VisuaLyzer : an approach for rapid visualization and analysis of epidemiological data

The ability to capture, store, and manage massive amounts of data is changing virtually every aspect of science, technology, and medicine. This new 'data age' calls for innovative methods to mine and interact with information. VisuaLyzer is a platform designed to identify and investigate meaningful relationships between variables within large datasets through rapid, dynamic, and intelligent data exploration. VisuaLyzer uses four key steps in its approach: 1. Data management: Enabling rapid and robust loading, managing, combining, and altering of multiple databases using a customized database management system. 2. Exploratory Data Analysis: Applying existing and novel statistics and machine learning algorithms to identify and quantify all potential associations among variables across datasets, in a model-independent manner. 3. Rapid, Dynamic Visualization: Using novel methods for visualizing and understanding trends through intuitive, dynamic, real-time visualizations that allow for the simultaneous analysis of up to ten variables. 4. Intelligent Hypothesis Generation: Using computer-identified correlations, together with human intuition gathered through human interaction with visualizations, to intelligently and automatically generate hypotheses about data. VisuaLyzer's power to simultaneously analyze and visualize massive amounts of data has important applications in the realm of epidemiology, where there are many large complex datasets collected from around the world, and an important need to elicit potential disease-defining factors from within these datasets.

Department dc:contributor.department

Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2009

Author dc:creator

• Reshef, David N

Advisor dc:contributor.advisor

• Paris Sabeti.

• Electrical Engineering and Computer Science.

Statement dc:rights

• M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/53135

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/53135