|
Activity Number:
|
18
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statisticians in Defense and National Security
|
| Abstract - #307401 |
|
Title:
|
Anomaly Detection
|
|
Author(s):
|
Francisco Vera*+
|
|
Companies:
|
National Institute of Statistical Sciences
|
|
Address:
|
19 TW Alexander Drive, Research Triangle Park, NC, 27709,
|
|
Keywords:
|
anomaly detection ; outliers ; sindromic surveillance ; clustering ; terrorist prediction
|
|
Abstract:
|
An important national defense issue is the ability to detect terrorist attacks as soon as possible. When an attack occurs, many numerical indicators show a behavior different from before. A research group was formed at the Statistical and Applied Mathematical Sciences Institute (SAMSI) to do research on how to detect anomalies from data when this occur. During the weekly activities of our group, we have presented previous work and discussed improvements and the creation of new statistical models for anomaly detection. This talk will be a synthesis of this work.
|
