Decision-Directed Estimation of a Two-Class Decision Boundary

Patrick, Edward A.; Costello, J.; Monds, F.C.

doi:10.1109/t-c.1970.222897

Cited by 11 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probably the most straightforward method, and one that has previously been used with success in [10], [26], is to compute bi as the empirical average of those samples yi (t) for which a detection in sector i occurred (i.e., when Si occurs). This (31) where the -y is a constant such that 0 < -y c 1.…”

Section: Estimation Of Signal Strengthmentioning

confidence: 99%

“…Decision-directed procedures have been used in [7]- [10] for adaptive (untaught) pattern recognition, wherein signal parameters are estimated using only observations classified as containing the signal. Other decision-directed adaptive classification schemes have been proposed for synchronous detection [11] and for adaptive equalization in the digital communications context [12].…”

Section: Introductionmentioning

confidence: 99%

“…The process x (t) modulates the rate of the discrete-time vector process N(t) according to (7) and (10). We wish to obtain equations of evolution of the process x(t + 1 t) = E{x(t + 41) I} -E = x(t + 1), the conditional expectation of x ( t + 1 ) given the a-field 5t.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Decision-Directed Multivariate Empirical Bayes Classification with Nonstationary Priors

Stirling

Swindlehurst

1987

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-A decision-directed learning strategy is presented to recursively estimate (i.e., track) the time-varying a priori distribution for a multivariate empirical Bayes adaptive classification rule. The problem is formulated by modeling the prior distribution as a finite-state vector Markov chain and using past decisions to estimate the time evolution of the state of this chain. The solution is obtained by implementing an exact recursive nonlinear estimator for the rate vector of a multivariate discrete-time point process representing the decisions. This estimator obtains the Doob decomposition of the decision process with respect to the a-field generated by all past decisions and corresponds to the nonlinear least squares estimate of the prior distribution. Monte Carlo simulation results are provided to assess the performance of the estimator.

show abstract

Section: Estimation Of Signal Strengthmentioning

confidence: 99%