The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
Activity Number:
|
520
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 3, 2011 : 10:30 AM to 12:20 PM
|
Sponsor:
|
IMS
|
Abstract - #302004 |
Title:
|
Scalable Mixture Sequential Multi-Sensor Change-Point Detection Procedure
|
Author(s):
|
Yao Xie*+ and David Siegmund
|
Companies:
|
Stanford University and Stanford University
|
Address:
|
109 McFarland CT, APT 400, Stanford, CA, 94305, USA
|
Keywords:
|
Multisensor detection ;
Change-point problem ;
Sequential detection ;
False-alarm rate ;
generalized likelihood ratio (GLR) ;
maximum of ranom field
|
Abstract:
|
We develop a scalable mixture (SaM) procedure for unstructured multi-sensor sequential change-point detection problems, where multiple sensors are distributed to monitor the emergence of a signal that changes the means of observations from part of sensors. We assume that the affected sensors and their post-change means are unknown. SaM uses an estimate for the fraction of affected sensors, p, and sums the nonlinearly transformed generalized likelihood ratio statistics (GLR) from each sensor. The sum is then compared with a threshold chosen to maintain a certain false alarm rate. In SaM, the nonlinear transform achieves noise suppression from unaffected sensors by a soft-thresholding, which is controlled by p. We derive a closed-form false alarm rate for SaM as well as its expected detection delay with good accuracy verified numerically. We also show that SaM does not require an accurate
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.