Decreasing Occlusion and Increasing Explanation in Interactive Visual Knowledge Discovery

Lack of explanation and occlusion are the major problems for interactive visual knowledge discovery, machine learning and data mining in multidimensional data. This thesis proposes a hybrid method that combines visual and analytical means to deal with these problems. This method, denoted as FSP, uses visualization of n-D data in 2-D in a set of Shifted Paired Coordinates (SPC). SPC for n-D data consists of n/2 pairs of Cartesian coordinates that are shifted relative to each other to avoid their overlap. Each n-D point is represented as a directed graph in SPC. It is shown that the FSP method simplifies pattern discovery in n-D data providing explainable rules in a visual form with significantly decrease of the cognitive load for analysis of n-D data. The computational experiments on real data has shown its efficiency on both training and validation data.

Name thesis:degree_name

Master of Science (MS)

Discipline thesis:degree_discipline

Computational Science

Year

2018

Author dc:creator

• Gharawi, Abdulrahman Ahmed

Contributors dc:contributor

• Boris Kovalerchuk
• Razvan Andonie
• Szilárd Vajda

• Visual Knowledge Discovery
• Visual Analytics
• Visual Data Mining
• Occlusion
• Interactive Visualization
• Shifted Paired Coordinates
• Artificial Intelligence and Robotics
• Graphics and Human Computer Interfaces

Language dc:language

English

Repository record dc:identifier

https://digitalcommons.cwu.edu/etd/941

OAI identifier oai:identifier

oai:digitalcommons.cwu.edu:etd-1969