In this paper, the problem of adaptive neural state-feedback tracking control is considered for a class of stochastic nonstrict-feedback nonlinear switched systems with completely unknown ...nonlinearities. In the design procedure, the universal approximation capability of radial basis function neural networks is used for identifying the unknown compounded nonlinear functions, and a variable separation technique is employed to overcome the design difficulty caused by the nonstrict-feedback structure. The most outstanding novelty of this paper is that individual Lyapunov function of each subsystem is constructed by flexibly adopting the upper and lower bounds of the control gain functions of each subsystem. Furthermore, by combining the average dwell-time scheme and the adaptive backstepping design, a valid adaptive neural state-feedback controller design algorithm is presented such that all the signals of the switched closed-loop system are in probability semiglobally uniformly ultimately bounded, and the tracking error eventually converges to a small neighborhood of the origin in probability. Finally, the availability of the developed control scheme is verified by two simulation examples.
This paper deals with the event-based finite-time state estimation problem for a class of discrete-time stochastic neural networks with mixed discrete and distributed time delays. In order to ...mitigate the burden of data communication, a general component-based event-triggered transmission mechanism is proposed to determine whether the measurement output should be released to the estimator at certain time-point according to a specific triggering condition. A new concept of finite-time boundedness in the mean square is put forward to quantify the estimation performance by introducing a settling-like time function. The objective of the addressed problem is to construct an event-based state estimator to estimate the neuron states such that, in the presence of both mixed time delays and external noise disturbances, the dynamics of the estimation error is finite-time bounded in the mean square with a prescribed error upper bound. Sufficient conditions are established, via stochastic analysis techniques, to guarantee the desired estimation performance. By solving an optimization problem with some inequality constraints, the explicit expression of the estimator gain matrix is characterized to minimize the settling-like time. Finally, a numerical simulation example is exploited to demonstrate the effectiveness of the proposed estimator design scheme.
Summary
This paper is concerned with the distributed filtering problem for a class of nonlinear time‐delay system over sensor networks subject to multiplicative link noises and switching topology. ...Both discrete and distributed time delays are included in the system model. Each sensor estimates the system state by means of the measurements not only from itself but also from its neighboring nodes according to an interactive topology. The multiplicative stochastic link noises are taken into consideration to reflect the random perturbations during the information exchanges between sensor nodes. The considered communication topology is switching according to certain predetermined rules. The purpose of the addressed problem is to develop a distributed filtering strategy such that, in the presence of multiplicative stochastic link noises and switching topology, the resulting filtering error dynamics is exponentially stable in the mean square sense and also satisfies the prespecified weighted disturbance attenuation level. In light of the average dwell time technique in combination with stochastic analysis, sufficient conditions are derived for the solvability of the addressed distributed filtering problem, and the desired filtering gains are then obtained through solving certain convex optimization problems. An illustrative simulation example is presented to demonstrate the correctness and applicability of the obtained theoretical results.
In this paper, a magnetic resonance imaging (MRI) oriented novel attention-based glioma grading network (AGGN) is proposed. By applying the dual-domain attention mechanism, both channel and spatial ...information can be considered to assign weights, which benefits highlighting the key modalities and locations in the feature maps. Multi-branch convolution and pooling operations are applied in a multi-scale feature extraction module to separately obtain shallow and deep features on each modality, and a multi-modal information fusion module is adopted to sufficiently merge low-level detailed and high-level semantic features, which promotes the synergistic interaction among different modality information. The proposed AGGN is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the proposed AGGN in comparison to other advanced models, which also presents high generalization ability and strong robustness. In addition, even without the manually labeled tumor masks, AGGN can present considerable performance as other state-of-the-art algorithms, which alleviates the excessive reliance on supervised information in the end-to-end learning paradigm.
•The proposed AGGN can alleviate the reliance on manually labeled tumor masks.•Dual-domain attention is useful for selecting the modality and location of MRI.•Multi-modal and multi-scale learning benefits analyzing brain MRI comprehensively.•Effective fusion methods enhance the presentation ability of robust features.
In this paper, the particle filtering problem is investigated for a class of nonlinear/non-Gaussian systems with energy harvesting sensors subject to randomly occurring sensor saturations (ROSSs). ...The random occurrences of the sensor saturations are characterized by a series of Bernoulli distributed stochastic variables with known probability distributions. The energy harvesting sensor transmits its measurement output to the remote filter only when the current energy level is sufficient, where the transmission probability of the measurement is recursively calculated by using the probability distribution of the sensor energy level. The effects of the ROSSs and the possible measurement losses induced by insufficient energies are fully considered in the design of filtering scheme, and an explicit expression of the likelihood function is derived. Finally, the numerical simulation examples (including a benchmark example for nonlinear filtering and the applications in moving target tracking problem) are provided to demonstrate the feasibility and effectiveness of the proposed particle filtering algorithm.
This paper is concerned with the fixed-time synchronization for a class of complex-valued neural networks in the presence of discontinuous activation functions and parameter uncertainties. Fixed-time ...synchronization not only claims that the considered master–slave system realizes synchronization within a finite time segment, but also requires a uniform upper bound for such time intervals for all initial synchronization errors. To accomplish the target of fixed-time synchronization, a novel feedback control procedure is designed for the slave neural networks. By means of the Filippov discontinuity theories and Lyapunov stability theories, some sufficient conditions are established for the selection of control parameters to guarantee synchronization within a fixed time, while an upper bound of the settling time is acquired as well, which allows to be modulated to predefined values independently on initial conditions. Additionally, criteria of modified controller for assurance of fixed-time anti-synchronization are also derived for the same system. An example is included to illustrate the proposed methodologies.
This paper is concerned with the fault detection problem for a class of networked multi-rate systems with nonuniform sampling and dynamic quantization. The sampling interval of the measurements is ...allowed to be nonuniform that is governed by a time-homogenous Markov process with partly unknown and uncertain transition probabilities. The measured output is quantized by a dynamic quantizer and then transmitted through communication network subject to data missing. The main purpose of the problem under consideration is to design sampling-interval-dependent fault detection filters such that, in the simultaneous presence of nonuniform sampling, dynamic quantization, intermittent faults as well as missing measurements, the robustness of residuals with respect to the disturbance and the sensitivity of the residuals against the fault are guaranteed. Finally, a three-tank system is utilized to illustrate the effectiveness of the proposed fault detection scheme.
Summary
This paper considers the problem of adaptive fuzzy output‐feedback tracking control for a class of switched stochastic nonlinear systems in pure‐feedback form. Unknown nonlinear functions and ...unmeasurable states are taken into account. Fuzzy logic systems are used to approximate the unknown nonlinear functions, and a fuzzy observer is designed to estimate the immeasurable states. Based on these methods, an adaptive fuzzy output‐feedback control scheme is developed by combining the backstepping recursive design technique and the common Lyapunov function approach. It is shown that all the signals in the closed‐loop system are semiglobally uniformly ultimately bounded in mean square in the sense of probability, and the observer errors and tracking errors can be regulated to a small neighborhood of the origin by choosing appropriate parameters. Finally, a simulation result is provided to show the effectiveness of the proposed control method.
In this paper, the boundedness and robust stability for a class of delayed complex-valued neural networks with interval parameter uncertainties are investigated. By using Homomorphic mapping theorem, ...Lyapunov method and inequality techniques, sufficient condition to guarantee the boundedness of networks and the existence, uniqueness and global robust stability of equilibrium point is derived for the considered uncertain neural networks. The obtained robust stability criterion is expressed in complex-valued LMI, which can be calculated numerically using YALMIP with solver of SDPT3 in MATLAB. An example with simulations is supplied to show the applicability and advantages of the acquired result.
This study is concerned with the event-based security control problem for a class of discrete-time stochastic systems with multiplicative noises subject to both randomly occurring denial-of-service ...(DoS) attacks and randomly occurring deception attacks. An event-triggered mechanism is adopted with hope to reduce the communication burden, where the measurement signal is transmitted only when a certain triggering condition is violated. A novel attack model is proposed to reflect the randomly occurring behaviours of the DoS attacks as well as the deception attacks within a unified framework via two sets of Bernoulli distributed white sequences with known conditional probabilities. A new concept of mean-square security domain is put forward to quantify the security degree. The authors aim to design an output feedback controller such that the closed-loop system achieves the desired security. By using the stochastic analysis techniques, some sufficient conditions are established to guarantee the desired security requirement and the control gain is obtained by solving some linear matrix inequalities with non-linear constraints. A simulation example is utilised to illustrate the usefulness of the proposed controller design scheme.