VISUAL AND SPATIAL ANALYSIS:
Advances in Data Mining,
Reasoning and Problem Solving

Editors

Boris Kovalerchuk
Jim Schwing

Preface

Back Next

    Chapter 6 describes an iconic reasoning architecture for analysis and decision-making along with a storytelling iconic reasoning approach. The approach provides visuals for task identification, evidence, reasoning rules, links of evidence with pre-hypotheses, and evaluation of hypotheses. The iconic storytelling approach is consistent hierarchical reasoning that includes a variety of rules such as visual search-reasoning rules that are tools for finding confirming links. The chapter also provides a review of related work on iconic systems. The review discusses concepts and terminology, controversy in iconic language design, links between iconic reasoning and iconic languages and requirements for an efficient iconic system.

    Chapter 7 considers directions for visual reasoning and discovery. Currently, computer visualization is moving from a pure illustration domain to visual reasoning, discovery, and decisions making. This trend is associated with new terms such as visual data mining, visual decision making, and heterogeneous, iconic and diagrammatic reasoning. Beyond a new terminology, the trend itself is not new as the early history of mathematics clearly shows. This chapter demonstrates that we can learn valuable lessons from the history of mathematics for visual reasoning and discovery.

    Visual correlation is the thrust of Part 3, which consists of Chapters 8-10. Chapter 8 introduces the concept of visual correlation and describes the essence of a generalized correlation to be used for multilevel and conflicting data. Several categories of visual correlation are presented accompanied by both numeric and non-numeric examples with three levels (high, medium and low) of coordination. The chapter presents examples of multi-type visual correlaŽtions. The chapter also provides a classification of visual correlation methods with corresponding metaphors and criteria for visual correlation efficiency. The chapter finishes with a more formal treatment of visual correlation, providing formal definitions, analysis, and theory.

    Chapter 9 presents the state-of-the-art in iconic descriptive approaches to annotating, searching, and correlating that are based on the concepts of compound and composite icons, the iconic annotation process, and iconic queries. Specific iconic languages used for applications such as video annotation, military use and text annotation are discussed. Graphical coding principals are derived through the consideration of questions such as: How much information can a small icon convey? How many attributes can be displayed on a small icon either explicitly or implicitly? The chapter also summirizes impact of human perception on icon design.

    Chapter 10 addresses the problem of visually correlating objects and events. The new Bruegel visual correlation system based on an iconographic language that permits compact information representation is described. The description includes the Bruegel concept, functionality, the ability to compress information via iconic semantic zooming, and dynamic iconic sentences. The formal Bruegel iconic language for automatic icon generation is outlined. The chapter is devoted to case studies that describe how Bruegel iconic architecture can be used.

Back Next

 

Home

Overview

Table of Contents

Preface

Authors List

Links Page

Publisher Flyer

Springer (Buying Info)

Amazon.com (Buying Info)