### Skapa referens, olika format (klipp och klistra)

**Harvard**

Granström, K., Willett, P. och Bar-Shalom, Y. (2016) *Detectability prediction of hidden Markov models with cluttered observation sequences*.

** BibTeX **

@conference{

Granström2016,

author={Granström, Karl and Willett, Peter and Bar-Shalom, Yaakov},

title={Detectability prediction of hidden Markov models with cluttered observation sequences},

booktitle={41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016; Shanghai International Convention CenterShanghai; China; 20 March 2016 through 25 March 2016},

isbn={978-147999988-0},

pages={4269-4273},

abstract={There is good reason to model an asymmetric threat (a structured action such as a terrorist attack) as an hmm whose observations are cluttered. Recently a Bernoulli filter was presented that can process cluttered observations («transactions») and is capable of detecting if there is an hmm present, and if so, estimate the state of the HMM. An important question in this context is: when is the HMM-in-clutter problem feasible? In other words, what system properties allow for a solvable problem? In this paper we show that, given a Gaussian approximation of the pdf of the log-likelihood, approximate detection error bounds can be derived. These error bounds allow a prediction of the detection performance, i.e. a prediction of the probability of detection given an «operating point» of transaction-level false alarm rate and miss probability. Simulations show that our analysis accurately predicts detectability of such threats. Our purpose here is to make statements about what sort of threats can be detected, and what quality of observations are necessary that this be accomplished.},

year={2016},

keywords={Asymmetric threat; Bernoulli filter; detectability; Hidden Markov Models},

}

** RefWorks **

RT Conference Proceedings

SR Electronic

ID 239245

A1 Granström, Karl

A1 Willett, Peter

A1 Bar-Shalom, Yaakov

T1 Detectability prediction of hidden Markov models with cluttered observation sequences

YR 2016

T2 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016; Shanghai International Convention CenterShanghai; China; 20 March 2016 through 25 March 2016

SN 978-147999988-0

SP 4269

OP 4273

AB There is good reason to model an asymmetric threat (a structured action such as a terrorist attack) as an hmm whose observations are cluttered. Recently a Bernoulli filter was presented that can process cluttered observations («transactions») and is capable of detecting if there is an hmm present, and if so, estimate the state of the HMM. An important question in this context is: when is the HMM-in-clutter problem feasible? In other words, what system properties allow for a solvable problem? In this paper we show that, given a Gaussian approximation of the pdf of the log-likelihood, approximate detection error bounds can be derived. These error bounds allow a prediction of the detection performance, i.e. a prediction of the probability of detection given an «operating point» of transaction-level false alarm rate and miss probability. Simulations show that our analysis accurately predicts detectability of such threats. Our purpose here is to make statements about what sort of threats can be detected, and what quality of observations are necessary that this be accomplished.

LA eng

DO 10.1109/ICASSP.2016.7472482

LK http://dx.doi.org/10.1109/ICASSP.2016.7472482

OL 30