this is for holding javascript data
Daniel Stanley Tan edited section_Proposed_Topic_for_Research__.tex
about 8 years ago
Commit id: 778156b90cbfa8b0718e3ac565a92cd635f39437
deletions | additions
diff --git a/section_Proposed_Topic_for_Research__.tex b/section_Proposed_Topic_for_Research__.tex
index 0e8e925..09e4302 100644
--- a/section_Proposed_Topic_for_Research__.tex
+++ b/section_Proposed_Topic_for_Research__.tex
...
\section{Proposed Topic for Research}
Figure 1: Envisioned flow of the interactive visualization tool.
The proposed topic seeks to explore how an algorithm for big data visualization might be developed that combines the desirable properties of the existing algorithms for data mining for big data. We aim to create an interactive visualization tool for big data that incorporates user feedback into the algorithm to give some degree of freedom for the user to manipulate the visualization to their preference, as shown in figure 1. Similar to how SOM, MDS, and PCA preserves neighborhoods, distances, and variances, this visualization too allows users to inject domain knowledge on their visualizations and preserve certain properties that they deem fit. A similar work was done on computer aided thinking \cite{sumi1997computer} where the thought spaces can be manipulated by the user to allow idea formulation. The concept can be related to the game of text twist where you can rearrange letters, which in their case are words, to discover patterns and formulate ideas that might not be obvious in some arrangements. The thought spaces can also be fixed to certain spaces and the rest of the points around the fixed points will position themselves with respect to these fixed points.
