TY - JOUR
T1 - Estimation of 1-bit quantized time-series with Markov regime
AU - Logothetis, Andrew
AU - Krishnamurthy, Vikram
AU - Poor, H. Vincent
N1 - Funding Information:
Dans cet article nous Btudions le probleme consistant a des-entrelacer un nombre fini de sources paramhriques et stochatiques. Les sources sont mod&lides comme des processus autor&essifs (AR) indkndants. En nous basant sur une politique de passage markovienne, nous supposons que les diffkrentes sources transmettent des signaux sur le mgme canal. Le rkcepteur enregistre la version quantifike b 1 bit du signal transmis et cherche B identifier la sequence des sources actives. Une fois que la sequence des source a Ct&i dentifibe, les cara&ristiques (paramktres) de chaque source l Corresponding author. Tel.: 613 9344 6714; fax: 613 9344 6678; e-mail: [email protected]. ’ Partially supported by the Australian Telecommunications and Electronics Research Board (ATERB), Australian Research Council (ARC) and the Co-operative Research Centre for Sensor Signal and Information Processing (CSSIP).
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 1997/5
Y1 - 1997/5
N2 - In this paper we consider de-interleaving a finite number of stochastic parametric sources. The sources are modeled as independent autoregressive (AR) processes. Based on a Markovian switching policy, we assume that the different sources transmit signals on the same single channel. The receiver records the 1-bit quantized version of the transmitted signal and aims to identify the sequence of active sources. Once the source sequence has been identified, the characteristics (parameters) of each source are estimated. We formulate the parametric pulse train de-interleaving problem as a 1-bit quantized Markov modulated AR series. The algorithm proposed in this paper combines Hidden Markov Model (HMM) and Binary Time Series (BTS) estimation techniques. Our estimation scheme generalizes Kedem's (1980) binary time series algorithm for linear time series to Markov modulated time series.
AB - In this paper we consider de-interleaving a finite number of stochastic parametric sources. The sources are modeled as independent autoregressive (AR) processes. Based on a Markovian switching policy, we assume that the different sources transmit signals on the same single channel. The receiver records the 1-bit quantized version of the transmitted signal and aims to identify the sequence of active sources. Once the source sequence has been identified, the characteristics (parameters) of each source are estimated. We formulate the parametric pulse train de-interleaving problem as a 1-bit quantized Markov modulated AR series. The algorithm proposed in this paper combines Hidden Markov Model (HMM) and Binary Time Series (BTS) estimation techniques. Our estimation scheme generalizes Kedem's (1980) binary time series algorithm for linear time series to Markov modulated time series.
KW - Autoregressive process
KW - Binary time series
KW - Expectation maximization algorithm
KW - Hidden Markov models
KW - Parameter estimation
UR - http://www.scopus.com/inward/record.url?scp=0031141755&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031141755&partnerID=8YFLogxK
U2 - 10.1016/s0165-1684(97)00029-7
DO - 10.1016/s0165-1684(97)00029-7
M3 - Article
AN - SCOPUS:0031141755
SN - 0165-1684
VL - 58
SP - 273
EP - 292
JO - Signal Processing
JF - Signal Processing
IS - 3
ER -