Data Analysis Tools for Visualization Study
Abstract
A study in fiscal year (FY) 2014 led by Dr Robert Erbacher, described in Evaluation of the Presentation of Network Data via Visualization Tools for Network Analysts, resulted in a large body of data from trial results. This report presents tools that I have developed to codify, display, and analyze the data. In the current visualization study, test subjects looked at a set of network intrusion alerts and decided which of those alerts represented true threats. The correct answers and the selections by each subject were recorded as fixed-format text files. My tools parse this text, insert the data into tables in a relational database, and create views to facilitate reading selected data from the tables. Additional tables were built, which contained sums of the performance statistics for each trial. I wrote Python programs to analyze the summary data and applied statistical tests to some of the means to determine whether they were statistically different. A plot capability was added as well.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 2015
- Accession Number
- ADA625734
Entities
People
- Richard L. Astrom
Organizations
- United States Army Research Laboratory