TY - JOUR
T1 - Intruder detection
T2 - An optimal decision analysis strategy
AU - Ben-Zvi, Tal
AU - Nickerson, Jeffrey V.
PY - 2012/3
Y1 - 2012/3
N2 - This study considers a situation in which a sensor network aims to protect a stationary target (e.g., a large battleship at anchor) and detects signals from approaching objects (e.g., small boats traveling in a harbor). Once the network detects a sufficient number of signals from the object (for example, through video surveillance), it may classify the objects intention as hostile and act accordingly by informing responders. The objective is to design an optimal strategy for recognition that guarantees accurate and timely intruder detection. We show that the optimal policy is of a control limit threshold.
AB - This study considers a situation in which a sensor network aims to protect a stationary target (e.g., a large battleship at anchor) and detects signals from approaching objects (e.g., small boats traveling in a harbor). Once the network detects a sufficient number of signals from the object (for example, through video surveillance), it may classify the objects intention as hostile and act accordingly by informing responders. The objective is to design an optimal strategy for recognition that guarantees accurate and timely intruder detection. We show that the optimal policy is of a control limit threshold.
KW - Decision-making
KW - Markov models
KW - sensors
KW - signal detection
UR - http://www.scopus.com/inward/record.url?scp=84857507941&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84857507941&partnerID=8YFLogxK
U2 - 10.1109/TSMCC.2011.2126043
DO - 10.1109/TSMCC.2011.2126043
M3 - Article
AN - SCOPUS:84857507941
SN - 1094-6977
VL - 42
SP - 249
EP - 253
JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
IS - 2
M1 - 5744129
ER -