Search

In this letter, we consider the problem of field estimation using binary measurements. Previous work has formulated the problem as a parameter estimation problem, which can be solved in an online manner using sequential Monte Carlo (SMC) techniques. In the current work, we consider an alternative approach to the parameter estimation problem based on online logistic regression. The developed algorithm is less computationally intensive than the SMC approach, while having more reliable estimation performance. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the performance of distributed estimation schemes in a wireless sensor network in the presence of an eavesdropper. The sensors transmit observations to the fusion center (FC), which at the same time are overheard by the eavesdropper. Both the FC and the eavesdropper reconstruct a minimum mean-squared error estimate of the physical quantity observed. We address the problem of transmit power allocation for system performance optimization subject to a total average power constraint on the sensor(s), and a security/secrecy constraint on the eavesdropper. We mainly focus on two scenarios: 1) a single sensor with multiple transmit antennas and 2) multiple sensors with each sensor having a single transmit antenna. For each scenario, given perfect channel state information (CSI) of the FC and full or partial CSI of the eavesdropper, we derive the transmission policies for short-term and long-term cases. For the long-term power allocation case, when the sensor is equipped with multiple antennas, we can achieve zero information leakage in the full CSI case, and dramatically enhance the system performance by deploying the artificial noise technique for the partial CSI case. Asymptotic expressions are derived for the long-term distortion at the FC as the number of sensors or the number of antennas becomes large. In addition, we also consider multiple-sensor multiple-antenna scenario, and simulations show that given the same total number of transmitting antennas the multiple-antenna sensor network is superior to the performance of the multiple-sensor single-antenna network. [ABSTRACT FROM PUBLISHER]

In this paper, we investigate the distortion outage performance of distributed estimation schemes in wireless sensor networks, where a distortion outage is defined as the event that the estimation error or distortion exceeds a predetermined threshold. The sensors transmit their observation signals using the analog amplify and forward scheme through coherent multiaccess channels to the fusion center, which reconstructs a minimum mean squared error (MMSE) estimate of the physical quantity observed. We consider three power allocation schemes: 1) equal power allocation (EPA); 2) short-term optimal power allocation (ST-OPA), where we minimize the distortion subject to a power constraint at each time step; and 3) long-term optimal power allocation (LT-OPA), where we minimize the distortion outage probability subject to a long-term average power constraint. We study their diversity orders of distortion outage in terms of increasing numbers of sensors, and show that under Rayleigh fading EPA and ST-OPA achieve the same diversity order of N\log N, where N is the number of sensors. This suggests that in the case of a large number of sensors, the spatial diversity gain in EPA can overcome fading equally well as in ST-OPA. On the other hand, in LT-OPA, we find that for N>1 the outage probability can be driven to zero with a finite amount of total power. [ABSTRACT FROM AUTHOR]

This paper is concerned with decentralized estimation of a Gaussian source using multiple sensors. We consider a diversity scheme where only the sensor with the best channel sends their measurements over a fading channel to a fusion center, using the analog amplify and forwarding technique. The fusion centre reconstructs a minimum mean squared error (MMSE) estimate of the source based on the received measurements. A distributed version of the diversity scheme where sensors decide whether to transmit based only on their local channel information is also considered. We derive asymptotic expressions for the expected distortion (of the MMSE estimate at the fusion centre) of these schemes as the number of sensors becomes large. For comparison, asymptotic expressions for the expected distortion for a coherent multiaccess scheme and an orthogonal access scheme are derived. It is seen that as opposed to the coherent multiaccess scheme and the orthogonal scheme (where the expected distortion decays as 1/M, M being the number of sensors), the expected distortion decays only as 1/\ln(M) for the diversity schemes. This reduction of the decay rate can be seen as a tradeoff between the simplicity of the diversity schemes and the strict synchronization and large bandwidth requirements for the coherent multiaccess and the orthogonal schemes, respectively. We study for the diversity schemes, the optimal power allocation for minimizing the expected distortion subject to average power constraints. The effect of optimizing the probability of transmission on the expected distortion in the distributed scenario is also studied. It is proved that for Rayleigh fading optimal sensor transmit power allocation achieves the same asymptotic scaling law as the constant power allocation scheme, whereas it is observed that optimizing the sensor transmission probability (with or without optimal power allocation) in the distributed case makes very little difference to the asymptotic scaling laws. [ABSTRACT FROM AUTHOR]

This paper studies the outage probability minimization problem for state estimation of linear dynamical systems using multiple sensors, where an estimation outage is defined as an event when the state estimation error exceeds a pre-determined threshold. The sensors amplify-and-forward their measurements (using uncoded analog transmission) to a remote fusion center over wireless fading channels. For stable systems, the resulting infinite horizon problem can be formulated as a constrained average cost Markov decision process (MDP) control problem. A suboptimal power allocation that is less computationally intensive is proposed and numerical results demonstrate very close performance to the power allocation obtained from the solution of the MDP based average cost optimality equation. Motivated by practical considerations, assuming that sensors can transmit with only a finite number of power levels, optimization of the values of these levels is also considered using a stochastic approximation technique. In the case of unstable systems, a finite horizon formulation of the estimation outage minization problem is presented and solved. An extension to the problem of minimization of the expected error covariance is also studied. [ABSTRACT FROM PUBLISHER]

This correspondence studies the performance of Kalman fixed lag smoothers with random packet losses and its comparison with the Kalman filter with packet loss. In terms of estimator stability via boundedness of the expectation of the error covariance, we show that smoothing does not provide any benefit over filtering. On the other hand, it is demonstrated that using a probabilistic notion of performance, smoothing can provide significant gains when compared to Kalman filtering. An analysis of Kalman filtering using two simple retransmission schemes and its comparison with Kalman smoothing is also made. [ABSTRACT FROM AUTHOR]

A numerical method for computing the error exponent for Neyman-Pearson detection of two-state Markov chains in noise is presented, for both time-invariant and fading channels. We give numerical studies showing the behavior of the error exponent as the transition parameters of the Markov chain and the signal-to-noise ratio (SNR) are varied. Comparisons between the high-SNR asymptotics in Gaussian noise for the time-invariant and fading situations will also be made. [ABSTRACT FROM AUTHOR]

This paper studies the probability of error for maximum a posteriori (MAP) estimation of hidden Markov models, where measurements can be either lost or received according to an- other Markov process. Analytical expressions for the error prob- abilities are derived for the noiseless and noisy cases. Some relationships between the error probability and the parameters of the loss process are demonstated via both analysis and numerical resuIts. In the high signal-to-noise ratio (SNR) regime, approximate expressions which can be more easily computed than the exact analytical form for the noisy case are presented. [ABSTRACT FROM AUTHOR]

State estimation of linear systems using analog amplify and forwarding with multiple sensors, for both multiple access and orthogonal access schemes is considered. Optimal state estimation can be achieved at the fusion center using a time-varying Kalman filter. We show that in many situations, the estimation error covariance decays at a rate of 1/M when the number of sensors M is large. We consider optimal allocation of transmission powers that 1) minimizes the sum power usage subject to an error covariance constraint, and 2) minimizes the error covariance subject to a sum power constraint. In the case of fading channels with channel-state information, the optimization problems are solved using a greedy approach, while for fading channels without channel state information (CSI) but with channel statistics available, a suboptimal linear estimator is derived. [ABSTRACT FROM AUTHOR]