Title :
Quickest detection of hidden Markov models
Author :
Chen, Biao ; Willett, Peter
Author_Institution :
Connecticut Univ., Storrs, CT, USA
Abstract :
Page´s test is optimal in quickly detecting distributional changes among independent observations. In this paper we propose a similar procedure for the quickest detection of dependent signals which can be conveniently modeled as hidden Markov models. Considering Page´s test as a repeated sequential probability ratio test, we use Wald´s approximation, with modification regarding the threshold overshoot, to predict the performance of the test, namely the average run length (ARL), between false alarms T. Using the asymptotic convergence property of the test statistic, we are also able to predict the ARL to detection D. The analysis shows that T is asymptotically exponential in D, as in the i.i.d. case. The results are supported by numerical examples
Keywords :
approximation theory; convergence of numerical methods; hidden Markov models; maximum likelihood detection; probability; Page test; Wald approximation; asymptotic convergence; average run length; false alarms; hidden Markov model detection; sequential probability ratio test; signal detection; Convergence; Delay; Error probability; Gas detectors; Hidden Markov models; Performance analysis; Sequential analysis; Signal detection; Statistical analysis; Testing;
Conference_Titel :
Decision and Control, 1997., Proceedings of the 36th IEEE Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-4187-2
DOI :
10.1109/CDC.1997.652487
