Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/26048
Title: | Recursive filtering for complex networks with time-correlated fading channels: An outlier-resistant approach |
Authors: | Li, Q Wang, Z Dong, H Sheng, W |
Keywords: | complex networks;recursive filtering;time-correlated fading channels;measurement outliers |
Issue Date: | 10-Oct-2022 |
Publisher: | Elsevier |
Citation: | Li, Q. et al. (2022) 'Recursive filtering for complex networks with time-correlated fading channels: An outlier-resistant approach', Information Sciences, 615, pp. 348 - 367. doi: 10.1016/j.ins.2022.10.023. |
Abstract: | In this paper, the outlier-resistant recursive filtering problem is fully discussed for complex networks with time-correlated fading channels. Each sensor is able to communicate with its corresponding filter within a set of time-correlated fading channels, and the channel coefficient is assumed to be governed by certain dynamical process. In order to alleviate undesired effects (e.g. performance degradation or even divergence of the filtering error) from possible measurement outliers, a certain saturation structure is introduced in our constructed filter. The purpose is at estimating network states with satisfactory error dynamics with not only time-correlated fading channels but also measurement outliers. First, an augmented model is constructed in order to combine network dynamic evolutions along with channel coefficients. Subsequently, by means of the inductive method, upper covariance bounds are first given and later minimized by properly parameterizing filter gains. Finally, two example are given for effectiveness validation. |
URI: | https://bura.brunel.ac.uk/handle/2438/26048 |
DOI: | https://doi.org/10.1016/j.ins.2022.10.023 |
ISSN: | 0020-0255 |
Other Identifiers: | ORCID iD: Zidong Wang https://orcid.org/0000-0002-9576-7401 |
Appears in Collections: | Dept of Computer Science Embargoed Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Embargoed until 10 October 2023 | 705.57 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License