An information-theoretic framework for flow visualization

The process of visualization can be seen as a visual communication channel where the input to the channel is the raw data, and the output is the result of a visualization algorithm. From this point of view, we can evaluate the effectiveness of visualization by measuring how much information in the original data is being communicated through the visual communication channel. In this paper, we present an information-theoretic framework for flow visualization with a special focus on streamline generation. In our framework, a vector field is modeled as a distribution of directions from which Shannon's entropy is used to measure the information content in the field. The effectiveness of the streamlines displayed in visualization can be measured by first constructing a new distribution of vectors derived from the existing streamlines, and then comparing this distribution with that of the original data set using the conditional entropy. The conditional entropy between these two distributions indicates how much information in the original data remains hidden after the selected streamlines are displayed. The quality of the visualization can be improved by progressively introducing new streamlines until the conditional entropy converges to a small value. We describe the key components of our framework with detailed analysis, and show that the framework can effectively visualize 2D and 3D flow data.     

A unifying information-theoretic framework for independent component analysis

We show that different theories recently proposed for independent component analysis (ICA) lead to the same iterative learning algorithm for blind separation of mixed independent sources. We review those theories and suggest that information theory can be used to unify several lines of research. Pearlmutter and Parra [1] and Cardoso [2] showed that the infomax approach of Bell and Sejnowski [3] and the maximum likelihood estimation approach are equivalent. We show that negentropy maximization also has equivalent properties, and therefore, all three approaches yield the same learning rule for a fixed nonlinearity. Girolami and Fyfe [4] have shown that the nonlinear principal component analysis (PCA) algorithm of Karhunen and Joutsensalo [5] and Oja [6] can also be viewed from information-theoretic principles since it minimizes the sum of squares of the fourth-order marginal cumulants, and therefore, approximately minimizes the mutual information [7]. Lambert [8] has proposed different Bussgang cost functions for multichannel blind deconvolution. We show how the Bussgang property relates to the infomax principle. Finally, we discuss convergence and stability as well as future research issues in blind source separation.     

An object-oriented framework for medical image registration, fusion, and visualization

An object-oriented framework for image registration, fusion, and visualization was developed based on the classic model-view-controller paradigm. The framework employs many design patterns to facilitate legacy code reuse, manage software complexity, and enhance the maintainability and portability of the framework. Three sample applications built a-top of this framework are illustrated to show the effectiveness of this framework: the first one is for volume image grouping and re-sampling, the second one is for 2D registration and fusion, and the last one is for visualization of single images as well as registered volume images.     

An information-theoretic method for multimodality medical image registration

In this paper, an information-theoretic approach for multimodal image registration is presented. In the proposed approach, image registration is carried out by maximizing a Tsallis entropy-based divergence using a modified simultaneous perturbation stochastic approximation algorithm. This divergence measure achieves its maximum value when the conditional intensity probabilities of the transformed target image given the reference image are degenerate distributions. Experimental results are provided to demonstrate the registration accuracy of the proposed approach in comparison to existing entropic image alignment techniques. The feasibility of the proposed algorithm is demonstrated on medical images from magnetic resonance imaging, computer tomography, and positron emission tomography.     

Designing a visualization framework for multidimensional data

Interest in visualization has grown in recent years, producing rapid advances in the diversity of research and in the scope of proposed techniques. Much of the initial focus in computer-based visualization concentrated on display algorithms, often for specific domains. For example, volume, flow, and terrain visualization techniques have generated significant insights into fundamental graphics and visualization theory, aiding the application experts who use these techniques to advance their own research. More recent work has extended visualization to abstract data sets like network intrusion detection, recommender systems, and database query results. This article describes our initial end-to-end system that starts with data management and continues through assisted visualization design, display, navigation, and user interaction. The purposes of this discussion are to (i) promote a more comprehensive visualization framework; (ii) describe how to apply expertise from human psychophysics, databases, rational logic, and artificial intelligence to visualization; and (iii) illustrate the benefits of a more complete framework using examples from our own experiences.     

Data stream visualization framework for smart cities

Monitoring smart cities is a key challenge due the variety of data streams generated from different process (traffic, human dynamics, pollution, energy supply, water supply, etc.). All these streams show us what is happening and as to where and when in the city. The purpose of this paper was to apply different types of glyphs for showing real-time stream evolution of data gathered in the city. The use of glyphs is intended to make the most out of the human capacity for detecting visual patterns.     

A model and framework for visualization exploration

Visualization exploration is the process of extracting insight from data via interaction with visual depictions of that data. Visualization exploration is more than presentation; the interaction with both the data and its depiction is as important as the data and depiction itself. Significant visualization research has focused on the generation of visualizations (the depiction); less effort has focused on the exploratory aspects of visualization (the process). However, without formal models of the process, visualization exploration sessions cannot be fully utilized to assist users and system designers. Toward this end, we introduce the P-Set model of visualization exploration for describing this process and a framework to encapsulate, share, and analyze visual explorations. In addition, systems utilizing the model and framework are more efficient as redundant exploration is avoided. Several examples drawn from visualization applications demonstrate these benefits. Taken together, the model and framework provide an effective means to exploit the information within the visual exploration process     

behaviorism: a framework for dynamic data visualization

While a number of information visualization software frameworks exist, creating new visualizations, especially those that involve novel visualization metaphors, interaction techniques, data analysis strategies, and specialized rendering algorithms, is still often a difficult process. To facilitate the creation of novel visualizations we present a new software framework, behaviorism, which provides a wide range of flexibility when working with dynamic information on visual, temporal, and ontological levels, but at the same time providing appropriate abstractions which allow developers to create prototypes quickly which can then easily be turned into robust systems. The core of the framework is a set of three interconnected graphs, each with associated operators: a scene graph for high-performance 3D rendering, a data graph for different layers of semantically linked heterogeneous data, and a timing graph for sophisticated control of scheduling, interaction, and animation. In particular, the timing graph provides a unified system to add behaviors to both data and visual elements, as well as to the behaviors themselves. To evaluate the framework we look briefly at three different projects all of which required novel visualizations in different domains, and all of which worked with dynamic data in different ways: an interactive ecological simulation, an information art installation, and an information visualization technique.     

An information-theoretic treatment of passive haptic media

Haptic rendering has been long considered as the process of estimating the force that stems from the interaction of a user and an object. Even if this approach follows the principles of natural haptic interaction, it places severe limitations in processing haptic media. This paper presents an information theoretic framework that aims to provide a new view of haptic rendering that can accommodate for open-loop synthetic haptic media, where interaction-based rendering is a special case. As a result, using the proposed information-theoretic approach, the haptic signal can be precomputed as a force field, stored and then filtered by taking into account device and perceptual capabilities of the receiver in order to lower the required bandwidth of the resulting stream, thus opening new possibilities for the representation and processing of haptic media.     

An information-theoretic view of visual analytics.

Visual analytics is an emerging discipline that helps connect dots. It facilitates analytical reasoning and decision making through integrated and highly interactive visualization of complex and dynamic data and situations. Solving mysteries is only part of the game. Visual analytics must augment analyst and decision-maker capabilities to assimilate complex situations and reach informed decisions. In information theory, the information value carried by a message is the difference in information entropy before and after receipt of the message. Information entropy is a macroscopic measure of uncertainty defined on a frequency or probability distribution. The information-theoretical approach attempts to quantify discrepancies of the information content of distributions.     

An adaptive spatial information-theoretic fuzzy clustering algorithm for image segmentation

This paper presents an adaptive spatial information-theoretic fuzzy clustering algorithm to improve the robustness of the conventional fuzzy c-means (FCM) clustering algorithms for image segmentation. This is achieved through the incorporation of information-theoretic framework into the FCM-type algorithms. By combining these two concepts and modifying the objective function of the FCM algorithm, we are able to solve the problems of sensitivity to noisy data and the lack of spatial information, and improve the image segmentation results. The experimental results have shown that this robust clustering algorithm is useful for MRI brain image segmentation and it yields better segmentation results when compared to the conventional FCM approach.     

An information-theoretic evaluation of narrative complexity for interactive writing support

Narrative complexity should be managed systematically during the creation process because it heavily influences the levels of understanding and the interest of recipients. Existing research has tended to depend on impressionist criticism or to deal with narrative complexity at general and superficial levels. In this paper, we consider the creation and acceptance of narrative as information processing mediated by a narrative text. Under this assumption, we propose a method to quantitatively evaluate narrative complexity at the recipient's cognitive level, and to effectively utilize the evaluation to aid in the author's narrative creation process. Within our knowledge distribution model, a narrative is represented as a knowledge structure, and the knowledge state and knowledge flow of narrative agents are evaluated using a probabilistic reasoning model. From the knowledge flows, the amount of information processed and required by the recipient is calculated as a measure of the narrative complexity using entropy theory. As a case study, we conduct a comparative analysis of an actual cinematic narrative and a structurally manipulated version of that narrative to show how the method captures characteristics and changes of the narrative; we also discuss the improvements presented in this paper as compared to our previous research.     

An information-theoretic approach to combining object models

This paper introduces a new method for combining different object models. By determining a configuration of the models, which maximizes their mutual information, the proposed method creates a unified hypothesis from multiple object models on the fly without prior training. To validate the effectiveness of the proposed method, experiments are conducted in which human faces are detected and localized in images by combining different face models.     

A bidirectional-transformation-based framework for software visualization and visual editing

Software visualization and visual editing are important and practical techniques to improve the development of complex software systems. A challenge when applying the two technologies is how to realize the correspondence, a bidirectional relationship, between the data and its visual representation correctly. Although many tools and frameworks have been developed to support the construction of visual tools, it is still compli- cated and error-prone to realize the bidirectional relationship. In this paper, we propose a model-driven and bidirectional-transformation-based framework for data visualization and visual editing. Our approach mainly focuses on 1） how to define and manage graphical symbols in the model form and 2） how to specify and im- plement the bidirectional relationship based on the technique of bidirectional model transformation. Then, a prototype tool and four case studies are presented to evaluate the feasibility of our work.     

Distributed cognition as a theoretical framework for information visualization

Even though information visualization (InfoVis) research has matured in recent years, it is generally acknowledged that the field still lacks supporting, encompassing theories. In this paper, we argue that the distributed cognition framework can be used to substantiate the theoretical foundation of InfoVis. We highlight fundamental assumptions and theoretical constructs of the distributed cognition approach, based on the cognitive science literature and a real life scenario. We then discuss how the distributed cognition framework can have an impact on the research directions and methodologies we take as InfoVis researchers. Our contributions are as follows. First, we highlight the view that cognition is more an emergent property of interaction than a property of the human mind. Second, we argue that a reductionist approach to study the abstract properties of isolated human minds may not be useful in informing InfoVis design. Finally we propose to make cognition an explicit research agenda, and discuss the implications on how we perform evaluation and theory building.     

An information-theoretic approach to quantitative association rule mining

Quantitative association rule (QAR) mining has been recognized an influential research problem over the last decade due to the popularity of quantitative databases and the usefulness of association rules in real life. Unlike boolean association rules (BARs), which only consider boolean attributes, QARs consist of quantitative attributes which contain much richer information than the boolean attributes. However, the combination of these quantitative attributes and their value intervals always gives rise to the generation of an explosively large number of itemsets, thereby severely degrading the mining efficiency. In this paper, we propose an information-theoretic approach to avoid unrewarding combinations of both the attributes and their value intervals being generated in the mining process. We study the mutual information between the attributes in a quantitative database and devise a normalization on the mutual information to make it applicable in the context of QAR mining. To indicate the strong informative relationships among the attributes, we construct a mutual information graph (MI graph), whose edges are attribute pairs that have normalized mutual information no less than a predefined information threshold. We find that the cliques in the MI graph represent a majority of the frequent itemsets. We also show that frequent itemsets that do not form a clique in the MI graph are those whose attributes are not informatively correlated to each other. By utilizing the cliques in the MI graph, we devise an efficient algorithm that significantly reduces the number of value intervals of the attribute sets to be joined during the mining process. Extensive experiments show that our algorithm speeds up the mining process by up to two orders of magnitude. Most importantly, we are able to obtain most of the high-confidence QARs, whereas the QARs that are not returned by MIC are shown to be less interesting.     

A regularized graph layout framework for dynamic network visualization

Many real-world networks, including social and information networks, are dynamic structures that evolve over time. Such dynamic networks are typically visualized using a sequence of static graph layouts. In addition to providing a visual representation of the network structure at each time step, the sequence should preserve the mental map between layouts of consecutive time steps to allow a human to interpret the temporal evolution of the network. In this paper, we propose a framework for dynamic network visualization in the on-line setting where only present and past graph snapshots are available to create the present layout. The proposed framework creates regularized graph layouts by augmenting the cost function of a static graph layout algorithm with a grouping penalty, which discourages nodes from deviating too far from other nodes belonging to the same group, and a temporal penalty, which discourages large node movements between consecutive time steps. The penalties increase the stability of the layout sequence, thus preserving the mental map. We introduce two dynamic layout algorithms within the proposed framework, namely dynamic multidimensional scaling and dynamic graph Laplacian layout. We apply these algorithms on several data sets to illustrate the importance of both grouping and temporal regularization for producing interpretable visualizations of dynamic networks.     

IDSRadar: a real-time visualization framework for IDS alerts

Intrusion Detection Systems(IDS) is an automated cyber security monitoring system to sense malicious activities.Unfortunately,IDS often generates both a considerable number of alerts and false positives in IDS logs.Information visualization allows users to discover and analyze large amounts of information through visual exploration and interaction efficiently.Even with the aid of visualization,identifying the attack patterns and recognizing the false positives from a great number of alerts are still challenges.In this paper,a novel visualization framework,IDSRadar,is proposed for IDS alerts,which can monitor the network and perceive the overall view of the security situation by using radial graph in real-time.IDSRadar utilizes five categories of entropy functions to quantitatively analyze the irregular behavioral patterns,and synthesizes interactions,filtering and drill-down to detect the potential intrusions.In conclusion,IDSRadar is used to analyze the mini-challenges of the VAST challenge 2011 and 2012.     

Zone analysis: a visualization framework for classification problems

There have been large attempts to adopt the bias-variance framework from the regression problems to the classification problems. However, recently, it has been shown that only non-straightforward extensions exist for classification problems. In this paper, we present an alternative visualization framework for classification problems called zone analysis. Our zone analysis framework partly extends the bias-variance idea; instead of decomposing an error into two parts, i.e. the biased and unbiased components, our framework decomposes the error into K components. While bias-variance information is still contained in our framework, our framework provides interesting observations which are not obviously seen in the previous bias-variance framework, e.g. a prejudice behavior of the bagging algorithm to various unbiased instances. Our framework is suitable for visualizing an effect of context changes on learning performance. The type of context changes which we primarily investigate in the paper is “a change from a base learner to an ensemble learner such as bagging, adaboost, arc-x4 and multi-boosting”.