This paper introduces several algorithms for signal estimation using binary-valued outputsensing.The main idea is derived from the empirical measure approach for quantized identification,which has been shown to be con...This paper introduces several algorithms for signal estimation using binary-valued outputsensing.The main idea is derived from the empirical measure approach for quantized identification,which has been shown to be convergent and asymptotically efficient when the unknown parametersare constants.Signal estimation under binary-valued observations must take into consideration oftime varying variables.Typical empirical measure based algorithms are modified with exponentialweighting and threshold adaptation to accommodate time-varying natures of the signals.Without anyinformation on signal generators,the authors establish estimation algorithms,interaction between noisereduction by averaging and signal tracking,convergence rates,and asymptotic efficiency.A thresholdadaptation algorithm is introduced.Its convergence and convergence rates are analyzed by using theODE method for stochastic approximation problems.展开更多
基金supported in part by the National Science Foundation under ECS-0329597 and DMS-0624849in part by the Air Force Office of Scientific Research under FA9550-10-1-0210+2 种基金supported by the National Science Foundation under DMS-0907753 and DMS-0624849in part by the Air Force Office of Scientific Research under FA9550-10-1-0210supported in part by a research grant from the Australian Research Council
文摘This paper introduces several algorithms for signal estimation using binary-valued outputsensing.The main idea is derived from the empirical measure approach for quantized identification,which has been shown to be convergent and asymptotically efficient when the unknown parametersare constants.Signal estimation under binary-valued observations must take into consideration oftime varying variables.Typical empirical measure based algorithms are modified with exponentialweighting and threshold adaptation to accommodate time-varying natures of the signals.Without anyinformation on signal generators,the authors establish estimation algorithms,interaction between noisereduction by averaging and signal tracking,convergence rates,and asymptotic efficiency.A thresholdadaptation algorithm is introduced.Its convergence and convergence rates are analyzed by using theODE method for stochastic approximation problems.
