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

Liu, Qiang; Brigham, Katharine; Rao, Nageswara S. V.

doi:10.1109/TSIPN.2017.2662619

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

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 long-haul sensor networks. In particular, we consider learning based on various implementations of artificial neural networks (ANNs). The joint effect of 1) imperfect communication condition, namely, link-level loss and delay, and 2) 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.

Authors:

^[1]; Brigham, Katharine ^[2]; Rao, Nageswara S. V. ^[1]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Durham Univ. (United Kingdom)

Publication Date:: Wed Feb 01 00:00:00 EST 2017

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); Office of Naval Research (ONR) (United States)

OSTI Identifier:: 1394388

Alternate Identifier(s):: OSTI ID: 1468110

Grant/Contract Number:: AC05-00OR22725

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Transactions on Signal and Information Processing over Networks

Additional Journal Information:: Journal Volume: 3; Journal Issue: 4; Journal ID: ISSN 2373-7778

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; estimation; information processing; fuses; testing; artificial neural networks; target tracking; reporting deadline; long-haul sensor networks; state estimate fusion; error regularization; root-mean-square-error (RMSE) performance

Citation Formats


                    Liu, Qiang, Brigham, Katharine, and Rao, Nageswara S. V. Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks.  United States: N. p., 2017. 
Web.  doi:10.1109/TSIPN.2017.2662619.

Copy to clipboard


                    Liu, Qiang, Brigham, Katharine, & Rao, Nageswara S. V. Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks.  United States.  https://doi.org/10.1109/TSIPN.2017.2662619

Copy to clipboard


                    Liu, Qiang, Brigham, Katharine, and Rao, Nageswara S. V. Wed .  
"Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks".  United States.  https://doi.org/10.1109/TSIPN.2017.2662619.  https://www.osti.gov/servlets/purl/1394388.

Copy to clipboard


                    
@article{osti_1394388,

  title        = {Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks},

  author       = {Liu, Qiang and Brigham, Katharine and Rao, Nageswara S. V.},

  abstractNote = {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 long-haul sensor networks. In particular, we consider learning based on various implementations of artificial neural networks (ANNs). The joint effect of 1) imperfect communication condition, namely, link-level loss and delay, and 2) 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.},

  doi          = {10.1109/TSIPN.2017.2662619},

  journal      = {IEEE Transactions on Signal and Information Processing over Networks},

  number       = 4,

  volume       = 3,

  place        = {United States},

  year         = {Wed Feb 01 00:00:00 EST 2017},

  month        = {Wed Feb 01 00:00:00 EST 2017}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/TSIPN.2017.2662619

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 8 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referencing / citing this record:

Analysis of interpolation algorithms for the missing values in IoT time series: a case of air quality in Taiwan
journal, September 2019

Yen, Neil Y.; Chang, Jia-Wei; Liao, Jia-Yi
The Journal of Supercomputing, Vol. 76, Issue 8
DOI: 10.1007/s11227-019-02991-7

A Clamping Force Estimation Method Based on a Joint Torque Disturbance Observer Using PSO-BPNN for Cable-Driven Surgical Robot End-Effectors
journal, December 2019

Wang, Zhengyu; Wang, Daoming; Chen, Bing
Sensors, Vol. 19, Issue 23
DOI: 10.3390/s19235291

Similar Records in DOE PAGES and OSTI.GOV collections:

Staggered scheduling of sensor estimation and fusion for tracking over long-haul links

Journal Article Liu, Qiang ; Rao, Nageswara S. V. ; Wang, Xin - IEEE Sensors Journal

Networked sensing can be found in a multitude of real-world applications. Here, we focus on the communication-and computation-constrained long-haul sensor networks, where sensors are remotely deployed over a vast geographical area to perform certain tasks. Of special interest is a class of such networks where sensors take measurements of one or more dynamic targets and send their state estimates to a remote fusion center via long-haul satellite links. The severe loss and delay over such links can easily reduce the amount of sensor data received by the fusion center, thereby limiting the potential information fusion gain and resulting in suboptimalmore »« less
Cited by 6
https://doi.org/10.1109/JSEN.2016.2575099

Full Text Available
Projection-Based linear constrained estimation and fusion over long-haul links

Conference Rao, Nageswara S

We study estimation and fusion with linear dynamics in long-haul sensor networks, wherein a number of sensors are remotely deployed over a large geographical area for performing tasks such as target tracking, and a remote fusion center serves to combine the information provided by these sensors in order to improve the overall tracking accuracy. In reality, the motion of a dynamic target might be subject to certain constraints, for instance, those defined by a road network. We explore the accuracy performance of projection-based constrained estimation and fusion methods that is affected by information loss over the long-haul links. We usemore »« less
Projection-Based Linear Constrained Estimation and Fusion over Long-Haul Links

Conference Rao, Nageswara S

In this work, we study estimation and fusion with linear dynamics in long-haul sensor networks, wherein a number of sensors are remotely deployed over a large geographical area for performing tasks such as target tracking, and a remote fusion center serves to combine the information provided by these sensors in order to improve the overall tracking accuracy. In reality, the motion of a dynamic target might be subject to certain constraints, for instance, those defined by a road network. We explore the accuracy performance of projection-based constrained estimation and fusion methods that is affected by information loss over the long-haulmore »« less
Projection-based circular constrained state estimation and fusion over long-haul links

Conference Liu, Qiang ; Rao, Nageswara S.

In this paper, we consider a scenario where sensors are deployed over a large geographical area for tracking a target with circular nonlinear constraints on its motion dynamics. The sensor state estimates are sent over long-haul networks to a remote fusion center for fusion. We are interested in different ways to incorporate the constraints into the estimation and fusion process in the presence of communication loss. In particular, we consider closed-form projection-based solutions, including rules for fusing the estimates and for incorporating the constraints, which jointly can guarantee timely fusion often required in realtime systems. We test the performance ofmore »« less
https://doi.org/10.23919/ICIF.2017.8009836

Full Text Available
Effect of retransmission and retrodiction on estimation and fusion in long-haul sensor networks

Journal Article Liu, Qiang ; Wang, Xin ; Rao, Nageswara S. V. ; ... - IEEE/ACM Transactions on Networking

In a long-haul sensor network, sensors are remotely deployed over a large geographical area to perform certain tasks, such as target tracking. In this work, we study the scenario where sensors take measurements of one or more dynamic targets and send state estimates of the targets to a fusion center via satellite links. The severe loss and delay inherent over the satellite channels reduce the number of estimates successfully arriving at the fusion center, thereby limiting the potential fusion gain and resulting in suboptimal accuracy performance of the fused estimates. In addition, the errors in target-sensor data association can alsomore »« less
Cited by 9
https://doi.org/10.1109/TNET.2014.2363841

Full Text Available

Similar Records

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

Abstract

Citation Formats

Analysis of interpolation algorithms for the missing values in IoT time series: a case of air quality in Taiwan journal, September 2019

A Clamping Force Estimation Method Based on a Joint Torque Disturbance Observer Using PSO-BPNN for Cable-Driven Surgical Robot End-Effectors journal, December 2019

Analysis of interpolation algorithms for the missing values in IoT time series: a case of air quality in Taiwan
journal, September 2019

A Clamping Force Estimation Method Based on a Joint Torque Disturbance Observer Using PSO-BPNN for Cable-Driven Surgical Robot End-Effectors
journal, December 2019