Work

Multisensor Particle Filtering for Nonlinear Complex Networks With Heterogeneous Measurements Under Non-Gaussian Noises

Year: 2025

Type: article

Abstract: In this article, the multisensor particle filtering problem is investigated for a class of nonlinear complex networks with multirate heterogeneous measurements. The underlying complex networks are subject to non-Gaussian noises and randomly switching couplings, while the multirate heterogeneous measurements (including fast-rate binary measurements and slow-rate integral measurements) are transmitted to remote filters via imperfect wireless communication channels. Both the deterministic and stochastic channel gains, along with possible transmission failures, are taken into account to characterize the properties of wireless communication channels. The purpose of this article is to propose a channel-related filtering scheme in the particle filtering framework to address these engineering-oriented complexities. To achieve this, a mixture distribution is established to reflect the effects of randomly switching couplings and generate new particle candidates. By utilizing the Monte Carlo approximation method, two types of update expressions for importance weights are explicitly derived based on the channel properties and the likelihood functions. Finally, numerical simulations are presented to demonstrate the viability and effectiveness of the proposed particle filtering algorithms.

Source: IEEE Transactions on Cybernetics

DOI: 10.1109/tcyb.2025.3623631

Authors: Weihao Song, Zidong Wang, Zhongkui Li, Hongli Dong

Institutions: Peking University, Brunel University of London, Northeast Petroleum University

Language: English

Topic: Target Tracking and Data Fusion in Sensor Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Natural Science Foundation of China, China Postdoctoral Science Foundation