Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks

Abstract

Nageswara S. V. (2017) 'Estimation and fusion for tracking over long-haul links using articial neural networks.', IEEE transactions on signal and information processing over networks., 3 (4). pp. 760-770. Further information on publisher's website: Additional information: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract-In a long-haul sensor network, sensors are remotely deployed over a large geographical area to perform certain tasks, such as tracking and/or monitoring of one or more dynamic targets. A remote fusion center fuses the information provided by these sensors so that a final estimate of certain target characteristics -such as the position -is expected to possess much improved quality. In this work, we pursue learning-based approaches for estimation and fusion of target states in longhaul sensor networks. In particular, we consider learning based on various implementations of artificial neural networks (ANNs). The joint effect of (i) imperfect communication condition, namely, link-level loss and delay, and (ii) computation constraints, in the form of low-quality sensor estimates, on ANN-based estimation and fusion, is investigated by means of analytical and simulation studies.Index Terms-Long-haul sensor networks, state estimate fusion, artificial neural networks, estimation bias, error regularization, root-mean-square-error (RMSE) performance, reporting deadline.

A Clamping Force Estimation Method Based on a Joint Torque Disturbance Observer Using PSO-BPNN for Cable-Driven Surgical Robot End-Effectors

“…The BPNN is a supervised artificial neural network, and it is widely used for nonlinear and non-convex function approximation [40]. However, its main disadvantages include slow learning speed, a propensity to easily fall into a local minimum, a limited number of network layers, and overfitting [41]. The traditional BPNN can be improved by global optimization of PSO to solve the problems of oscillation, slow convergence and local extremum in the training process [42].…”

Projection-Based Constrained State Estimation and Fusion for Tracking Over Long-Haul Links

“…Suppose a message sent by a sensor is lost during transmission with probability p, and a probability density function f (t) describes the overall latency t that a message experiences before it is successfully delivered to the fusion center. A typical example is the shifted exponential distribution [16]:…”

“…A series of studies on out-of-sequence measurements (OOSMs) aim to incorporate variably delayed sensor measurements into the regular estimation and fusion process, and the results have been summarized in [3]. In our earlier works, we have considered various approaches, notably information-based selective fusion [21], retransmission [22], staggered scheduling [20], and learning-based fusion [16], to counteract the effect of incomplete sensor data. More recently, we have presented results for linear [17], circular [19], and elliptical [18] constrained fusion, accounting for the long-haul link loss, and proposed distance-based weighted fusers in [15] to mitigate the effect of sensor bias.…”

Distributed Multisensor Data Fusion under Unknown Correlation and Data Inconsistency

“…Distributed fusion estimation for the case of asynchronous systems with correlated noises was studied in References [ 66 , 67 , 68 ]. Some authors have also explored learning based approaches for multisensor data fusion [ 4 , 6 , 7 , 69 , 70 , 71 ]. While Kalman filter and Bayesian formulation rely on known statistics for data fusion, learning based approaches learn the statistical model of the uncertainty from incoming data.…”