Title

Interactive Data Visualization Using Shifted Paired Coordinates

Document Type

Oral Presentation

Campus where you would like to present

Ellensburg

Event Website

https://digitalcommons.cwu.edu/source

Start Date

18-5-2020

Abstract

Multidimensional data are usually visualized by reducing the dimensionality of the data often leading to loss of information. One of the ways to overcome this problem is to represent the data using new Shifted Paired Coordinates (SPC) [Kovalerchuk, 2018] which represent the multidimensional data by a graph in the sequence of pairs of dimensions in the 2-dimensional plane. Interactive SPC is a software system that provides a medium for visualizing multidimensional (n-D) data in Shifted Paired Coordinate system without losing any information. This system is developed on Windows Forms in C++ and OpenGL library. It loads the data from a csv file and visualizes the data in SPC without any loss of information. Apart from the lossless representation of the n-D data, the system also provides user interactive controls like clicking and dragging the user selected graphs on the screen and reversing the user selected coordinates of the data to reorient the data representation according to user convenience. Also, this system provides a feature wherein the mean of the user selected data is calculated and redisplayed to visualize the data along the mean. These features help in better understanding of the data, especially when the data contain two or more classes. Additional options like zooming and panning are provided for user convenience for data exploration. Also, color selection functionality is given where the user can customize the color of data classes. This system works for real world data like iris, breast cancer data, ionosphere data etc.

Faculty Mentor(s)

Boris Kovalerchuk

Department/Program

Computer Sciences

This document is currently not available here.

Share

COinS
 
May 18th, 12:00 PM

Interactive Data Visualization Using Shifted Paired Coordinates

Ellensburg

Multidimensional data are usually visualized by reducing the dimensionality of the data often leading to loss of information. One of the ways to overcome this problem is to represent the data using new Shifted Paired Coordinates (SPC) [Kovalerchuk, 2018] which represent the multidimensional data by a graph in the sequence of pairs of dimensions in the 2-dimensional plane. Interactive SPC is a software system that provides a medium for visualizing multidimensional (n-D) data in Shifted Paired Coordinate system without losing any information. This system is developed on Windows Forms in C++ and OpenGL library. It loads the data from a csv file and visualizes the data in SPC without any loss of information. Apart from the lossless representation of the n-D data, the system also provides user interactive controls like clicking and dragging the user selected graphs on the screen and reversing the user selected coordinates of the data to reorient the data representation according to user convenience. Also, this system provides a feature wherein the mean of the user selected data is calculated and redisplayed to visualize the data along the mean. These features help in better understanding of the data, especially when the data contain two or more classes. Additional options like zooming and panning are provided for user convenience for data exploration. Also, color selection functionality is given where the user can customize the color of data classes. This system works for real world data like iris, breast cancer data, ionosphere data etc.

https://digitalcommons.cwu.edu/source/2020/COTS/51