Title :
Distributed detection by a large team of sensors in tandem
Author :
Papastavrou, Jason D. ; Athans, Michael
Author_Institution :
Sch. of Ind. Eng., Purdue Univ., West Lafayette, IN, USA
fDate :
7/1/1992 12:00:00 AM
Abstract :
The problem of decentralized binary hypothesis testing by a team consisting of N decision makers (DMs) in tandem is considered. Each DM receives an observation and transmits a binary message to its successor; the last DM has to decide which hypothesis is true. The necessary and sufficient condition for the probability of error to go asymptotically to zero as N→∞ is that the log-likelihood ratio of the observation of each DM be unbounded. The result is generalized for multiple hypotheses and multiple messages. An easily implementable suboptimal decision scheme is also considered; in this case, the necessary and sufficient condition for the probability of error to asymptotically go to zero is that the log-likelihood ratio of the observation of each DM be unbounded from both above and below. The tradeoff between the complexity of the decision rules and their performance is examined, and numerical results are presented, in order to demonstrate that the performance of both decision schemes is comparable
Keywords :
information theory; probability; binary message; decentralized binary hypothesis testing; decision makers; distributed detection; log-likelihood ratio; multiple hypotheses; multiple messages; necessary and sufficient condition; probability of error; sensors; suboptimal decision; tandem; Delta modulation; Distributed decision making; Explosives; Global communication; Humans; Industrial engineering; Performance analysis; Subcontracting; Sufficient conditions; System testing; Testing; Upper bound;
Journal_Title :
Aerospace and Electronic Systems, IEEE Transactions on