Learning Management Systems (LMSs) store different kinds of e-learning related data, whose analysis is important for monitoring students' learning processes and for helping detection of potential problems on these...
详细信息
ISBN:
(纸本)9780769529165
Learning Management Systems (LMSs) store different kinds of e-learning related data, whose analysis is important for monitoring students' learning processes and for helping detection of potential problems on these processes. Different researches apply Information visualization concepts and techniques for graphically and interactively presenting LMS data for analysis. Nonetheless, these researches show data obtained by predefined database queries, which fit only specific analysis situations, in despite of unforeseen situations derived from final user's knowledge about e-learning domain. Taking into account these situations, this paper presents a solution that enable LMS users to define database attributes they want to analyze, without need to know the internal organization of LMS database. Selected attributes are treated as a universal relation query and, after executed, query results are automatically converted into interactive graphical representations, avoiding user's concern with selecting the more adequate chart.
The proceedings contain 13 papers. The topics discussed include: coordinated parallel views for the exploratory analysis of microarray time-course data;MUSA-a prototype for multiple-step aggregation visualization;spri...
详细信息
ISBN:
(纸本)076952396X
The proceedings contain 13 papers. The topics discussed include: coordinated parallel views for the exploratory analysis of microarray time-course data;MUSA-a prototype for multiple-step aggregation visualization;spring view: cooperation of Radviz and parallel coordinates for view optimization and clutter reduction;multiple views to support engineering change management for complex products;visual dataanalysis using tracked statistical measures within parallel coordinate representations;interactive visual analysis of multi-parameter families of function graphs;exploration of dimensionality reduction for text visualization;a collaborative multi-view virtual environment for molecular visualization and modeling;prism: a multi-view visualization tool for multi-physics simulation;interactive exploration of unsteady 3-D flow with linked 2-D/3-D texture advection;and space-scale animation: enhancing cross-scale understanding of multiscale structures in multiple views.
The Self-Organizing Map is one of most prominent tools for the analysis and visualization of high-dimensional data. We propose a novel visualization technique for Self-Organizing Maps which can be displayed either as ...
详细信息
ISBN:
(纸本)3540260765
The Self-Organizing Map is one of most prominent tools for the analysis and visualization of high-dimensional data. We propose a novel visualization technique for Self-Organizing Maps which can be displayed either as a vector field where arrows point to cluster centers, or as a plot that stresses cluster borders. A parameter is provided that allows for visualization of the cluster structure at different levels of detail. Furthermore, we present a number of experimental results using standard data mining benchmark data.
We describe the visualization of high dimensional marketing data for a financial asset management company. The data typically consists of 30 to a 100 variables of 25000 to half a million clients. We use the visualizat...
详细信息
ISBN:
(纸本)0769523978
We describe the visualization of high dimensional marketing data for a financial asset management company. The data typically consists of 30 to a 100 variables of 25000 to half a million clients. We use the visualization of the correlation matrix as a variable selection tool which makes it easier to find patterns in the data. The user can then select data ranges of the selected variables and start a cluster analysis using 5 variables. The clustered data are then visualized as a set of spheres. In an additional visualization we first sort data values of a client variable and then visualize the sorted cubic data in a cube using volume rendering and isosurfaces. The interactive correlation visualization allows marketing researchers to quickly explore all kinds of combinations of variables, which enables them to find valuable client behavior patterns much faster. The cluster visualization allowed researchers to identify detailed groups of customer with similar behavior. Additionally, the visualization of the sorted cubic data gives in dept information of one variable over the total sample of customers. With these visualizations, a better understanding is given on customer behavior.
When used for visualization of high dimensional data, the self-organizing maps (SOM) requires a coloring scheme, or interpolation, or applying some projection techniques to analyze the intrinsic structure of the data....
详细信息
ISBN:
(纸本)3540287523
When used for visualization of high dimensional data, the self-organizing maps (SOM) requires a coloring scheme, or interpolation, or applying some projection techniques to analyze the intrinsic structure of the data. Even so, the structures of the data clusters may not be apparent and their shapes are often distorted. In order to overcome some shortcomings of the traditional SOM visualization method a novel technique is presented in this paper. Several experimental data sets including the chain-link problem and IRIS data are used to test the approach. The analysis results prove that the presented technique provides a better picture of the high dimensional data to understand their intrinsic structure.
A method for measuring the density of data sets that contain an unknown number of clusters of unknown sizes is proposed. This method, called Pareto Density Estimation (PDE), uses hyper spheres to estimate data density...
详细信息
ISBN:
(纸本)3540256776
A method for measuring the density of data sets that contain an unknown number of clusters of unknown sizes is proposed. This method, called Pareto Density Estimation (PDE), uses hyper spheres to estimate data density. The radius of the hyper spheres is derived from information optimal sets. PDE leads to a tool for the visualization of probability density distributions of variables (PDEplot). For Gaussian mixture data this is an optimal empirical density estimation. A new kind of visualization of the density structure of high dimensional data set, the P-Matrix is defined. The P-Matrix for a 79- dimensional data set from DNA array analysis is shown. The P-Matrix reveals local concentrations of data points representing similar gene expressions. The P-Matrix is also a very effective tool in the detection of clusters and outliers in data sets.
In this paper, we investigate a method of using principal component analysis(PCA) to fit an encapsulating ellipse to the image of a hypothetically ellipsoidal object. This technique is aimed at applications such as fr...
详细信息
ISBN:
(纸本)8090310079
In this paper, we investigate a method of using principal component analysis(PCA) to fit an encapsulating ellipse to the image of a hypothetically ellipsoidal object. This technique is aimed at applications such as fruit sorting, where resource constraints and speed requirements necessitate the approximation of data. Copyright UNION Agency-Science Press.
Significant advances have been made to non-intrusive flow field diagnostics in the past decade. Camera based techniques are now capable of determining physical qualities such as surface deformation, surface pressure a...
详细信息
This paper proposes a new experimental framework within which evidence regarding the perceptual characteristics of a visualization method can be collected, and describes how this evidence can be explored to discover p...
详细信息
This paper proposes a new experimental framework within which evidence regarding the perceptual characteristics of a visualization method can be collected, and describes how this evidence can be explored to discover principles and insights to guide the design of perceptually near-optimal visualizations. We make the case that each of the current approaches for evaluating visualizations is limited in what it can tell us about optimal tuning and visual design. We go on to argue that our new approach is better suited to optimizing the kinds of complex visual displays that are commonly created in visualization. Our method uses human-in-the-loop experiments to selectively search through the parameter space of a visualization method, generating large databases of rated visualization solutions. data mining is then used to extract results from the database, ranging from highly specific exemplar visualizations for a particular data set, to more broadly applicable guidelines for visualization design. We illustrate our approach using a recent study of optimal texturing for layered surfaces viewed in stereo and in motion. We show that a genetic algorithm is a valuable way of guiding the human-in-the-loop search through visualization parameter space. We also demonstrate several useful data mining methods including clustering, principal component analysis, neural networks, and statistical comparisons of functions of parameters.
For the visualization of abstract information with spatial dependencies, the combination of icon representations with maps is widely accepted. However, with an increasing amount of data creating complete, yet not over...
详细信息
ISBN:
(纸本)8090310079
For the visualization of abstract information with spatial dependencies, the combination of icon representations with maps is widely accepted. However, with an increasing amount of data creating complete, yet not overloaded, visualizations becomes evermore difficult. Effective interaction methods are therefore needed to discover hidden information in these pictures. Lens techniques offer the potential to efficiently combine proven methods from cartography and information visualization. Such techniques are not yet exploited sufficiently, exemplified by how little effort has been made so far in even systematizing lenses used in different fields. This paper introduces a common classification scheme that integrates known techniques and provides points of departure for new approaches. Derived from this work, a novel lens technique for the explorative analysis of maps is presented. The effectiveness of the proposed lens is demonstrated in an existing system for the visualization of health data. Copyright UNION Agency - Science Press.
暂无评论