by Chu, Hong Ki. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 75-79). / Abstracts in English and Chinese. / Acknowledgments --- p.ii / Abstract --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Problem Definitions --- p.3 / Chapter 1.2 --- Experimental Setup --- p.5 / Chapter 1.3 --- Outline of the thesis --- p.6 / Chapter 2 --- Survey on Previous Researches --- p.8 / Chapter 2.1 --- Association rules --- p.8 / Chapter 2.2 --- Clustering --- p.10 / Chapter 2.3 --- Motivation --- p.12 / Chapter 3 --- ID AN on discovering quantitative association rules --- p.16 / Chapter 3.1 --- Briefing --- p.17 / Chapter 3.2 --- A-Tree --- p.18 / Chapter 3.3 --- Insertion Algorithm --- p.25 / Chapter 3.4 --- Visualizing Association Rules --- p.28 / Chapter 4 --- ID AN on discovering patterns of clustering --- p.34 / Chapter 4.1 --- Briefing --- p.34 / Chapter 4.2 --- A-Tree --- p.36 / Chapter 4.3 --- Dimensionality Curse --- p.37 / Chapter 4.3.1 --- Discrete Fourier Transform --- p.38 / Chapter 4.3.2 --- Discrete Wavelet Transform --- p.40 / Chapter 4.3.3 --- Singular Value Decomposition --- p.42 / Chapter 4.4 --- IDAN - Algorithm --- p.45 / Chapter 4.5 --- Visualizing clustering patterns --- p.49 / Chapter 4.6 --- Comparison --- p.51 / Chapter 5 --- Performance Studies --- p.55 / Chapter 5.1 --- Association Rules --- p.55 / Chapter 5.2 --- Clustering --- p.58 / Chapter 6 --- Survey on data visualization techniques --- p.63 / Chapter 6.1 --- Geometric Projection Techniques --- p.64 / Chapter 6.1.1 --- Scatter-plot Matrix --- p.64 / Chapter 6.1.2 --- Parallel Coordinates --- p.65 / Chapter 6.2 --- Icon-based Techniques --- p.67 / Chapter 6.2.1 --- Chernoff Face --- p.67 / Chapter 6.2.2 --- Stick Figures --- p.68 / Chapter 6.3 --- Pixel-oriented Techniques --- p.70 / Chapter 6.4 --- Hierarchical Techniques --- p.72 / Chapter 7 --- Conclusion --- p.73 / Bibliography --- p.74

Data mining for patterns and knowledge discovery in multivariate datasets are very important processes and tasks to help analysts understand the dataset, describe the dataset, and predict unknown data values. However, conventional computer-supported data mining approaches often limit the user from getting involved in the mining process and performing interactions during the pattern discovery. Besides, without the visual representation of the extracted knowledge, the analysts can have difficulty explaining and understanding the patterns. Therefore, instead of directly applying automatic data mining techniques, it is necessary to develop appropriate techniques and visualization systems that allow users to interactively perform knowledge discovery, visually examine the patterns, adjust the parameters, and discover more interesting patterns based on their requirements. In the dissertation, I will discuss different proposed visualization systems to assist analysts in mining patterns and discovering knowledge in multivariate datasets, including the design, implementation, and the evaluation. Three types of different patterns are proposed and discussed, including trends, clusters of subgroups, and local patterns. For trend discovery, the parameter space is visualized to allow the user to visually examine the space and find where good linear patterns exist. For cluster discovery, the user is able to interactively set the query range on a target attribute, and retrieve all the sub-regions that satisfy the user's requirements. The sub-regions that satisfy the same query and are neareach other are grouped and aggregated to form clusters. For local pattern discovery, the patterns for the local sub-region with a focal point and its neighbors are computationally extracted and visually represented. To discover interesting local neighbors, the extracted local patterns are integrated and visually shown to the analysts. Evaluations of the three visualization systems using formal user studies are also performed and discussed.

This thesis presents two phases of research in applying visualization to network security challenges. The first phase included discovering the most useful and powerful features in existing computer security visualizations and incorporating them into the AdviseAid visualization platform, an existing software package. The incorporation of such a complete feature set required novel resolution of software engineering, human factors, and computer graphics issues. We also designed additional novel features, such as plugin interfaces, allowing for rapid prototyping and experimentation with novel visualization features and capabilities. The second phase of the research focused on the development of novel visualization techniques themselves. These novel visualizations were designed and created within AdviseAid to demonstrate that the features of AdviseAid are functional and helpful in the development process, as well as to be effective in the analysis of computer networks in their own right.

Nowadays a substantial trend occurs that vast amounts of geospatial data are supplied, managed, and processed over distributed GIS. It is important to provide users with the capability of visualising spatial data quality information in a meaningful way for distributed GIS, since it will significantly enhance user understanding of data quality and aid them in assessing the data fitness for their application requirements. This thesis investigates the issue of visualisation of spatial data quality for distributed GIS. Based on a review of core concepts associated with spatial data quality, metadata standards, and major research areas related to data quality, the limitations of current data quality presentation are highlighted. To overcome some of these limitations, the research topic of this thesis is proposed, namely, adding visualisation functionality to the presentation of spatial data quality to convey uncertainty information to users in an interactive and graphical manner. Based on a review of the theories on visualisation and the frameworks developed for visualisation of spatial data quality in literature, an extended framework is developed incorporating several aspects of visualisation such as contexts, contents, and techniques, where the hierarchical nature of data quality and error models are two main parts of the visualisation contents. A brief framework of visualisation of spatial data quality for distributed GIS is proposed, where data storage with quality information and web services for visualising data quality are two key components. To satisfy a series of requirements for representing spatial data quality, a new object-oriented data model is proposed based on the review of developments of data models. This data model can specifically deal with the hierarchical nature of data quality and error propagation, recognising data quality as a dynamic process. Further, The implementation of the data model using GML and SVG is discussed. The details of a web service for visualising spatial data quality are addressed. After proposing the requirements on building a system for spatial data quality visualisation for distributed GIS, the design of a prototype visualisation system for distributed GIS is addressed in detail. The prototype visualisation system for spatial data quality is developed and implemented with an example data set, where SVG and JavaScript are used to illustrate how various graphic methods such as animation, data quality filters, and colour gradients can be used for distributed GIS. In addition to the visualisation of positional accuracy at the feature level, in this pilot system, the hierarchical structure of data quality information is also presented. Limitations of the research in this thesis are also addressed. However, in general, this research is of great significance for the contributions made to a relatively new research area in terms of theories, procedures, and software developments.

In this survey article, we review glyph-based visualization techniques, which have been exploited when visualizing spatial multivariate medical data. To classify these techniques, we derive a taxonomy of glyph properties, which is based on classification concepts established in information visualization. By considering both the glyph visualization as well as the interaction techniques that are employed to generate or explore the glyph visualization, we are able to classify glyph techniques into two main groups: those supporting pre-attentive and those supporting attentive processing. With respect to this classification, we review glyph-based techniques described in the medical visualization literature. Based on the outcome of the literature review, we propose design guidelines for glyph visualizations in the medical domain.

Many large scale simulations now produce datasets that are signi cantly larger than can typically be stored in memory on a visualization system. Visualization algorithms then become ine ective and stall since the data must be paged to disk. Recently, in-situ visualization has received renewed attention for visualizing large datasets that are distributed among many processors during a simulation. It takes advantage of the fact that the full dataset is already in main memory, distributed among multiple processors. Visualization in this environment then requires communication which can be more expensive than disk access. The goal of this thesis was to develop an in-situ visualization technique using ray tracing that employs ray caches to reduce communication overhead. Ray caches attempt to replace a communication operation with a less expensive cache search operation. A prototype implemented on Sharcnet shows ray caching can signi cantly improve overall performance at a small cost to image quality. / UOIT

The radiation field visualization options available for engineers, scientists and health physicists have traditionally been based in the 2d realm, with techniques such as the generation of isodose curves. From the perspective of a health physicist the creation of 3d visuals to illustrate radiation levels within an environment is an invaluable tool both for training and As Low As Reasonably Achievable (ALARA) radiation dose planning. This thesis describes a novel technique for the creation of 3d visualizations of radiation fields. The methodology is developed and shown to be effective within the Google SketchUp Computer Aided Design (CAD) software package. The methodology takes an input file of information stored in coordinate form with a representative value at each point. It constructs elemental shapes automatically within Google SketchUp at those coordinates. All shapes are associated with an intensity value related to a pre-defined scale. The shapes are colorized and enhanced with transparency effects to complete a radiation field visualization scene. / UOIT

In this study, crystal formation of polypropylene (PP) and poly lactic acid (PLA) in the presence of CO2 in foam extrusion process was investigated using a visualization chamber and a CCD camera. The role of pre-existing crystals on the foaming behavior of PP and PLA were studied by characterizing the foam morphology. Visualization results showed that crystals formed within the die before foaming and these crystals affect the cell nucleation behavior and expansion ratio of PP and PLA significantly. Due to the fast crystallization kinetics of PP, crystallinity should be optimum to achieve uniform cell structure with high cell density and high expansion ratio. In PLA, enhancement of crystallinity is crucial for getting foam with a high expansion ratio. It was also visualized that CO2 significantly suppresses the crystallization temperature in PP through the plasticization effect as well as its influence on flow induced crystallinity.

In this study, crystal formation of polypropylene (PP) and poly lactic acid (PLA) in the presence of CO2 in foam extrusion process was investigated using a visualization chamber and a CCD camera. The role of pre-existing crystals on the foaming behavior of PP and PLA were studied by characterizing the foam morphology. Visualization results showed that crystals formed within the die before foaming and these crystals affect the cell nucleation behavior and expansion ratio of PP and PLA significantly. Due to the fast crystallization kinetics of PP, crystallinity should be optimum to achieve uniform cell structure with high cell density and high expansion ratio. In PLA, enhancement of crystallinity is crucial for getting foam with a high expansion ratio. It was also visualized that CO2 significantly suppresses the crystallization temperature in PP through the plasticization effect as well as its influence on flow induced crystallinity.

Mobile devices, such as smartphones and other personal devices, are increasingly used to view maps and other large datasets. Their necessarily small displays can only show a small portion of the data at one time. Researchers have developed various visual techniques that overlay icons or shapes onto the edge of the display to provide the user with hints regarding the existence and location of undisplayed points of interest. However, current techniques fail in practice on mobile devices because they are confusing, do not scale or take up too much valuable screen space. In this thesis, I describe a new technique to visualize the location of off-screen points of interest. This technique, called Wedge, addresses specific shortcomings of existing techniques. This thesis details the design and implementation of Wedge and summarizes the results of a thorough experimental evaluation. Furthermore, I present a preliminary model of user performance that I use to highlight design suggestions for practitioners using Wedge. / February 2009