Distributed estimation using online semi‐supervised particle filter for mobile sensor networks

Yoo, Jaehyun; Kim, Woojin; Kim, Hyoun Jin

doi:10.1049/iet-cta.2014.0495

Cited by 23 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the centralised estimation, distributed estimation has better scalability and robustness for mobile sensor networks (see, e.g. [3–5]). However, there are some practical problems which the distributed estimation has to face such as inconsistent estimation results, switching topologies and a large amount of data transfer.…”

Section: Introductionmentioning

confidence: 99%

Distributed event‐triggered cubature information filtering based on weighted average consensus

Tan

Dong

et al. 2018

IET Control Theory & Applications

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Distributed event‐triggered cubature information filtering based on weighted average consensus

Tan

Dong

et al. 2018

IET Control Theory & Applications

View full text Add to dashboard Cite

“…This feature enables the distributed filtering to present great advantages, such as separating the computational load and facilitating fault detection, over the centralized filtering relying on a fusion to deal with all the measurements [4,9]. Therefore, the distributed filtering has been widely applied in networked systems [15,23,42,40,29,28,13,41], networked monitoring systems [5,7,24,35,18], multi-agent consensus [2,20,6,25,14,12], and autonomous navigation [22,30], and so on.…”

Section: Introductionmentioning

confidence: 99%

Distributed networked set-membership filtering with ellipsoidal state estimations

Xia

Yang

Han

2018

Information Sciences

View full text Add to dashboard Cite

This paper addresses the problem of distributed networked set-membership filtering with ellipsoidal state estimations for a class of discrete time-varying systems in the presence of unknown-but-bounded process and measurement noises. Both global and local ellipsoidal state estimations are provided to locate the true state (target) via a distributed filtering network. A new geometric method based on Minkowski sum is proposed to produce the global ellipsoidal estimation. A novel convex optimization approach is developed to derive some sufficient conditions on the existence of local networked set-membership filters and to obtain the local ellipsoidal estimations by exchanging information among neighboring filters via communication networks. An experiment is conducted based on a 2-kW single-phase grid-connected power generation system platform to demonstrate the feasibility and the effectiveness of the proposed method in the real application.

show abstract

“…A novel implicit UKF algorithm and its observational analytical approach for a satellite stellar refraction navigation system have been proposed in [15]. When it comes to the non-Gaussian noise, particle filter (PF) can be a better choice than UKF; however, particle degeneration in PF is a common phenomenon [16]. Elimination of particle degeneracy mainly relies on two key techniques, selecting the appropriate important density function and resampling [17].…”

Section: Introductionmentioning

confidence: 99%

Celestial navigation in deep space exploration using spherical simplex unscented particle filter

Zhao

Zhang

et al. 2018

IET signal process.

View full text Add to dashboard Cite

Deep space exploration has significant meaning both in science and economy; however, it is very hard to obtain the relevant information due to its complexity. In this study, the autonomous celestial navigation method is utilised. To achieve high accuracy of the celestial navigation in a deep space environment, the improved filtering algorithm-spherical simplex unscented particle filter (SSUPF) is implemented, which adopts the spherical simplex unscented Kalman filter (SSUKF) algorithm to generate the important sampling density of particle filter (PF). According to simulation results, the authors derive that the SSUPF method can greatly increase the performance of the navigation system compared with unscented Kalman filter (UKF), SSUKF and unscented PF (UPF), and the computational burden of SSUPF is reduced by 24% in comparison with UPF.

show abstract

Distributed estimation using online semi‐supervised particle filter for mobile sensor networks

Cited by 23 publications

References 33 publications

Distributed event‐triggered cubature information filtering based on weighted average consensus

Distributed event‐triggered cubature information filtering based on weighted average consensus

Distributed networked set-membership filtering with ellipsoidal state estimations

Celestial navigation in deep space exploration using spherical simplex unscented particle filter

Contact Info

Product

Resources

About