Deep neural networks have recently achieved promising performance in the vein recognition task and have shown an increasing application trend. However, they are prone to adversarial attacks by adding imperceptible perturbations to the input, resulting in incorrect recognition. To address this issue, we propose a novel defense model named MsMemoryGAN, which aims to filter the perturbations from adversarial samples before recognition. First, we design a multiscale memory autoencoder (MsMemoryAE) to achieve high-quality reconstruction, where the memory module (MM) within it is capable of learning the detailed patterns of normal samples at different scales. Second, to overcome the limitations of handcrafted similarity metrics, we propose an MM with learnable similarity (LSMM), which retrieves the most relevant memory items to purify the input feature. Finally, the perceptual loss and adversarial loss are integrated with the pixel loss to further enhance the quality of the reconstructed image. During the training phase, the MsMemoryGAN learns to reconstruct the input by merely using fewer prototypical elements of the normal patterns recorded in the memory. At the testing stage, given an adversarial sample, the MsMemoryGAN retrieves its most relevant normal patterns in MMs for reconstruction. Perturbations in the adversarial sample are usually not reconstructed well, resulting in adversarial purification. We conduct extensive experiments on two public vein datasets under different adversarial attack methods to evaluate the performance of the proposed approach. The experimental results show that our approach removes a wide variety of adversarial perturbations, allowing vein classifiers to achieve the highest recognition accuracy.

This article proposes a novel observer-based adaptive neural network-based resilient consensus control approach to address hybrid cyberattacks, disturbances, and nonlinear dynamics in nonlinear leader-following multiagent systems (MASs). Specifically, a dimension expansion methodology is developed to dynamically model and compensate for false data injection (FDI) attacks, while denial-of-service (DoS) attacks are probabilistically characterized via Bernoulli variables, forming a comprehensive hybrid attack mitigation strategy. Then, a cascaded observer is designed, integrating dimension-extended system modeling with disturbance decoupling to simultaneously estimate system states and external disturbances with high precision. Furthermore, an adaptive neural network-based approximation scheme is employed to handle system nonlinearities, eliminating the conservatism of Lipschitz-based methods while enhancing robustness in complex environments. Finally, the simulation result validates that the proposed control method achieves resilient consensus of leader-following MASs under hybrid cyberattacks, disturbances, and nonlinear dynamics.

This article investigates the issue of composite anti-disturbance and attack control for networked systems under unknown actuator attacks and external disturbances. First, a double-ended event-triggering mechanism is designed to reduce unnecessary data transmission in the feedforward and feedback channels. Second, an augmented observer is designed to estimate the system states and disturbances. The intermittent estimation signal is then used to compensate for external disturbances through a novel trigger sampling mechanism. Third, the fuzzy logic system is used to approximate the unknown attack signal, and an adaptive output feedback controller is employed to mitigate its impact on the system. Based on these three key techniques, a novel functional dependent on the sampling instants is constructed to analyze semi-global uniform ultimate boundedness of the closed-loop system and obtain the criterion condition of low conservatism. Additionally, the event-triggering matrix and gains are explicitly solved by matrix transformation. Finally, the feasibility and effectiveness of the proposed method are validated via a visual servo control system and a third-order system.

This article investigates the issue of event-triggered tracking control for Takagi–Sugeno fuzzy systems subject to hybrid attacks. First, the deception attacks occurring on the feedback channel are considered using a Bernoulli process, in which an attacker injects state-dependent malicious signals. Next, the minimal ‘silent’ and maximal ‘active’ periods are defined to describe the duration of aperiodic denial-of-service (DoS) attacks. To take advantage of communication bandwidth and resist DoS attacks, a sampled data-based resilient dynamic event-triggered strategy is designed. Then, an event-based fuzzy tracking controller is designed to guarantee the stability of error system under hybrid attacks. Subsequently, sufficient conditions for the stability analysis are proposed by utilizing a fuzzy-basis-dependent Lyapunov-Krasovskii functional. Meanwhile, the control gains and event-triggering parameters are co-designed by applying linear matrix inequalities. Furthermore, the proposed method is extended to address the tracking control problem of multi-agent systems. Finally, the feasibility of the presented approach is validated by two examples.

This article proposes a sampled-data event-triggered adaptive neural network (NN) control strategy to cope with the digital communication and attack compensation problems of networked systems with actuator attacks and exogenous disturbance. By combining event triggering state, parameter estimation signals, and disturbance observer, a novel digital state feedback controller is designed to reduce its updating frequency and compensate for the deliberate impact of unknown actuator attacks. Moreover, considering that the state is partially measurable, a novel observer-based digital controller is designed via a double-ended event-triggering mechanism (ETM). Then, two new Lyapunov functionals are created to analyze the system stability, and two design methods are given to solve the control gain. Finally, the feasibility and validity of the derived results are verified by a visual servo control system and an offshore structure system.

This paper tackles the security cooperative tracking control problem for uncertain heterogeneous nonlinear multi-agent systems (MASs) subject to denial-of-service (DoS) attacks. Since the communication between agents can only transmit digital signals, a periodic sampling mechanism is used to reduce bandwidth pressure. Based on these digital signals, a novel distributed switching observer is designed to estimate the state of the reference system for each follower in the case of DoS attacks on aperiodic intermittently blocked communication channels. Then, an attack-parameter-dependent Lyapunov functional is established to analyze the exponential convergence of the error signals and a design scheme of observer gains is proposed. Further, with the help of the sampling observer outputs, follower’s states and adaptive signals, a sampled-data neural network controller is designed to guarantee the boundedness of the tracking errors by backstepping method and impulsive system analysis theory. Finally, a simulation example is performed to showcase the effectiveness of the developed strategy. Note to Practitioners—In industrial systems, since it is difficult for a single plant to complete complex control tasks, the cooperative control of MASs has gradually become a hot research issue. For example, in industrial automated production, a single robotic arm cannot achieve mass production of products, while multiple robotic arms can achieve this task and improve production efficiency. In this context, the study on cooperative control of MASs is of great scientific and economic value. The wireless communication network is the medium of information transfer between the agents and the controllers, while giving attacker an opportunity to attack. When network interaction information is affected by attacks, the performance and stability of the system are easily damaged. Moreover, under the condition of ensuring the performance of the system, the number of packet transmission is as small as possible, which will be conducive to the applications with limited bandwidth or congested network. Taking these problems into consideration, this paper studies sampled-data tracking control for uncertain heterogeneous nonlinear MASs under DoS attacks. This result provides a reference for the design of digital security controller, and can also be applied to intelligent engineering systems.

Recent advances in video tracking with discriminative correlation filters leverage diverse observation models. However, fusing hand-crafted and deep convolutional neural network representations equivalently would overly constrain resolution conditions for template matching, leading to peak response slippage and jittery neighboring search processes, especially problematic in autonomous driving scenarios. This article addresses the inference conservatism issue in multitype feature tracking. We propose a target-observation constraint framework to formalize discrimination conservatism across feature map channels. A learning constraint transformation methodology is introduced to cluster similar representations while pushing dissimilar ones apart. These discriminant constraints are further fine-tuned through joint learning with correlation filters, improving the positional precision of detection responses. Additionally, we propose an updating strategy that suppresses low scores of symmetric dispersion ratio, enhancing tracking robustness. Extensive evaluations on five tracking datasets demonstrate the superior performance of our approach: UAV20L, UAVDT, OTB-100, VOT-2019, and LaSOT.

In this article, we proposed a fuzzy controller for nonlinear two-time-scale systems with uncertain system parameters. The designed controller is implemented using integral control and event-triggered strategy to deal with the singularly perturbed system (SPS), which typically operates on both the fast and slow dynamics simultaneously because of the small value parameter, namely, the parasitic parameter $\varepsilon $ . Two main challenges of this work are the instability of SPS-caused by the presence of parasitic parameter, the parameter uncertainties and external disturbances-and the data transmission load between the system and the controller. To tackling with these problems, the proposed controller is designed based on the Takagi-Sugeno fuzzy model in cooperation with the integral feedback and event-triggering action, and its control performances are analyzed using linear matrix inequality (LMI) approach. Through the demonstrations, our proposed method ensures the asymptotic stability, enhances robustness against disturbances and parametric uncertainties, and also effectively reduces communication costs.

This article addresses the periodic event-triggered adaptive output feedback control problem for networked system with unknown nonlinear dynamics. Based on the output-dependent periodic event-triggered mechanism (PETM), a nonlinear observer is designed to estimate system states, where the fuzzy-logic systems-based approximation method and adaptive technique are employed to approximate and compensate for uncertainties. To enhance resource utilization efficiency in communication channels, a new observer and parameter estimators-dependent parallel PETM is proposed to schedule intermittent packet transmission. Then, a digital controller is designed to reduce frequent control updating. By constructing novel piecewise Lyapunov functional, it is proven that the underlying system states, the observation error signals and parameter estimation signals are semiglobally uniformly ultimately bounded. In addition, the proposed control method is applied to solve the stabilization problem of networked interconnected systems. Finally, a numerical simulation is performed to show the efficiency of the developed control method.

This paper presents event-triggered integral re-inforcement learning methods to solve nonlinear nonzero-sum differential game problems. Firstly, for nonlinear systems, by constructing coupled Hamilton-Jacobi equations, the theoretical basis for solving multi-player nonzero-sum game problems is established. With the help of integral reinforcement learning, the approximate optimal control strategy corresponding to each player can be obtained without knowing the drift dynamics of the system. Then, the event-triggered mechanism with preliminary operation is constructed by designing appropriate triggering condition. The dynamic triggering mechanism is further integrated into the algorithm architecture of online learning method to realize aperiodic adaptive learning and sampling control, and effectively save system computing and communication resources. Finally, the effectiveness of the proposed reinforcement learning method is verified by theory analyses and simulation experiments.

Abstract Effective control of the tower crane system (TCS) is crucial for the safe and quick transport of goods from one point to another in industries and construction sites. However, the existing literature either depends on the dynamic model of the system, which is prone to errors and assumptions, or requires the feedback of the states to be controlled, which can be costly and or complex. In particular, the TCS has many states and is highly nonlinear. Thus, a non‐model‐based control approach that depends on minimal feedback sensors is needed. The primary contribution of this work is that the potential hybrid configurations of the input shaping control (ISC) and fuzzy logic control (FLC) were proposed and investigated. The study provides the best hybrid configuration of the ISC and FLC (non‐model‐based controllers) for optimal positioning and anti‐swing control of the TCS. Three configurations of the ISC + FLC, namely shaper as reference input (SARI), shaper as input to the FLC (SAI2F), and shaper as input to the plant (SAI2P) were investigated to assess the optimal hybrid configuration of the ISC + FLC. The results demonstrated that the hybrid ISC + FLC scheme had improved the response of ISC by at least 150% and enhanced the oscillation reduction of FLC by 72%. Finally, these analyses showed that the ISC + FLC could achieve reasonable control of the tower crane by only considering the output of one state (position). This makes the control scheme cheaper and reduces the complexity and computational time compared to other full‐state feedback controllers.

This article focuses on the Pareto optimal issues of nonlinear game systems with asymmetric input saturation under dynamic event-triggered mechanism (DETM). First, the safe control is guaranteed by transforming the system with safety constraints into the one without state constraints utilizing barrier function. The united cost function integrating nonquadratic utility function is constructed to provide the foundation to achieve the Pareto optimal solutions. Then, the adaptive dynamic programming method with concurrent learning is proposed to approximate the Pareto optimal strategies wherein both current and historical data are utilized. To further lessen the consumptions of computation/communication resources, the DETM is integrated into the adaptive algorithm framework which can avoid Zeno phenomena. All the signals of the closed-loop system are proved to be uniformly ultimately bounded. Finally, the simulation results are given to validate the effectiveness of the proposed method from several aspects.

This article conducts the issue of event-triggered reduced-order filtering for continuous-time semi-Markov jump systems with imperfect measurements as well as randomly occurring uncertainties (ROUs). Specifically, the sojourn-time-dependent transition probability matrix (TPM) is presumed to be polytopic and a quantizer is introduced to quantize output signals aiming to reflect the reality. Both ROUs and sensor failures are generated by individual random variables belonging to be mutually independent Bernoulli-distributed white sequences. First, sufficient conditions for the existence of the event-triggered reduced-order filter are obtained by utilizing the dissipativity-based technique to ensure the asymptotical stability with a strictly dissipative performance of the filtering error system. The time-varying TPM is then fractionalized, which enhances the results as stated. Furthermore, the required reduced-order filter parameters are obtained by introducing slack symmetric matrix as well as cone complementarity linearization algorithm. The effectiveness of the suggested event-triggered reduced-order filter design method is shown through simulation results.

This article proposes an adaptive fuzzy dual-channel event-triggered output feedback control approach for a class of multi-input-multi-output (MIMO) systems with deception attacks and input saturation. Due to the consideration of two pivotal factors simultaneously, including deception attacks and input saturation, the existing methods are difficult to be directly applied. To this end, a novel fuzzy state observer and an auxiliary system are constructed to address unavailable impaired system states and input saturation, respectively. Furthermore, by constructing a new transformation of coordinate and employing adaptive fuzzy technique and single parameter learning approach, the sensor deception attacks, fuzzy weight and external disturbance are reconstructed online into linear composite uncertain terms with single parameter under the framework of backstepping and dynamic surface design. Additionally, the communication and computation burden is significantly reduced by using fewer single-parameter adaptive laws and dual-channel event-triggered strategy (DCETS). The proposed control method guarantees that all signals within the closed-loop system are bounded. Meanwhile, the Zeno behavior is avoided. Finally, a simulation example is provided to verify the availability of the presented approach.

This article addresses the problem of event-triggered dynamic output feedback controller design for networked Takagi-Sugeno (T-S) fuzzy systems subject to actuator failure and deception attacks. In order to save network resources effectively, two event-triggered schemes (ETSs) are introduced to test whether the measurement output and control input are transmitted under network communication. While the ETS brings advantages, it also leads to a mismatch between the premise variables of the system and the controller. To solve this problem, an asynchronous premise reconstruct method is considered, which relaxes the condition of the previous results that the premises of the plant and the controller are synchronous. Furthermore, two crucial factors, including actuator failure and deception attacks, are taken into consideration simultaneously. Then, the mean square asymptotic stability conditions of the resultant augmented system are derived by utilizing the Lyapunov stability theory. Besides, controller gains and event-triggered parameters are co-designed with the help of linear matrix inequality techniques. Finally, a cart-damper-spring system and a nonlinear mass-spring-damper mechanical system are presented to verify the theoretical analysis.

The security control of a vehicle platoon depends on the network topology and communication quality. Denial of service (DoS) attacks force vehicle formations to destabilize by disrupting digital communications between vehicles. To this end, this paper develops a resilient distributed event-triggered security control strategy to resist the malicious impact of DoS attacks on connected vehicles. By designing a distributed event-triggered mechanism based on sampled data, the controller updating frequency is reduced, thereby promoting utilization rate of network resources. Since the end of the attack is not the sampling instant, this may prolong the duration of the attack. To overcome this problem, a switched sampled-data scheme is proposed to ensure that the control signal acts on the system immediately when the attack ends. Then, a switched system model with artificial delay is established to capture the sampling period, event triggering mechanism and DoS attack purpose. With the analysis methods of switched system and time-delay system, sufficient conditions are obtained to guarantee the same safe distance and speed between vehicles, so that the connected vehicle system can achieve the desired tracking effect. A co-design approach is given with respect to controller gains and triggering parameter. Finally, simulation and experimental studies are provided to demonstrate the effectiveness of the proposed security control method.

In this article, the problem of asynchronous sliding-mode control (SMC) for a class of nonlinear singular Markovian jump systems (SMJSs) with actuator faults and uncertain transition rates (TRs) is investigated. Based on Takagi-Sugeno (T-S) fuzzy models, the nonlinear SMJSs are transformed to a set of local linear SMJSs connected by the so-called IF-THEN rules. The hidden Markov model is employed to demonstrate the nonsynchronization phenomenon of the jump mode between the plant and the designed controller. In combination with SMC and adaptive control techniques, a new asynchronous adaptive SMC scheme is developed, which has the ability to completely compensate for the effects of actuator faults and parameter uncertainties. Sufficient conditions for the stochastic asymptotic admissability of the closed-loop T-S fuzzy SMJSs are derived, and the design scheme for controller gain matrices is presented. The reachability of the sliding surface can be guaranteed by the designed control law. Finally, two examples are provided to illustrate the effectiveness of the proposed new design techniques.

The fault detection (FD) problem for systems with both model uncertainty and external disturbance is investigated in this article. First, the mathematical models of systems with model uncertainty and disturbance, systems with additive faults, and systems with multiplicative faults are established with both left and right coprime factorization. Then, an observer-based FD scheme is proposed and the FD thresholds are derived for both open-loop and closed-loop manners. The necessary conditions on multiplicative FD are obtained and the fault detectability analyses are carried out with the aid of the gap metric technique. Finally, the effectiveness of the proposed method is illustrated by a case study on a cart dynamic system.

In interconnected industrial control networks like smart grids, topology attacks on physical grids can lead to severe cascading failures and large-scale blackouts. Effective defense on vulnerable devices can significantly reduce the risk of cascading failures and improve overall system robustness. In this paper, we investigate the vulnerability analysis problem from a graph theoretical classification perspective. By calculating a node vulnerability vector composed of features based on complex network theory, node embedding, extended betweenness and power flow distribution, we propose a node vulnerability analysis method based on XGBoost classifier. A cascading failure simulation model based on DC power flow is used to simulate the smart grid behaviours under topology attacks and create the dataset for the XGBoost classifier. The effectiveness of the proposed XGBoost-based method with newly-introduced features is demonstrated by case studies.

This paper investigates the decentralized event-triggered output feedback control for nonlinear networked interconnected systems under multiple cyber attacks, where denial of service and deception attacks are considered. A resilient period event-triggered strategy is adopted to reduce the occupation of network resources. Considering the impact of cyber attacks, the output-based decentralized security controller is constructed within a unified framework. Sufficient conditions of stochastically finite-time stable of the switched system are given by employing the Lyapunov-Krasovskii functional. Then, the controller gains and event-triggered weight matrix are designed simultaneously. Finally, a chemical reactor system is used to substantiate the effectiveness of the proposed method.

Abstract A novel optimal proportional integral derivative (PID) autotuning controller design based on a new algorithm approach, the “swarm learning process” (SLP) algorithm, is proposed. It improves the convergence and performance of the autotuning PID parameter by applying the swarm and learning algorithm concepts. Its convergence is verified by two methods, global convergence and characteristic convergence. In the case of global convergence, the convergence rule of a random search algorithm is employed to judge, and Markov chain modelling is used to analyse. The superiority of the proposed method, in terms of characteristic convergence and performance, is verified through the simulation based on the automatic voltage regulator and direct current motor control system. Verification is performed by comparing the results of the proposed model with those of other algorithms, that is, the ant colony optimization with a new constrained Nelder–Mead algorithm, the genetic algorithm (GA), the particle swarm optimization (PSO) algorithm, and a neural network (NN). According to the global convergence analysis, the proposed method satisfies the convergence rule of the random search algorithm. With respect to the characteristic convergence and performance, the proposed method provides a better response than the GA, the PSO, and the NN for both control systems.

In this paper, a robust level set method is proposed for image segmentation. Traditional level set methods are sensitive to noise in images which greatly limits its application in real project. To overcome this shortcoming, the fractional order regularization and Markov random fields term are incorporated into the traditional level methods in this paper. The fractional order regularization can reveal more details of the image and the Markov random field (MRF) term takes the hole image into account. In additional to these two terms, a region term and a penalty term are added into the energy function. The comparison of the proposed method with the classical level set method is made and the results show that the proposed method is robust to noise in images in image segmentation application.