In this article, a dynamic feedback (DF)-based dynamic event-triggered (DET) control method for unknown nonaffine systems (UNSs) is developed by using reinforcement learning (RL). Through introducing a DF signal as a virtual control input, the UNS is augmented into a partially unknown affine system (PUAS). Subsequently, by designing a novel cost function that reflects the system states, and the actual and virtual control inputs, the DET optimal control (OC) problem of UNS is transformed into a DET OC problem of PUAS. To relax the requirement of PUAS dynamics, a neural network (NN)-based observer is established by using the measured system data. Moreover, a novel DET condition is established based on the static event-triggered (SET) rule, and the relationship of the triggering interval between SET and DET is revealed. In order to solve the DET Hamilton–Jacobi–Bellman equation (HJBE), a critic NN is constructed with the concurrent learning method to release the persistence of excitation (PE) condition. Furthermore, according to Lyapunov’s direct method, the stability of the closed-loop system is guaranteed under the developed DF-based DET control strategy. Finally, simulation results of two examples demonstrate the effectiveness of the present DF-based DET method.

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing demand for the Internet of Medical Things (IoMT) integration. The advent of generative artificial intelligence (GenAI) has further elevated multimodal large language models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can handle multimodal inputs and generate different kinds of data by utilizing large-scale training on massive multimodal datasets. Nevertheless, significant challenges remain in developing medical MLLMs, especially security and data freshness concerns, which impact the quality of MLLM outputs. To this end, this article proposes a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. The proposed framework enables secure data training by utilizing a hierarchical cross-chain design. Furthermore, it improves the output quality of MLLMs by using hybrid RAG that filters different unimodal RAG results using multimodal metrics and integrates these retrieval results as additional inputs for MLLMs. Furthermore, we utilize the age of information (AoI) to indirectly assess the influence of data freshness on MLLMs and apply contract theory to motivate healthcare data stakeholders to disseminate their current data, thereby alleviating information asymmetry in the data-sharing process. Finally, we employ a generative diffusion model-based deep reinforcement learning (DRL) technique to find the optimal contract for efficient data sharing. Numerical results show the effectiveness of the proposed approach in achieving secure and efficient healthcare data management.

The work aims to solve the high-speed high-precision tracking control problem of piezoactuators in the presence of stochastic disturbances. First, a cascade model composed of the Preisach operator and a class of stochastic nonlinear systems is proposed to describe the sophisticated actuator dynamics during high-speed operation, and then a hysteresis decomposition strategy is developed to transform the Preisach model into an appropriate form tractable to control design so that a robust adaptive fuzzy control framework can be constructed successfully to suppress the hysteresis nonlinearities, and to robustify bounded stochastic disturbances. More importantly, based on such a framework, the fixed-time stability (instead of practical fixed-time stability), and the prescribed steady-state tracking performance can be established simultaneously. Besides theoretical analysis, some experimental tests are also conducted to illustrate the effectiveness of the proposed scheme.

This paper designs and optimizes the event-triggered impulsive controller (ETIC) of continuous-time nonlinear systems. A generalized-event-driven system model (GEM) is designed to characterize the impulsive dynamics over the impulsive actions. Using the GEM, we construct the ETIC which is further optimized by the proposed event-triggered impulsive adaptive dynamic programming (ETIADP) method. By utilizing a new value updating technique, the liquid-updating ETIADP (LADP) is presented such that the computing devices with low memory capacities can be used to carry out the optimization scheme. By analyzing the admissibility, convergence and error bound properties of ETIADP and LADP, it is proved that the optimal impulsive performance index function and ETIC can be successfully obtained. An experimental study is given to validate the effectiveness of the proposed approaches.

Driven by the great advances in metaverse and edge computing technologies, vehicular edge metaverses are expected to disrupt the current paradigm of intelligent transportation systems. As highly computerized avatars of Vehicular Metaverse Users (VMUs), the Vehicle Twins (VTs) deployed in edge servers can provide valuable metaverse services to improve driving safety and on-board satisfaction for their VMUs throughout journeys. To maintain uninterrupted metaverse experiences, VTs must be migrated among edge servers following the movements of vehicles. This can raise concerns about privacy breaches during the dynamic communications among vehicular edge metaverses. To address these concerns and safeguard location privacy, pseudonyms as temporary identifiers can be leveraged by both VMUs and VTs to realize anonymous communications in the physical space and virtual spaces. However, existing pseudonym management methods fall short in meeting the extensive pseudonym demands in vehicular edge metaverses, thus dramatically diminishing the performance of privacy preservation. To this end, we present a cross-metaverse empowered dual pseudonym management framework. We utilize cross-chain technology to enhance management efficiency and data security for pseudonyms. Furthermore, we propose a metric to assess the privacy level and employ a Multi-Agent Deep Reinforcement Learning (MADRL) approach to obtain an optimal pseudonym generating strategy. Numerical results demonstrate that our proposed schemes are high-efficiency and cost-effective, showcasing their promising applications in vehicular edge metaverses.

This article develops a novel online adaptive dynamic programming algorithm with adjustable convergence rate to address the optimal control problem of nonlinear systems. Relaxation factors are introduced to tune the convergence rate of value function sequence online. A novel update law based on recursive least squares is developed to adjust the weight of critic neural network at the sampling instant. The uniform ultimate boundedness of the neural network estimation error and the closed-loop system state are analyzed by utilizing the Lyapunov technique. Finally, the effectiveness of the present algorithm is demonstrated by executing three simulation examples.

An inversion-based control strategy has been shown to be effective in compensating the hysteresis nonlinearities modeled by the Preisach operator. However, when the operator is coupled with the dynamics of uncertain nonlinear systems, there is still no result available for constructing the hysteresis inverse controller. To fill in the gap, in this study, we propose an iterative inverse-based adaptive fuzzy control scheme. Technically, an adaptive hysteresis inverse constructed through an iteration algorithm and updated by a projection-based adaptive law is developed as a feedforward hysteresis compensator, and then, the hysteresis inverse compensation error and plant nonlinearities and uncertainties are handled by a newly designed adaptive fuzzy controller. With our scheme, the closed-loop stability in the sense of signal boundedness, the prescribed steady-state tracking performance, and the convergence of the iteration algorithm can be established. Besides theoretical analysis, the effectiveness of our scheme is also validated by simulation and experimental results.

Multiview clustering (MVC) is a fundamental research topic in the field of machine learning and data mining, which has been developed rapidly and made significant progress recently. However, the current works tend to learn the individual representation of each view and then naviely merge or align them to achieve a shared representation of multiview data. By doing this, they often ignore the interference caused by the entanglement among multiple views, leading to the shared latent embedding cannot well model the correlation of all views. To this end, in this article, we propose a novel self-supervised adversarial learning-based view-common latent autoencoders for MVC, termed by multi-SSALvcAE. Specifically, the proposed method can effectively disentangle the unique and common information of each view by virtue of multiview adversarial latent autoencoders. And then only the common parts are fused to form the shared information, after being aligned deliberately on multiview semantic space. Experimental results show that our method achieved the promising results on several datasets, against the state-of-the-arts.

The rapid development of the Internet of Vehicles (IoV) has boosted the prosperity of various on-vehicle applications, e.g., route guidance, speed advisory, and autonomous driving. These applications call for computation offloading due to limited resources of the users, where edge computing becomes a promising solution. However, it remains an open problem how the user dynamics can be handled by deploying mobile edge servers on service vehicles. To this end, this paper proposes a mobile edge computing deployment scheme to fulfill computation offloading using service vehicles. We first build a mathematical model to characterize the deployment cost of multiple cruising routes of the mobile servers and their bases. Next, we design heuristic algorithms to obtain the solutions based on Adelson-Velsky and Landis (AVL)-tree, Gaussian Mixture Model and Simulated Annealing (GMM-SA). The AVL algorithm is used to partition the map into regions and place bases, and the GMM-SA-based algorithm is designed to find the best routes within each region. Experimental results demonstrate that our proposed mobile server deployment scheme achieves the best performance compared with other popular methods in terms of computation resource utilization and travelling distance of the mobile servers.

With the rapid development of 5G communication technology, wireless communication equipment has also surged, resulting in a scarcity of spectrum resources. Cognitive radio networks (CRN) offer a solution to this problem by leveraging radio resource management technology and dynamic spectrum access, which can greatly enhance spectrum utilization. This paper addresses the challenge of how secondary users (SUs) can adopt a reasonable power control strategy to maximize their success rate and throughput while sharing the primary user’s spectrum without causing communication interference. To tackle this challenge, we propose a power control algorithm based on a stacked simple recurrent unit network combined with NoisyNet DQN. This approach combines the advantages of fast parallel training of network parameters in simple recurrent units (SRU) with the high exploratory and robustness provided by the noise network. By training the secondary users with this network model, they can independently adjust their transmission power according to the changing environment without interfering with the primary user (PU). This ultimately improves the average success rate and throughput of secondary users sharing the primary user’s spectrum resources.

In RFID systems, many anti-collision algorithms, driven by the concept of rescheduling the response sequence between the reader and unidentified tags, have been put forward to solve tag collision problem, including ALOHA-based, tree-based and hybrid algorithms. In this paper, we propose a novel RFID anti-collision algorithm called EAQ-CBB, which adopts three main approaches: tag population estimation based on collided bit detection method, optimal partitions and trimmed query tree based on the strategy of collided block bit-mapping (QTCBB). The relatively accurate estimation of tag backlog and optimal partition ensure a great reduction of collisions in the initial phase. For each collided partition, a QTCBB process is introduced immediately, which eliminates all the empty slots and significantly reduces the collided slots. Simulation results show that EAQ-CBB performs good stability and scalability when the key parameters change. Compared with the existing algorithms, such as DFSA, QTI, T-GDFSA and CT, EAQ-CBB outperforms the others with high system throughput, low normalized latency and low normalized overhead at a low cost of energy, which makes it easier to be used widely in the efficient-aware and energy-aware applications.

In this study, a novel general impulsive transition matrix is defined, which can reveal the transition dynamics and probability distribution evolution patterns for all system states between two impulsive "events," instead of two regular time indexes. Based on this general matrix, the policy iteration-based impulsive adaptive dynamic programming (IADP) algorithm along with its variant, which is a more efficient IADP (EIADP) algorithm, are developed in order to solve the optimal impulsive control problems of discrete stochastic systems. Through analyzing the monotonicity, stability, and convergency properties of the obtained iterative value functions and control laws, it is proved that the IADP and EIADP algorithms both converge to the optimal impulsive performance index function. By dividing the whole impulsive policy into smaller pieces, the proposed EIADP algorithm updates the iterative policies in a "piece-by-piece" manner according to the actual hardware constraints. This feature of the EIADP method enables these ADP-based algorithms to be fully optimized to run on all "sizes" of computing devices including the ones with low memory spaces. A simulation experiment is conducted to validate the effectiveness of the present methods.

Abstract The latest research on hybrid networks of decode‐and‐forward (DF) relay and intelligent reflecting surface (IRS) is limited to just a single relay. To harvest multiple relay gains, this paper proposes a hybrid communication networks that combines multiple DF relays with an IRS. The authors formulate and address the joint optimization problem to maximize the end‐to‐end transmission rate by jointly optimizing the reflect beam forming, the best relay selection and the power allocation, subject to total transmit power constraint. Moreover, to better exploit the degrees of freedom, it is proposed that the source also transmits signals in the second time slot. While the optimization problem is difficult to solve, the authors propose some efficient approaches to make the problem tractable. First, power allocation problem is simplified by applying Cauchy‐Schwarz inequality and introducing equivalent channel gain, second, non‐convex rank‐one constraint is overcome by utilizing semidefinite relaxation (SDR) approach, then the slacked non‐convex constraint is overcome by applying first‐order Taylor expansion approximation. The simulation results demonstrate that our proposed joint optimization scheme for hybrid networks of multiple DF relays with an IRS has significant performance improvement over the other optimization schemes, such as the optimization scheme for hybrid networks of single DF relay and an IRS.

For vehicularad hocnetworks (VANETs), edge caching has attracted considerable research attention to maximize the efficiency and reliability of infotainment applications. In this article, we propose a two-layer distributed content caching scheme for VANETs by jointly exploiting the cache at both vehicles and roadside units (RSUs). Specifically, we formulate the content caching problem to minimize the overall transmission delay and cost as a nonlinear integer programming (NLIP) problem and propose an alternate dynamic programming search (ADPS)-based algorithm to solve it. In ADPS, we divide the original problem into three subproblems and then we use the dynamic programming (DP) method to solve each subproblem separately. To reduce the complexity, we further propose a cooperation-based greedy (CBG) algorithm to solve the large-scale original problem. Both numerical simulation results and experiments in the testbed show that the proposed caching scheme outperforms existed caching schemes, and the transmission delay and cost can be reduced by 10% and 24%, respectively, while the hit ratio can be increased by 30% in a practical environment, as compared to the popularity-based caching scheme.

Based on the distributed event-triggered impulsive mechanism, the leader-following mean-square consensus of stochastic multiagent systems with randomly occurring uncertainties and randomly occurring nonlinearities is investigated for the first time in this article. In order to make better use of the limited communication resources, we proposed some novel communication rules among agents and corresponding control protocol. Moreover, some new triggering functions are designed for different types of agents, which cannot only ensure that the Zeno behavior can be excluded but also make the upper bound of impulsive interval in the total time sequence satisfy a newly proposed constraint condition. When the expected value of the triggering function of the i th agent is non-negative within an event time interval, the impulsive control will be triggered. If the system achieves the consensus, the triggering events of all agents will not occur after some time. The original system is transformed into the delay system by using the input delay approach. Based on the Lyapunov stability theory, several sufficient delay-independent criteria for mean-square consensus are derived by a class of Halanay impulsive differential inequalities. Finally, the effectiveness of theoretical results is illustrated by numerical simulation examples.

Wireless body area network (WBAN) suffers secure challenges, especially the eavesdropping attack, due to constraint resources. In this article, deep reinforcement learning (DRL) and mobile edge computing (MEC) technology are adopted to formulate a DRL-MEC-based jamming-aided anti-eavesdropping (DMEC-JAE) scheme to resist the eavesdropping attack without considering the channel state information. In this scheme, a MEC sensor is chosen to send artificial jamming signals to improve the secrecy rate of the system. Power control technique is utilized to optimize the transmission power of both the source sensor and the MEC sensor to save energy. The remaining energy of the MEC sensor is concerned to ensure routine data transmission and jamming signal transmission. Additionally, the DMEC-JAE scheme integrates with transfer learning for a higher learning rate. The performance bounds of the scheme concerning the secrecy rate, energy consumption, and the utility are evaluated. Simulation results show that the DMEC-JAE scheme can approach the performance bounds with high learning speed, which outperforms the benchmark schemes.

Dropout is one of the most widely used methods to avoid overfitting neural networks. However, it rigidly and randomly activates neurons according to a fixed probability, which is not consistent with the activation mode of neurons in the human cerebral cortex. Inspired by gene theory and the activation mechanism of brain neurons, we propose a more intelligent adaptive dropout, in which a variational self-encoder (VAE) overlaps to an existing neural network to regularize its hidden neurons by adaptively setting activities to zero. Through alternating iterative training, the discarding probability of each hidden neuron can be learned according to the weights and thus effectively avoid the shortcomings of the standard dropout method. The experimental results in multiple data sets illustrate that this method can better suppress overfitting in various neural networks than can the standard dropout. Additionally, this adaptive dropout technique can reduce the number of neurons and improve training efficiency.

To solve the problems of poor performance of traditional spectrum sensing method under low signal‐to‐noise ratio, a new spectrum sensing method based on Empirical Mode Decomposition algorithm and K‐means clustering algorithm is proposed. Firstly, the Empirical Mode Decomposition algorithm and the wavelet threshold algorithm are used to remove the noise components in the spectrum sensing signal, and K‐means clustering algorithm is used to determine whether the primary user exists. The method can remove the redundant components such as noise in the nonstationary or nonlinear sampling signal in the real environment and does not need to know the prior information such as signal, channel, and noise, so it can well handle the complicated sensing signal in real environment. This method can reduce the impact of noise on the spectrum sensing system and thus can improve the sensing performance of the system. In the experimental part, the difference between maximum and minimum eigenvalues and the difference between the maximum eigenvalue and the average energy in the random matrix are selected as signal features. Experiments also show that the proposed method is better than the traditional spectrum sensing methods.