel Designs Designing the Analyst Changing Interfaces: users, data and devices   Evaluation Evaluation include techniques, methods, modes and theories as well as software tools Quality, artefacts should be considered - the key aspects of quality are effectiveness, efficiency and user satisfaction Users Tasks Artefacts Data Recommendations Data - the challenge of dealing with very large, diverse, variable quality datasets Users - the challenge of meeting the needs of the user Design - the challenge of assisting designers of visual analytic systems Technology - the challenge of providing the necessary infrastructure