Interactive Multiscale Visualization of Large, Multi-dimensional Datasets

Abstract: This thesis project set out to find and implement a comfortable way to explore vast, multidimensional datasets using interactive multiscale visualizations to combat the ever-growing information overload that the digitized world is generating. Starting at the realization that even for people not working in the fields of information visualization and data science the size of interesting datasets often outgrows the capabilities of standard spreadsheet applications such as Microsoft Excel. This project established requirements for a system to overcome this problem. In this thesis report, we describe existing solutions, related work, and in the end designs and implementation of a working tool for initial data exploration that utilizes novel multiscale visualizations to make complex coherences comprehensible and has proven successful in a practical evaluation with two case studies.