This article deals with the optimized distributed filtering problem with binary measurements for a class of discrete linear time-varying systems. The system and the original measurements are subject to random noise with known statistical information. Two cases of extracting useful measurement information are designed based on binary measurements between two adjacent moments. Furthermore, a novel time-varying threshold strategy is introduced to reduce the impact of the uncertainties from the binary measurements. The dynamic event-triggering protocols under token bucket specifications are employed to schedule the information transmission among neighboring nodes with constrained resources. The former determines the necessity of information transmission, and the latter describes whether the communication resources are sufficient or not. Information is successfully transmitted only when these two conditions (formulated by two indicator variables) are satisfied. A set of locally sufficient conditions is constructed for each node to guarantee the existence of the distributed filter such that the filtering error system satisfies the exponential boundedness in the mean square. The filter parameters are recursively calculated by solving the distributed optimization problems, which are constrained by linear matrix inequalities for each node. Such a structure achieves the desirable scalability of distributed filtering. A simulation example demonstrates the effectiveness of the distributed filtering scheme developed in this article.

This article is concerned with the distributed set-membership estimation problem for a class of discrete time-varying systems over binary sensor networks. For the binary sensors, the cases of fixed and time-varying thresholds are considered. In both the cases, the information useful for state estimation purposes is extracted by utilizing the crossings of binary measurements at two adjacent time instants, and then distributed estimators are constructed for each sensor node with the aid of the available measurements, where a set of vector saturation functions is introduced to resist the adverse effect of outliers during signal transmission. A novel distributed set-membership performance index is provided by averaging over the ellipsoidal constraints of all the sensor nodes, and the local performance analysis method is employed to establish sufficient criteria that guarantee the existence of desired estimators whose parameters are then derived for every node by recursively optimizing certain ellipsoids in the sense of matrix trace. The applicability and feasibility of the distributed set-membership schemes developed in this article are verified by two illustrative examples.

In this article, as inspired by multiagent systems, a novel leader–follower-based particle swarm optimization (LFPSO) algorithm is presented where the particles are classified into leaders and followers according to their respective roles. The leaders are responsible for searching a wide range of the optimal candidate solutions so as to ensure the diversity of the particle population, and the followers are dedicated to seeking the global-best solution in order to guarantee the convergence of particles. A controller parameter is introduced to fine tune the impact of the leaders on the followers. Owing to the leader–follower mechanism, the proposed LFPSO algorithm not only maintains the diversity of the particle population but also improves the possibility of escaping from the locally optimal solution. It is demonstrated via experimental results that the proposed LFPSO algorithm significantly improves the accuracy and convergence rate of conventional particle swarm optimization algorithms. Furthermore, the LFPSO algorithm is successfully applied to denoise real-time signals in oilfield pipeline network and its superiority over existing denoising algorithms is verified as well.

In this article, the recursive filtering problem is investigated for state-saturated complex networks (CNs) subject to uncertain coupling strengths (UCSs) and deception attacks. The measurement signals transmitted via the communication network may suffer from deception attacks, which are governed by Bernoulli-distributed random variables. The purpose of the problem under consideration is to design a minimum-variance filter for CNs with deception attacks, state saturations, and UCSs such that upper bounds on the resulting error covariances are guaranteed. Then, the expected filter gains are acquired via minimizing the traces of such upper bounds, and sufficient conditions are established to ensure the exponential mean-square boundedness of the filtering errors. Finally, two simulation examples (including a practical application) are exploited to validate the effectiveness of our designed approach.

This paper deals with the scalable distributed H∞-consensus filtering problem for a class of discrete time-varying systems subject to multiplicative noises and censored measurements over sensor networks (SNs). For the underlying SN, it is assumed that only the measurement outputs from partial sensor nodes are available. Also, the phenomenon of censored measurements is taken into account to reflect the limited capability in measuring. A new H∞-consensus performance index is put forward to evaluate the disturbance rejection level of the filters against the simultaneous presence of external disturbances, initial conditions, as well as censoring effects. By utilizing the vector dissipativity theory and the recursive matrix inequality technique, sufficient conditions are established under which the prescribed H∞-consensus performance index is achieved. The parameters of the desired distributed filters are calculated via solving certain matrix inequalities, where such a calculation is conducted in a local sense so as to preserve the scalability of the filter design. Finally, a numerical simulation example is provided to demonstrate the validity and applicability of the proposed filtering strategy.

In this article, the recursive filtering problem is investigated for a class of time-varying complex networks with state saturations and random coupling strengths under an event-triggering transmission mechanism. The coupled strengths among nodes are characterized by a set of random variables obeying the uniform distribution. The event-triggering scheme is employed to mitigate the network data transmission burden. The purpose of the problem addressed is to design a recursive filter such that in the presence of the state saturations, event-triggering communication mechanism, and random coupling strengths, certain locally optimized upper bound is guaranteed on the filtering error covariance. By using the stochastic analysis technique, an upper bound on the filtering error covariance is first derived via the solution to a set of matrix difference equations. Next, the obtained upper bound is minimized by properly parameterizing the filter parameters. Subsequently, the boundedness issue of the filtering error covariance is studied. Finally, two numerical simulation examples are provided to illustrate the effectiveness of the proposed algorithm.

The distributed state estimation problem is examined for a kind of nonlinear time-varying stochastic systems through sensor networks (SNs) with randomly switching topologies as well as redundant channels. The random switches of the topologies for SNs are governed by Markovian jumping parameters and the redundant channels are introduced to help improve the capability of the network communication. We are interested in designing distributed state estimators so that the estimation error dynamics is confirmed to reach a prescribed level of average H∞performance in terms of a finite horizon. Through intensive stochastic analysis, we acquire some sufficient conditions that guarantee the existence of the expected state estimators whose gain parameters are obtained recursively by means of the solution to a series of matrix inequalities. A numerical simulation is carried out to illustrate the validity of the developed state estimation algorithm.

This paper is concerned with the exponential state estimation issue for a class of delayed Markovian jumping neural networks (MJNNs) with sensor nonlinearities and disturbances. The parameters and discrete delays of the neural networks are subject to the switching from one mode to another according to a Markov chain. By constructing a novel Lyapunov-Krasovskii functional, a mode-dependent exponential stability condition is proposed, such that the resulting estimation error system is exponentially stable in the mean square. The design of the desired state estimator is derived by solving a set of linear matrix inequalities (LMIs). Finally, a numerical example is given to illustrate the validity of the theoretical results.

In this paper, we are devoted to investigate the consensus-based distributed state estimation problems for a class of sensor networks within the unscented Kalman filter (UKF) framework. The communication status among sensors is represented by a connected undirected graph. Moreover, a weighted average consensus-based UKF algorithm is developed for the purpose of estimating the true state of interest, and its estimation error is bounded in mean square which has been proven in the following section. Finally, the effectiveness of the proposed consensus-based UKF algorithm is validated through a simulation example.