Distributed Set-Membership Fusion Filtering for Nonlinear 2-D Systems Over Sensor Networks: An Encoding–Decoding Scheme

Abstract

In this paper, the distributed set-membership fusion filtering problem is investigated for a class of nonlinear two-dimensional shift-varying systems subject to unknown-butbounded noises over sensor networks. The sensors are communicated with their neighbors according to a given topology through wireless networks of limited bandwidth. With the purpose of relieving the communication burden as well as enhancing the transmission security, a logarithmic-type encoding-decoding mechanism is introduced for each sensor node so as to encode the transmitted data with a finite number of bits. A distributed setmembership filter is designed to determine the local ellipsoidal set that contains the system state by only utilizing the data from the local sensor node and its neighbors, where the proposed filter scheme is truly distributed with desirable scalability. Then, a new ellipsoid-based fusion rule is developed for the designed set-membership filters in order to form the fused ellipsoidal set that has a globally smaller volume than all local ellipsoidal sets. With the aid of the mathematical induction technique, the set theory and the convex optimization approach, sufficient conditions are derived for the existence of the desired distributed set-membership filters and the fusion weights. Then, the filter parameters and the fusion weights are acquired by solving a set of constrained optimization problems. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed fusion filtering algorithm.

Received signal strength indicator‐based set‐membership filtering indoor localization under multipath effect

“…Fortunately, the so‐called set‐membership filtering (see refs. [29–31, 35, 36]) provides a rather promising countermeasure to this difficulty. Noise is assumed to be distributed in an unknown but bounded region in this algorithm, and the bound of the noise is easy to obtain relative to statistical properties.…”

“…Remark 4. Up to now, the linearized processing of the lognormal shadowing model is completed, and the higher-order remainder is restricted within the bounded interval, as shown in Equation (29). Different from the traditional algorithm that discarded the linearization error, the higher-order remainder in this paper is accurately obtained based on the interval mathematical analysis method to improve the accuracy of linearization.…”

“…In refs. [29, 30], the parameters in the measurement function are taken as constants, and the measurement model is set to a known time‐varying matrix in ref. [31].…”

Optimal Distributed Finite-Time Fusion Method for Multi-Sensor Networks under Dynamic Communication Weight

“…Many scholars have increased the weight of the fusion process to enhance the authenticity of sensor networks in various applications. In [19][20][21][22][23], fusion weights have been incorporated into information fusion algorithms, but the approaches to handle these weights vary. A global KF and long short-term memory (LSTM)-based measurement variance data fusion method were designed in [19] by incorporating an adaptive truncation mechanism to determine optimal weights.…”

“…The switching between the two filters is accomplished by applying probabilities to match the weights. In [23], a set of constrained optimization problems is solved using mathematical induction, set theory, and convex optimization methods to obtain the fusion weights for the filters. However, the aforementioned reference did not consider the communication weights of the sensor network, which has certain ideal constraints.…”