The exploration and analysis of data mining methodologies is an important task for effective knowledge discovery, especially in today's heterogeneous information networks. Previously presented approaches for minin...
详细信息
ISBN:
(纸本)9781538672020
The exploration and analysis of data mining methodologies is an important task for effective knowledge discovery, especially in today's heterogeneous information networks. Previously presented approaches for mining optimization aim primarily at the improvements of time complexity, space complexity, accuracy, and robustness. We extend the state-of-the-art method by concentrating on user-availability and algorithm understandability. Specifically, we use Rankclus, a classic clustering algorithm as an example. After uncovering the unseen computing processes to be displayed in a visual form, the whole clustering processes are transparent to the users, which may help them more clearly and quickly understand how the algorithms are computed, how does each object influence one another. In addition, we use a density approach to intuitively simplify the discovery of data patterns, and through the visualized results, users can adjust algorithm parameters with or without professional training. Finally, we use another two visual techniques to improve the visualization quality: a heatmap matrix designed for checking the similarities of objects which are in the same cluster, and a DOItree implemented to further analyze the accuracy of the algorithms.
A fundamental challenge for time-varying volume dataanalysis and visualization is the lack of capability to observe and track data change or evolution in an occlusion-free, controllable, and adaptive fashion. In this...
详细信息
A fundamental challenge for time-varying volume dataanalysis and visualization is the lack of capability to observe and track data change or evolution in an occlusion-free, controllable, and adaptive fashion. In this paper, we propose to organize a time-varying data set into a hierarchy of states. By deriving transition probabilities among states, we construct a global map that captures the essential transition relationships in the time-varying data. We introduce the TransGraph, a graph-based representation to visualize hierarchical state transition relationships. The TransGraph not only provides a visual mapping that abstracts data evolution over time in different levels of detail, but also serves as a navigation tool that guides dataexploration and tracking. The user interacts with the TransGraph and makes connection to the volumetric data through brushing and linking. A set of intuitive queries is provided to enable knowledge extraction from time-varying data. We test our approach with time-varying data sets of different characteristics and the results show that the TransGraph can effectively augment our ability in understanding time-varying data.
Event sequences analysis plays an important role in many application domains such as customer behavior analysis, electronic health record analysis and vehicle fault diagnosis. Real-world event sequence data is often n...
详细信息
Event sequences analysis plays an important role in many application domains such as customer behavior analysis, electronic health record analysis and vehicle fault diagnosis. Real-world event sequence data is often noisy and complex with high event cardinality, making it a challenging task to construct concise yet comprehensive overviews for such data. In this paper. we propose a novel visualization technique based on the minimum description length (MDL) principle to construct a coarse-level overview of event sequence data while balancing the information loss in it. The method addresses a fundamental trade-off in visualization design: reducing visual clutter vs. increasing the information content in a visualization. The method enables simultaneous sequence clustering and pattern extraction and is highly tolerant to noises such as missing or additional events in the data. Based on this approach we propose a visual analytics framework with multiple levels-of-detail to facilitate interactive dataexploration. We demonstrate the usability and effectiveness of our approach through case studies with two real-world datasets. One dataset showcases a new application domain for event sequence visualization, i.e., fault development path analysis in vehicles for predictive maintenance. We also discuss the strengths and limitations of the proposed method based on user feedback.
The proceedings contain 50 papers. The topics discussed include: visualization of sub-network sets by iterative graph sampling from large scale networks;multidimensional datavisualization for investigation of skin tr...
ISBN:
(纸本)9781665438278
The proceedings contain 50 papers. The topics discussed include: visualization of sub-network sets by iterative graph sampling from large scale networks;multidimensional datavisualization for investigation of skin transparency;towards a visual approach for representing analytical provenance in exploration processes;automatic creation of a vowel dataset for performing prosody analysis in ASD screening;visual analytics to support industrial vehicle fleet planning;visualization tool to support fraud detection;real-time visualization reconstruction in a real-world environment using augmented reality;visually exploring a collaborative augmented reality taxonomy;a brief review of dashboard visualizations employed to support management or business decisions;and visualexploration of the inner representation learned by a convolutional neural network.
We present a system that combines ambient visualization, information retrieval and machine learning to facilitate the ease and quality of document classification by subject matter experts for the purpose of organizing...
详细信息
ISBN:
(纸本)9781728128382
We present a system that combines ambient visualization, information retrieval and machine learning to facilitate the ease and quality of document classification by subject matter experts for the purpose of organizing documents by "tags" inferred by the resultant classifiers. This system includes data collection, a language model, query exploration, feature selection, semi-supervised machine learning and a visual analytic workflow enabling non-data scientists to rapidly define, verify, and refine high-quality document classifiers.
Time series (such as stock prices) and ensembles (such as model runs for weather forecasts) are two important types of one-dimensional time-varying data. Such data is readily available in large quantities but visual a...
详细信息
Time series (such as stock prices) and ensembles (such as model runs for weather forecasts) are two important types of one-dimensional time-varying data. Such data is readily available in large quantities but visualanalysis of the raw data quickly becomes infeasible, even for moderately sized data sets. Trend detection is an effective way to simplify time-varying data and to summarize salient information for visual display and interactive analysis. We propose a geometric model for trend-detection in one-dimensional time-varying data, inspired by topological grouping structures for moving objects in two-or higher-dimensional space. Our model gives provable guarantees on the trends detected and uses three natural parameters: granularity, support-size, and duration. These parameters can be changed on-demand. Our system also supports a variety of selection brushes and a time-sweep to facilitate refined searches and interactive visualization of (sub-)trends. We explore different visual styles and interactions through which trends, their persistence, and evolution can be explored.
As high volumes of a wide variety of valuable data of different veracities can be easily generated or collected at a high velocity nowadays, big datavisualisation and visual analytics are in demand in various real-li...
详细信息
ISBN:
(纸本)9781538672020
As high volumes of a wide variety of valuable data of different veracities can be easily generated or collected at a high velocity nowadays, big datavisualisation and visual analytics are in demand in various real-life applications. Musical data are examples of big data. Embedded in these big data are useful information and valuable knowledge. Many existing big data mining algorithms return useful information and valuable knowledge in textual or tabular forms. Knowing that "a picture is worth a thousand words", big datavisualisation and visual analytics are also in demand. In this paper, we present a system for visualising and analysing big data. In particular, our system focuses on the big data science task of the discovery and exploration of frequent patterns (i.e., collections of items that frequently occurring together) from musical data. Evaluation results show the applicability of our system in big datavisualisation and visual analytics for music data mining.
C An important task in exploration of data about phenomena and processes that develop over time is detection of significant changes that happened to the studied phenomenon. Our research is focused on supporting detect...
详细信息
ISBN:
(纸本)9780769541655
C An important task in exploration of data about phenomena and processes that develop over time is detection of significant changes that happened to the studied phenomenon. Our research is focused on supporting detection of significant changes, called events, in multiple time series of numeric values. We developed a suite of visual analytics techniques that combines interactive visualizations on time-aware displays and maps with statistical event detection methods implemented in R. We demonstrate the utility of our approach using two large data sets.
Rhinologists are often faced with the challenge of assessing nasal breathing from a functional point of view to derive effective therapeutic interventions. While the complex nasal anatomy can be revealed by visual ins...
详细信息
Rhinologists are often faced with the challenge of assessing nasal breathing from a functional point of view to derive effective therapeutic interventions. While the complex nasal anatomy can be revealed by visual inspection and medical imaging, only vague information is available regarding the nasal airflow itself: Rhinomanometry delivers rather unspecific integral information on the pressure gradient as well as on total flow and nasal flow resistance. In this article we demonstrate how the understanding of physiological nasal breathing can be improved by simulating and visually analyzing nasal airflow, based on an anatomically correct model of the upper human respiratory tract. In particular we demonstrate how various Information visualization (InfoVis) techniques, such as a highly scalable implementation of parallel coordinates, time series visualizations, as well as unstructured grid multi-volume rendering, all integrated within a multiple linked views framework, can be utilized to gain a deeper understanding of nasal breathing. Evaluation is accomplished by visualexploration of spatio-temporal airflow characteristics that include not only information on flow features but also on accompanying quantities such as temperature and humidity. To our knowledge, this is the first in-depth visualexploration of the physiological function of the nose over several simulated breathing cycles under consideration of a complete model of the nasal airways, realistic boundary conditions, and all physically relevant time-varying quantities.
Learning more about people mobility is an important task for official decision makers and urban planners. Mobility data sets characterize the variation of the presence of people in different places over time as well a...
详细信息
Learning more about people mobility is an important task for official decision makers and urban planners. Mobility data sets characterize the variation of the presence of people in different places over time as well as movements (or flows) of people between the places. The analysis of mobility data is challenging due to the need to analyze and compare spatial situations (i.e., presence and flows of people at certain time moments) and to gain an understanding of the spatio-temporal changes (variations of situations over time). Traditional flow visualizations usually fail due to massive clutter. Modern approaches offer limited support for investigating the complex variation of the movements over longer time periods. We propose a visual analytics methodology that solves these issues by combined spatial and temporal simplifications. We have developed a graph-based method, called Mobility Graphs, which reveals movement patterns that were occluded in flow maps. Our method enables the visual representation of the spatio-temporal variation of movements for long time series of spatial situations originally containing a large number of intersecting flows. The interactive system supports dataexploration from various perspectives and at various levels of detail by interactive setting of clustering parameters. The feasibility our approach was tested on aggregated mobility data derived from a set of geolocated Twitter posts within the Greater London city area and mobile phone call data records in Abidjan, ivory Coast. We could show that Mobility Graphs support the identification of regular daily and weekly movement patterns of resident population.
暂无评论