zoukankan      html  css  js  c++  java
  • PP: Pattern Trails: visual analysis of pattern transitions in subspaces

    Problem:

    1. We can't find patterns in full attribute space, and patterns may only be found in smaller subspaces. 

    2. Pattern Trails is an interactive visual approach for the exploration of subspaces of multivariate data

    Related work

    1. Multivariate data analysis and visualization

    parallel coordinate plots; pixel bar charts; Chernoff faces.

    2. using dimensionality reduction for visual analysis

     MDS: multidimensional scaling;

    PCA: principal component analysis; 

    t-SNE: t-distributed stochastic neighbor embedding;

    SOM: self-organizing maps

    3. Subspace search and visualization

    Methodology

    1. Derive interesting subspaces of the multivariate data

    Supplementary knowledge

    1. what are subspace patterns and subspace analysis. 

    2. The main task in understanding such multivariate data is to identify and interpret relevant patterns like dense groups (clusters), outliers, or correlations.

    3. Techniques for visually exploring multivariate data:

    Parallel Coordinate Plots;

    dimensionality reduction降维; to transform the data to a lower-dimensional space but preserving the main structure of the data. 

    4. Chernoff Faces

    5. 

  • 相关阅读:
    《人件》阅读笔记五
    《人件》阅读笔记四
    《人件》阅读笔记三
    《人件》阅读笔记二
    《人件》阅读笔记一
    年报系统课堂讨论记录
    系统利益相关者描述案例
    Android开发学习记录--活动生命周期
    jQuery AJAX简介
    jQuery HTML简介
  • 原文地址:https://www.cnblogs.com/dulun/p/12194732.html
Copyright © 2011-2022 走看看