Search

In this paper, the singularity-free predefined-time fuzzy adaptive tracking control problem is studied for non-strict feedback (NSF) nonlinear systems considering mismatched external disturbances. An innovative practical predefined-time stability (PPTS) criterion is proposed to provide the theoretical basis for subsequent control design. Compared to the existing predefined-time stability (PTS) criterion, this criterion has a broader application range and can solve the control design issues of nonlinear systems with system uncertainties. Fuzzy logic systems (FLSs) are employed to identify unknown nonlinear functions. Based on the backstepping control technology, a singularity-free predefined-time control (PTC) design method is proposed, in which the hyperbolic tangent function is utilized to avoid the singular problem, and the nature of fuzzy basis function is adopted to resolve the algebraic loop problem. The PPTS of the closed-loop NSF nonlinear system is proven with the Lyapunov theory and the proposed PPTS criterion. Ultimately, the efficiency of the presented PTC design method is verified by several sets of simulations on a single link manipulator system. [ABSTRACT FROM AUTHOR]

Although multimodal physiological data from the central and peripheral nervous systems can objectively respond to human emotional states, the individual differences caused by non-stationary and low signal-to-noise properties bring several challenges to cross-subject emotion recognition tasks. Many previous studies usually focused on learning high correlation information between different modalities, which easily leads to incomplete descriptions of different physiological signals and difficulties in aligning critical emotional information. To tackle these challenges, this paper proposes a novel multimodal emotion recognition model for improving the generalization performance to unseen target domain subjects, termed Completeness-induced Adaptative Broad Learning (CiABL). The proposed CiABL can gradely explore the completeness modality representation that encompasses both modality-relevant and modality-independent information, avoiding the loss of performance due to spurious correlations from different modalities. Subsequently, a well-designed weighted representation distribution alignment mechanism of CiABL can appropriately align the marginal and conditional distributions to reduce the influences of individual differences greatly. Extensive experiments on the SEED and SEED-FRA datasets demonstrate the effectiveness and generalization of the proposed CiABL, which outperforms current state-of-the-art methods. In addition, CiABL can precisely quantify the importance of global features to properly explain the modality contribution and averaged activation patterns of the brain under cross-subject emotion recognition tasks. [ABSTRACT FROM AUTHOR]

Metal oxide composites with graphene/graphene oxide have increasingly gained popularity in enhancing the photocatalytic degradation of several existing harmful dyes. Moreover, identifying the role of carbon networks and their interactions in composite formation would assist in the design and development of photocatalysts. In the present study, we investigated the role of carbon networks in improving photocatalytic properties. Electronic structure analysis of cobalt oxide–graphene (C2)/graphene oxide (C3) nanocomposites using XAS suggested possible charge transfer from cobalt oxide nanoparticles to the carbon network during composite formation. The photocatalytic degradation of C3 towards phenol dye (1 × 10−3 M) was >50% and improved the degradation rate with k = 0.231 h−1.In the quest to understand the mechanism unfolding on its surface, in situ XAS under UV–visible irradiation was performed, which shed light on delayed excitonic recombination in the synthesized nanocomposites. This enabled hydroxy radicals (˙OH) to play a preeminent role in the cleavage of the phenol ring and its intermediaries. Based on these observations, a detailed mechanism for charge transfer occurring during nanocomposite formation and the mechanism involved in the enhanced photocatalytic activity of the nanocomposite photocatalyst towards phenol degradation under the influence of UV–visible irradiation are discussed. [ABSTRACT FROM AUTHOR]

Separable nonlinear models (SNMs) serve as potent instruments for system identification, data analysis, and machine learning. However, the online identification of SNMs poses a greater challenge compared to their offline counterparts, primarily due to the dynamic nature of nonlinear systems. Traditional approaches, including the recursive Gauss–Newton and recursive variable projection methods, falter in managing parameter interdependence, culminating in sluggish convergence and suboptimal outcomes. Addressing these limitations, our study introduces a pioneering multi-innovation-based recursive variabl projection (MIRVP) algorithm, which extends the RVP algorithm with a multi-innovation strategy. This strategy enables the algorithm to handle the interaction of the linear and nonlinear parameters more effectively, by using multiple past innovations instead of only the current one, thus improving the identification effect. The proposed algorithm's effectiveness has been validated through tests on synthetic data, real-life industrial control tracking scenarios such as the Box–Jenkins gas furnace data and Glass tube drawing processing, as well as on the training of large-scale neural networks. The results demonstrate that our algorithm outperforms existing methods in terms of convergence speed and robustness [ABSTRACT FROM AUTHOR]

This paper studies the non-singular practical fixed-time neural adaptive control issues for multi-input and multi-output (MIMO) nonlinear systems with non-strict feedback form. Neural networks (NN) are used to estimate the unknown nonlinearities and deal with the problem of an algebraic loop. Under the framework of the backstepping control design, a practical fixed-time adaptive NN control method is developed by using the adding power integration technology. According to the Lyapunov function theory, it is proved that the closed-loop system is practical fixed-time stable, and the system can track the desired reference signal within a fixed time. Finally, the proposed practical fixed-time control method is applied to a multi-motor control platform, which proves the effectiveness of the control method. [ABSTRACT FROM AUTHOR]

Summary: This article investigates an adaptive neural networks (NNs) tracking control design issue for nonlinear multi‐input and multi‐output (MIMO) systems involving the sensor‐to‐controller event‐triggered mechanism (ETM). In the design, NNs are utilized to approximate the unknown nonlinear functions. A sensor‐to‐controller ETM is designed to save unnecessary transmission and communication resources. Subsequently, a first‐order filter technique is presented to solve the problem that the virtual control function is not differentiable. Furthermore, an event‐triggered adaptive NNs control strategy is presented by constructing Lyapunov functions and using adaptive backstepping recursive design. It is demonstrated that the presented scheme can ensure the whole closed‐loop signals are uniformly ultimately bounded without exhibiting the Zeno behavior. Finally, a numerical simulation example confirms the effectiveness of the presented adaptive event‐triggered control (ETC) approach. [ABSTRACT FROM AUTHOR]

In this study, an adaptive neural network (NN) control is proposed for nonlinear two-degree-of-freedom (2-DOF) helicopter systems considering the input constraints and global prescribed performance. First, radial basis function NN (RBFNN) is employed to estimate the unknown dynamics of the helicopter system. Second, a smooth nonaffine function is exploited to approximate and address nonlinear constraint functions. Subsequently, a new prescribed function is proposed, and an original constrained error is transformed into an equivalent unconstrained error using the error transformation and barrier function transformation methods. The analysis of the established Lyapunov function proves that the controlled system is globally uniformly bounded. Finally, the simulation and experimental results on a constructed Quanser’s test platform verify the rationality and feasibility of the proposed control. [ABSTRACT FROM AUTHOR]

Cross-subject EEG emotion recognition suffers a major setback due to high inter-subject variability in emotional responses. Many prior studies have endeavored to alleviate the inter-subject discrepancies of EEG feature distributions, ignoring the variable EEG connectivity and prediction deviation caused by individual differences, which may cause poor generalization to the unseen subject. This article proposes a graph domain disentanglement network (GDDN) to generalize EEG emotion recognition across subjects in terms of EEG connectivity, representation, and prediction. More specifically, a graph domain disentanglement module is proposed to extract common-specific characteristics on both EEG graph connectivity and graph representation, enabling a more comprehensive network transferability to the unseen individual. Meanwhile, to strengthen stable emotion prediction capability, a domain-adaptive classifier aggregation module is developed to facilitate adaptive emotional prediction for the unseen individual conditioned on the domain weights of the input individuals. Finally, an auxiliary supervision module is imposed to alleviate the domain discrepancy and reduce information loss during the disentanglement learning. Extensive experiments on three public EEG emotion datasets, i.e., SEED, SEED-IV, and MPED, validate the superior generalizability of GDDN compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

EEG emotion recognition has been hampered by the clear individual differences in the electroencephalogram (EEG). Nowadays, domain adaptation is a good way to deal with this issue because it aligns the distribution of data across subjects. However, the performance for EEG emotion recognition is limited by the existing research, which mainly focuses on the global alignment between the source domain and the target domain and ignores much fine-grained information. In this study, we propose a method called Graph-based Unsupervised Subdomain Adaptation (Gusa), which simultaneously aligns the distribution between the source and target domains in a fine-grained way from both the channel and emotion subdomains. Gusa employs three modules, such as the Node-wise Domain Constraints Module to align each EEG channel and obtain a domain-variant representation, the Class-level Distribution Constraints Module, and the Emotion-wise Domain Constraints Module, to collect more fine-grained information, create more discriminative representations for each emotion, and lessen the impact of noisy emotion labels. The studies on the SEED, SEED-IV, and MPED datasets demonstrate that Gusa significantly improves the ability of EEG to recognize emotions and can extract more granular and discriminative representations for EEG. [ABSTRACT FROM AUTHOR]

Summary: In this paper, the problem of adaptive security control for a class of nonlinear multi‐agent systems (MASs) under deception attacks is studied. This scheme aims to design a new adaptive fuzzy control scheme for each subsystem of MASs to reduce the impact of network attacks (from sensor to controller) on state signals, and proposes Nussbaum function to deal with unknown time‐varying control directions. In addition, for multi‐agent systems, a finite‐time convergent security control scheme is designed to ensure the convergence of tracking error and the boundedness of signals in the closed‐loop system. Finally, the effectiveness of the proposed method is verified by a simulation example. [ABSTRACT FROM AUTHOR]

Imbalanced learning constitutes one of the most formidable challenges within data mining and machine learning. Despite continuous research advancement over the past decades, learning from data with an imbalanced class distribution remains a compelling research area. Imbalanced class distributions commonly constrain the practical utility of machine learning and even deep learning models in tangible applications. Numerous recent studies have made substantial progress in the field of imbalanced learning, deepening our understanding of its nature while concurrently unearthing new challenges. Given the field’s rapid evolution, this paper aims to encapsulate the recent breakthroughs in imbalanced learning by providing an in-depth review of extant strategies to confront this issue. Unlike most surveys that primarily address classification tasks in machine learning, we also delve into techniques addressing regression tasks and facets of deep long-tail learning. Furthermore, we explore real-world applications of imbalanced learning, devising a broad spectrum of research applications from management science to engineering, and lastly, discuss newly-emerging issues and challenges necessitating further exploration in the realm of imbalanced learning. [ABSTRACT FROM AUTHOR]

This paper addresses integral sliding mode output feedback fault-tolerant control (FTC) of unmanned marine vessels (UMVs) with unknown premise variables and actuator faults. Due to the complexity of the marine environment, the presence of uncertainties in the yaw angle renders the premise variables in the Takagi–Sugeno (T–S) fuzzy model of UMVs unknown. Consequently, traditional integral sliding mode techniques become infeasible. To address this issue, a control strategy combining integral sliding mode based on output feedback with a compensator utilizing switching mechanisms is proposed. First, a radial basis function neural network is used to approximate the nonlinear terms in the UMV T–S fuzzy model. In addition, an integral sliding mode surface is constructed based on fault estimation information and membership function estimation. On this basis, an FTC scheme based on integral sliding mode output feedback is developed to ensure that the UMV system is asymptotically stable and satisfies the prescribed H ∞ performance index. Finally, simulation results are provided to demonstrate the effectiveness of the presented control strategy. [ABSTRACT FROM AUTHOR]

Environmental protection and energy conservation have become highly concerning themes. In the transportation field, green electric vehicles (EVs) are rapidly being promoted and applied, and power sources, as one of the core technologies, greatly affect the working performances of EVs. Currently, a single battery power supply is the mainstream configuration for EVs, but the instantaneous/short-term high-power output required by the battery for vehicle working conditions has a serious impact on the service life of the battery. As an effective solution, the battery/super-capacitor (SC) hybrid power source (HPS) has attracted increasing attention. This article proposes an improved semi-active battery/SC HPS, which can achieve multiple operating modes and fully utilize the advantages of the two power sources to effectively protect the battery. A fitness function is established with the optimization objective of minimizing the HPS cost and the number of cells in SC and battery as control variables. A genetic algorithm (GA) is adopted to optimize the HPS configuration based on the power required of the New European Driving Cycle (NEDC) working condition. The optimized number of battery cells is 777, much smaller than the 1191 calculated based on theoretical formulas. Additionally, a logic threshold strategy is introduced to flexibly control the collaborative work of the two power sources and achieve effective energy management. The availability of the presented control method of HPS in various working modes is verified through MATLAB/Simulink-based modeling and simulation. This work provides a theoretical reference for the application research of HPS in EVs. [ABSTRACT FROM AUTHOR]

In view of the input dead‐zone, unknown control direction and difficulty in satisfying the prescribed performance that suffered in practical systems, an improved prescribed performance‐based adaptive control scheme is stressed for uncertain nonlinear systems in this paper. Firstly, by adopting a characteristic function, the input dead‐zone is linearized to a model with bounded perturbation. To settle the "computation complexity" issue, an adaptive controller is built via command filter design method, where the fuzzy logic systems are introduced to approximate the unknown nonlinearities. Meanwhile, the Nussbaum function is brought in controller design to counter the hardship of unknown control direction. Besides, the tracking error can be restricted in the prescribed boundary in finite time with the improved performance function. The presented control approach can not only ensure the finite‐time convergence property of tracking error and the boundedness of all signals in the closed‐loop system, but also easily implement in engineering. Finally, the simulation examples confirm the validity of the designed control scheme. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (Re-ID) is more substantial than the supervised one because it does not require any labeled samples. Currently, the most advanced unsupervised Re-ID models generate pseudo-labels to group images into different clusters and then establish a memory bank to calculate contrastive loss between instances and clusters. This framework has been proven to be remarkably efficient for unsupervised person Re-ID tasks. However, clustering operation inevitably produces misclassification, which brings noises and difficulties to contrastive learning and affects the initialization and updating of the prototype features stored in the memory bank. To solve this problem, we propose a new robust unsupervised person Re-ID model with two developed modules: Cluster Sample Aggregation module (CSA) and Hard Positive Sampling strategy (HPS). The CSA module aggregates each sample in the same cluster through the multi-head self-attention mechanism. This process enables the initialization of prototypes based on the similarities observed within clusters. Additionally, the HPS strategy extracts the dispersion degree of each sample by means of a self-attention aggregation module (SAA) that has been trained by CSA module. According to the obtained indicators, the hardest positive sample is sampled to update the prototype feature stored in the memory bank. With the self-attention mechanism fusing the information among instances in each cluster, the implicit relationships between samples can be better explored in a more refined way. Experiments show that our method achieves state-of-the-art results against existing unsupervised baselines on Market-1501, PersonX, and MSMT17 datasets. [ABSTRACT FROM AUTHOR]

Representation-based methods have found widespread applications in various classification tasks. However, these methods cannot deal effectively with imbalanced data scenarios. They tend to neglect the importance of minority samples, resulting in bias toward the majority class. To address this limitation, we propose a density-based discriminative nonnegative representation approach for imbalanced classification tasks. First, a new class-specific regularization term is incorporated into the framework of a nonnegative representation based classifier (NRC) to reduce the correlation between classes and improve the discrimination ability of the NRC. Second, a weight matrix is generated based on the hybrid density information of each sample’s neighbors and the decision boundary, which can assign larger weights to minority samples and thus reduce the preference for the majority class. Furthermore, the resulting model can be efficiently optimized through the alternating direction method of multipliers. Extensive experimental results demonstrate that our proposed method is superior to numerous state-of-the-art imbalanced learning methods. [ABSTRACT FROM AUTHOR]

This paper focuses on the significant and practical problem that how to improve communication rate between neighbor agents for high-order nonlinear multiagent systems. This issue shall be addressed by establishing a series of event-triggered mechanisms between neighbor agents, such that neighbor signals are transmitted only when the preset events are activated. By utilizing backstepping approach, a novel event-triggered consensus controller design procedure is elaborated. Initially, the uncertainties of the systems are handled by radial basis function neural network, whose unknown weight vectors can be estimated by only one required adaptive law. Next, a novel consensus control strategy is proposed to resolve a contradiction between communication rate and system performance. Stability analysis of the control algorithm is then strictly proved by Lyapunov functional theory. This ensures that all the closed-loop signals remain bounded and the consensus errors converge exponentially to an adjustable domain. Simulation studies at the end demonstrate the effectiveness of this method. [ABSTRACT FROM AUTHOR]

EEG emotion recognition plays a significant role in various mental health services. Deep learning-based methods perform excellently, but still suffer from interpretability. Although methods such as Gradient-weighted Class Activation Mapping(Grad-CAM) can cope with the above problem, their coarse granularity cannot accurately reveal the mechanism to promote emotional intelligence. In this paper, fine-grained interpretability is proposed, called Concat-aided Grad-CAM. Specifically, the multi-level feature mapping before the fully connected layer is concatenated to obtain the gradients of the target concept so that the discriminant information can be directly located in the high-precision area. Unlike coarse-grained interpretability methods applied in EEG emotion recognition, it can accurately highlight the EEG channels related to emotion rather than an obscure area. In addition, a systematic brain functional network is proposed to reveal the relationship between those channels and to further improve emotion recognition performance. The channels with greater contributions are connected, and those connections are learned by dynamic graph convolutional networks, while the others are independent to eliminate interference. Experiments on four EEG emotion recognition datasets manifest that Concat-aided Grad-CAM can be interpreted by the fine-grained. In addition, it has been shown that the learned brain functional network can improve the performance of the baselines. Significantly, the experiment results achieve state-of-the-art performance in multiple experiments. [ABSTRACT FROM AUTHOR]

In addition to stability, the system optimality has also received attention because the system is expected to achieve higher performance with lower energy consumption. In general, the conventional approach to achieve optimal control of nonlinear MIMO systems is to solve the Hamilton–Jacobi–Bellman equation directly, which is time-consuming and sometimes impossible. To address this issue, this paper proposes an adaptive neural inverse optimal control method for uncertain MIMO systems. The method is based on an improved design criterion for the inverse optimal controller, which avoids the need for constructing auxiliary systems and enables direct stability analysis of MIMO systems. Additionally, an adaptive one-parameter update strategy is proposed to reduce the computational effort, which avoids the need to update the entire neural network. The proposed scheme guarantees that the tracking errors of the MIMO system converge to a given domain while minimizing a family of meaningful loss functions. Finally, the effectiveness of the presented method is verified through simulations. [ABSTRACT FROM AUTHOR]

This article investigates the problem of inverse optimal fixed-time tracking for nonlinear switched systems. Given this, a control scheme is developed based on an adaptive direct fuzzy inverse optimal and fixed time. The proposed control strategy accomplishes optimal performance without solutions for the Hamiltonian function. On the other hand, this scheme designs inverse optimal controller and virtual controller without involving partial differential derivative terms, using a one-parameter learning mechanism so that the time difference of the Lyapunov function is non-positive. Two common Lyapunov function candidates are employed to demonstrate that the proposed control scheme stabilizes the switched system and the tracking error converges to a predefined region. [ABSTRACT FROM AUTHOR]

With the rapid increase of economic globalization, the significant expansion of shipping volume has resulted in shipping route congestion, causing the necessity of trajectory prediction for effective service and efficient management. While trajectory prediction can achieve a relatively high level of accuracy, the performance and generalization of prediction models remain critical bottlenecks. Therefore, this article proposes a dual-attention (DA) based end-to-end (E2E) neural network (DAE2ENet) for trajectory prediction. In the E2E structure, long short-term memory (LSTM) units are included for the task of pursuing sequential trajectory data from the encoder layer to the decoder layer. In DA mechanisms, global attention is introduced between the encoder and decoder layers to facilitate interactions between input and output trajectory sequences, and multi-head self-attention is utilized to extract sequential features from the input trajectory. In experiments, we use a ro-ro ship with a fixed navigation route as a case study. Compared with baseline models and benchmark neural networks, DAE2ENet can obtain higher performance on trajectory prediction, and better validation of environmental factors on ship navigation. [ABSTRACT FROM AUTHOR]

Collaborative representation-based classification (CRC) has been extensively applied to various recognition fields due to its effectiveness and efficiency. Nevertheless, it is generally suboptimal for imbalanced learning. Previous studies have revealed that a class-imbalance distribution can lead CRC, and even most conventional classification methods, to ignore the minority class and prioritize the majority class. To address this deficiency, this paper proposes a hybrid density-based adaptive weighted collaborative representation model that incorporates a regularization technique and an adaptive weight generation mechanism into the CRC framework. A new regularization term, based on class-specific representation, is introduced to decrease the correlation between classes and enhance CRC's discriminative ability. The sample distribution and density information within and between classes are employed to assign greater weights to minority samples, thereby strengthening the representation capabilities of minority samples and reducing the bias towards the majority class. Furthermore, it is theoretically demonstrated that this model has a closed-form solution. Its complexity is comparable to that of CRC, ensuring its efficiency. Extensive experiments on diverse data sets from the KEEL repository show the superiority of the proposed method compared to other state-of-the-art imbalanced classification methods. [ABSTRACT FROM AUTHOR]

This paper proposes a non‐singular fixed‐time fault‐tolerant adaptive tracking control method for a kind of multi‐input and multi‐output nonlinear system, which is in form of non‐strict feedback and is subject to actuator faults. The major contribution, compared to other practical fixed‐time fault‐tolerant control methods, is that the fixed time can be calculated precisely. By applying fuzzy logic systems, the identification of unknown nonlinearities is achieved, and by the boundness of fuzzy basis functions, the algebraic loop problem is avoided. Based on the fixed‐time stability theory, the practical fixed‐time fault‐tolerant adaptive tracking control method is proposed with adaptive back‐stepping control technology, in which the control singular problem is overcome by applying the adding power integration method. By the Lyapunov function theory, the practical fixed‐time stability of the closed‐loop system is theoretically proved. And even in the case of unknown actuator faults, the tracking error of the controlled system for the given command signal can still converge to a small neighbourhood of zero within a fixed time, regardless of the system initial state. Finally, the proposed control method is successfully implemented on a multi‐motor control platform, proving its effectiveness, and multiple comparative simulations are carried out, demonstrating its superiority. [ABSTRACT FROM AUTHOR]

Promoting cooperation in the network has always been a focus of evolutionary game dynamics research. In this paper, a three-strategy local decision model is designed to promote cooperative behavior between agents. The hide right is introduced to accurately describe the agents which tend to choose conservative strategy to achieve stable payoffs. Agents only consider their own and non-defective neighbors' payoffs information to make their decisions for next move. According to the adaptive dynamics, the equilibrium states under different conditions have been studied. It is found that the introduction of hide strategy helps to reduce the occurrence of defection. The conclusion of this paper will provide a reference for the cooperation promotion mechanism of selfish agents that are closer to the actual situation. [ABSTRACT FROM AUTHOR]

For uncertain interconnected MIMO nonlinear systems with Preisach-type hysteresis inputs, the construction of a control strategy such that the fixed-time stability and the presettable steady-state tracking performance can be established simultaneously has not yet been achieved in the existing literature, despite theoretical and practical importance of such a problem. Technically, establishing the fixed-time stability needs the construction of a stringent Lyapunov-based conditional inequality, which is indeed not a trivial task when the existence of interconnection of subsystems, Preisach-type hysteresis inputs, and uncertain unparametrizable nonlinear dynamics, in particular when the predefined steady-state tracking accuracy needs to be established at the same time. To fill in the gap, and overcome the difficulties, in this paper, we propose a novel adaptive fuzzy control approach, for which a robust adaptive framework is developed to accommodate hysteresis nonlinearities and plant dynamics, and a smooth functions-based backstepping design is presented to construct a scheme capable of achieving the desired system performances. With our approach, it can be proved that all signals in the closed-loop system are bounded, and the tracking error for each subsystem converges to the predetermined interval in fixed time. Simulation and experimental tests are conducted to confirm the obtained results. [ABSTRACT FROM AUTHOR]

Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually use the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to that of the NLA with randomly selected regions prompted us to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and a pre-trained model were uploaded to GitHub (https://github.com/laoyangui/HSPAN) for validation. [ABSTRACT FROM AUTHOR]

This paper presents a study of the cooperative optimal swarm control problem for two‐order multi‐agent systems with partially unknown nonlinear functions. Unlike traditional approaches that consider a single error, this paper proposes to use multi‐order errors in the performance index function to achieve optimal control performance. Additionally, different proportional coefficients are assigned to illustrate the varying influences of each sequence error, and a two‐order cooperative (TOC)performance index function is designed. To address the influence of unknown nonlinear functions, a swarm control system based on sliding mode control with an actor‐critic network is constructed, which increases the applicability of the proposed method to a variety of dynamic models. Furthermore, to alleviate the computational pressure caused by the multi‐order errors in the TOC performance index function, a new reinforcement learning (RL)‐based sliding mode swarm controller is designed. The stability of the proposed controller is demonstrated using the Lyapunov function. Finally, the control model and control rate are applied to a quadrotor unmanned aerial vehicle system, and simulation results demonstrate that the multi‐agent systems can effectively achieve swarm control. Impact Statement: This paper proposes a reinforcement learning‐based sliding mode control strategy for the cooperative optimal swarm control problem, where the nonlinear functions of two‐order multi‐agent systems are only partially known. In addition, we also propose a cooperative performance index function, which takes into account multi‐order errors for optimizing the performance. This contribution is significant for research in sliding mode control strategies and error co‐optimization. [ABSTRACT FROM AUTHOR]

This work aims to address two issues that often exist in least square regression (LSR) models for classification tasks, which are (1) learning a compact projection matrix for feature selection and (2) adopting relaxed regression targets. To this end, we first propose a sparse regularized LSR framework for feature selection by introducing the ℓ 2 , 1 regularizer. Second, we utilize two different strategies to relax the strict regression targets based on the sparse framework. One way is to exploit the -dragging technique. Another strategy is to directly learn the labels from the inputs and constrain the distance between true and false classes simultaneously. Hence, more feasible regression schemes are constructed, and the models will be more flexible. Further, efficient iterative methods are derived to optimize the proposed models. Various experiments on image databases intend to manifest our proposed models have outstanding recognition capability compared with many state-of-the-art classifiers. [ABSTRACT FROM AUTHOR]

In the present study, synchrotron-based X-ray diffraction (XRD), X-ray absorption spectroscopy (XAS) and X-ray excited optical luminescence (XEOL) have been used to investigate the induced defect states in metal oxide nanomaterials. Specifically, two synthesis approaches have been followed to develop unique nano-sized peanut-shaped (N-ZnO) nanostructures and micron-sized hexagonal rods (M-ZnO). XANES analysis at the Zn K-edge revealed the presence of defect states with a divalent oxidation state of zinc (Zn2+) in a tetrahedral structure. Furthermore, XAS measurements performed at the Zn L3,2-edge and O K-edge confirm higher oxygen-related defects in M-ZnO, while N-ZnO appeared to have a higher concentration of surface defects due to size confinement. Moreover, the in-line XEOL and time dependent-XEOL measurements exposed the radiative excitonic recombination phenomena occurring in the band-tailing region as a function of absorption length, X-ray energy excitation, and time. Based on the chronology developed in the defect state improvement, a possible energy band diagram is proposed to accurately locate the defect states in the two systems. Furthermore, the increased absorption intensity at the Zn L3,2-edge and the O K-edge under the UV lamp suggests delayed recombination of electrons and holes, highlighting their potential use as photo catalysts. The photocatalytic activity degrading the rhodamine B dye established M-ZnO as a superior catalyst with a rapid degradation rate and significant mineralization. Overall, this work provides valuable insights into ZnO defect states and provides a foundation for efficient advanced materials for environmental or other optoelectronic applications. [ABSTRACT FROM AUTHOR]

When a multi-modal affective analysis model generalizes from a bimodal task to a trimodal or multi-modal task, it is usually transformed into a hierarchical fusion model based on every two pairwise modalities, similar to a binary tree structure. This easily leads to large growth in model parameters and computation as the number of modalities increases, which limits the model's generalization. Moreover, many multi-modal fusion methods ignore that different modalities contribute differently to affective analysis. To tackle these challenges, this article proposes a general multi-modal fusion model that supports trimodal or multi-modal affective analysis tasks, called Multi-modal Interactive Attention Network (MIA-Net). Instead of treating different modalities equally, MIA-Net takes the modality that contributes the most to emotion as the main modality and the others as auxiliary modalities. MIA-Net introduces multi-modal interactive attention modules to adaptively select the important information of each auxiliary modality one by one to improve the main-modal representation. Moreover, MIA-Net enables quick generalization to trimodal or multi-modal tasks through stacking multiple MIA modules, which maintains efficient training and only requires linear computation and stable parameter counts. Experimental results of the transfer, generalization, and efficiency experiments on the widely-used datasets demonstrate the effectiveness and generalization of the proposed method. [ABSTRACT FROM AUTHOR]

Iron- and steel-making industry is one of the most water-intensive industries. An industrial wastewater purification plant using ultrafiltration and reverse osmosis is utilized by the iron and steel production industry to reclaim wastewater from the manufacturing processes. After sustained operation, the ultrafiltration membranes suffered from severe fouling problems. The frequent and necessary chemical cleaning results in raised operating cost, reduced permeate, and shortened membrane lifetime. The objective of this research was to identify the major foulants that result from long-term real-world operation of the ultrafiltration system. The fouled ultrafiltration membrane samples were collected four times during a 1.5-year period. Scanning electron microscope with energy-dispersive spectrometer, loss on ignition, and fouling resistance analysis were conducted to characterize the foulants. We identify iron (Fe) and manganese (Mn) oxides as the major foulants on the membrane surface and in the pores. We also demonstrate that irrecoverable fouling as the major contributor to fouling resistance, accounting for approximately 43 ~ 47% of the total increase in resistance. Based on our data, the irrecoverable fouling likely begins with the deposit of Fe and Mn ions and oxide particulates within the membrane pores, following by accumulation of additional oxides in part through an autocatalytic process, which ultimately leads to pore clogging. Therefore, pretreatment of the ultrafiltration influent to remove Fe and Mn ions can be a sound strategy to mitigate irrecoverable fouling. [ABSTRACT FROM AUTHOR]

In this paper, the secure state estimation attack and reconstruction problems are considered for linear cyber‐physical systems (CPSs) under actuator attacks and unknown disturbances. By introducing a continuous sliding mode observer with an exponential reaching law strategy, the dynamic quality of approach motion is greatly improved and the chattering is eliminated. Then by transforming the original system into a special attack channel separation form so that an improved sliding mode observer with disturbance compensation is obtained to solve the secure state estimation problem. In addition, with the obtained observer's information, not only the actuator attack can be reconstructed but also the estimation of the disturbance can be obtained. Meanwhile, the influence of disturbance estimation error on attack reconstruction can be attenuated. Finally, simulations on a VTOL aircraft are presented to verify the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Target tracking has a wide range of applications in intelligent transportation, real‐time monitoring, human‐computer interaction and other aspects. However, in the tracking process, the target is prone to deformation, occlusion, loss, scale variation, background clutter, illumination variation, etc., which bring great challenges to realize accurate and real‐time tracking. Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking, ensuring both accuracy and real‐time performance. However, due to its offline training, it is difficult to deal with the fast motion, serious occlusion, loss and deformation of the target during tracking. Therefore, it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online. The broad learning system (BLS) has a simple network structure, high learning efficiency, and strong feature learning ability. Aiming at the problems of Siamese networks and the characteristics of BLS, a target tracking method based on BLS is proposed. The method combines offline training with fast online learning of new features, which not only adopts the powerful feature representation ability of deep learning, but also skillfully uses the BLS for re‐learning and re‐detection. The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on, so as to change the selection of the Siamese networks search area, solve the problem that the search range cannot meet the fast motion of the target, and improve the adaptability. Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios. [ABSTRACT FROM AUTHOR]

With the rapid growth of shipping volumes, ship navigation and path planning have attracted increased attention. To design navigation routes and avoid ship collisions, accurate ship trajectory prediction based on automatic identification system data is required. Therefore, this study developed an encoder–decoder learning model for ship trajectory prediction, to avoid ship collisions. The proposed model includes long short-term memory units and an attention mechanism. Long short-term memory can extract relationships between the historical trajectory of a ship and the current state of encountered ships. Simultaneously, the global attention mechanism in the proposed model can identify interactions between the output and input trajectory sequences, and a multi-head self-attention mechanism in the proposed model is used to learn the feature fusion representation between the input trajectory sequences. Six case studies of trajectory prediction for ship collision avoidance from the Yangtze River of China and the eastern coast of the U.S. were investigated and compared. The results showed that the average mean absolute errors of our model were much lower than those of the classical neural networks and other state-of-the-art models that included attention mechanisms. [ABSTRACT FROM AUTHOR]

This research investigates the fixed‐time event‐triggered consensus tracking control for a class of uncertain nonlinear multiagent systems (MASs) under directed graphs. In MASs, frequent and continuous communication is difficult to achieve because the network bandwidth of the system is limited. In addition, unknown nonlinearities and dead‐zone input may exacerbate the communication burden of the system. It is challenging to guarantee the fixed‐time stability of the system when it suffers from these constraints. To overcome the above problems, based on the radial basis neural networks and backstepping technology, an event‐triggered mechanism is designed to reduce the frequency of control input updates and compensate for the dead‐zone input. On this basis, a novel consensus tracking control protocol is established based on the practically fixed‐time stability theorem. Technically, by using the protocol, the system is practically fixed‐time stable, even under the effect of those aforementioned constraints. Finally, some simulation examples validate the validity of the proposed protocol. [ABSTRACT FROM AUTHOR]

Summary: In this paper, we propose a heterogeneous swarm control method based on a two‐layer communication topology, which solves the problems of great difficulty in controller design and high computational complexity of communication topology in large‐scale heterogeneous swarm control. Firstly, we divide large‐scale heterogeneous swarms into several independent isomorphic sub‐swarm and design corresponding sub‐swarm controllers, which dramatically reduces the difficulty of swarm controller design. Secondly, we introduce a two‐layer communication topology to treat the followers in the first‐layer communication topology as leaders in the second‐layer communication topology, which establishes the connection between each sub‐swarm and the global leader and reduces the computational complexity of the communication topology. Finally, based on the two‐layer communication topology, the swarm controllers in the first‐layer and second‐layer communication topologies are designed using the sliding mode and dynamic surface methods. The Lyapunov function is designed to prove its stability. The simulation results verify the effectiveness of the controllers. [ABSTRACT FROM AUTHOR]

Introduction: Alzheimer's disease (AD) is a chronic neurodegenerative disease of the brain that has attracted wide attention in the world. The diagnosis of Alzheimer's disease is faced with the dificulties of insufficientmanpower and great dificulty. With the intervention of artificial intelligence, deep learning methods are widely used to assist clinicians in the early recognition of Alzheimer's disease. And a series of methods based on data input with different dimensions have been proposed. However, traditional deep learning models rely on expensive hardware resources and consume a lot of training time, and may fall into the dilemma of local optima. Methods: In recent years, broad learning system (BLS) has provided researchers with new research ideas. Based on the three-dimensional residual convolution module and BLS, a novel broad-deep ensemble model based on BLS is proposed for the early detection of Alzheimer's disease. The Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI image dataset is used to train the model and then we compare the performance of proposed model with previous work and clinicians' diagnosis. Results: The result of experiments demonstrate that the broad-deep ensemble model is superior to previously proposed related works, including 3D-ResNet and VoxCNN, in accuracy, sensitivity, specificity and F1. Discussion: The proposed broad-deep ensemble model is effective for early detection of Alzheimer's disease. In addition, the proposed model does not need the pre-training process of its depth module, which greatly reduces the training time and hardware dependence. [ABSTRACT FROM AUTHOR]

In modern precision medicine, it is an important research topic to predict cancer drug response. Due to incomplete chemical structures and complex gene features, however, it is an ongoing work to design efficient data-driven methods for predicting drug response. Moreover, since the clinical data cannot be easily obtained all at once, the data-driven methods may require relearning when new data are available, resulting in increased time consumption and cost. To address these issues, an incremental broad Transformer network (iBT-Net) is proposed for cancer drug response prediction. Different from the gene expression features learning from cancer cell lines, structural features are further extracted from drugs by Transformer. Broad learning system is then designed to integrate the learned gene features and structural features of drugs to predict the response. With the capability of incremental learning, the proposed method can further use new data to improve its prediction performance without retraining totally. Experiments and comparison studies demonstrate the effectiveness and superiority of iBT-Net under different experimental configurations and continuous data learning. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification has continued to be a hot research topic in recent years, and the broad learning system (BLS) has been considered by scholars for the classification of HSIs due to its superior internal structure. Different from the traditional HSI classification mechanism, this paper proposes an active broad learning system approach for HSI classification. The spectral and spatial features of the image are extracted using principal component analysis and local binary patterns, respectively. Then, the vector fusion of the above two features is utilized as the input of the BLS and trained to obtain pre-labels of the samples. The next training samples are selected among the pre-labels by active learning. Unlike other classification algorithms, the method proposed in this paper utilizes active learning (AL) to select high-quality samples for training, thereby reducing the number of samples used and the cost of sample labeling. In addition, the use of incremental learning in broad learning significantly reduces the training time and improves the classification accuracy. The algorithm proposed in this paper is more effective compared to other state-of-the-art algorithms on three HSI datasets. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of fixed-time control and pre-described tracking performance design for time-varying uncertain nonlinear systems. Unlike the pure robust control, the proposed so-called nominal substitution method avoids unnecessarily high gain and noise amplification. The control problem for n-dimensional time-varying uncertain nonlinear systems is discussed to show how to combine the nominal substitution method with adaptive fuzzy fixed-time control and a singularity-avoidance virtual controller design. To achieve pre-described tracking performance in a fixed-time convergence environment, a projection operator-based adaptive algorithm and a series of symbolic-like functions are introduced in the control design. It is shown that the proposed control method can guarantee that the tracking error asymptotically converges to a user-defined accuracy within a pre-described fixed time. Two simulation results, including comparison experiments and analysis of practical examples, verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Broad learning system (BLS) is a fast and efficient learning model. However, BLS has limited representation capacity in the feature mapping layer. Additionally, BLS lacks local mapping capability. To address these problems, a cascaded neural network framework based on a sparse polynomial-based RBF neural network and an attention-based broad learning system (SPRBF-ABLS) is proposed. We first propose a sparse polynomial weight-based RBF neural network (SPRBF) for feature mapping. Then an attention mechanism for BLS is proposed to enhance the representation capacity of BLS. The proposed model is evaluated on regression, classification, and face recognition datasets. In regression and classification experiments, the nonlinear approximation capability of the proposed model outperforms other BLS models. In face recognition experiments, the proposed model can improve the representation capacity, especially the robustness against noisy images. The experiments demonstrate the effectiveness and robustness of the proposed model. [ABSTRACT FROM AUTHOR]

This work investigates a Neural Network‐ (NN) based event‐triggered finite‐time control for a class of uncertain nonlinear systems with full‐state constraints and actuator failures. Firstly, practical engineering systems are widely affected by state constraints, actuator failures, etc. Violation of constraints would considerably affect the system's performance. Especially, it is challenging to guarantee system stability when the system is subject to these constraints, which are uncertain in time, form, and value. To address these issues, an intelligent control method is constructed based on logarithm‐type Barrier Lyapunov Functions and Backstepping technology. Furthermore, consider that bandwidth resources are limited in practical engineering systems, and the excellent convergence performance of the system is the actual industrial requirement. Thus, a NN‐based event‐triggered finite‐time control strategy is established to save bandwidth and achieve finite‐time convergence of the system. Finally, theoretical analysis and simulation examples are presented to demonstrate the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

This paper investigates a fault-tolerant control problem for the dynamic positioning of unmanned marine vehicles based on a Takagi–Sugeno (T-S) fuzzy model using an integral sliding mode scheme. First, the T-S fuzzy model of an unmanned marine vehicle is established by taking the yaw angle variable range into account. An integral sliding mode control scheme combined with the H ∞ performance index is then developed to attenuate the initial influence of thruster faults and ocean disturbances. The unknown nonlinear function is approximated using a fuzzy logic system based on a representation of marine data, which provides a good tradeoff between resolution of the unknown nonlinear term approximation and computational complexity for marine engineering by adjusting the number of fuzzy logic system rules. In addition, the fault estimation information is utilized to design the sliding mode surface on the basis of an adaptive mechanism and a matrix full rank decomposition technique, which reduces conservatism. The validity of the proposed approach is finally demonstrated by an analysis of simulation results using a typical floating production vessel model. [ABSTRACT FROM AUTHOR]

This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. By introducing a series of event sequences, a new multiphase constrained optimal control formulation is constructed to describe the automatic overtaking process. Although existing trajectory optimization techniques can be applied to address the constructed problem, they may suffer from poor or premature convergence issues due to the complexity of the mission formulation. Thus, to offer an effective alternative, a novel desensitized trajectory optimization method is designed and implemented to explore the optimal overtaking maneuver for the AGVs. The proposed method applies a double layer structure, where an enhanced intelligent optimization method is used in the outer layer such that the main inner optimization routine can be boosted by starting at a better reference solution. The algorithm convergence as well as the solution optimality conditions are theoretically analyzed. Numerical results are provided to illustrate the validity of the established formulation. Comparative case studies were executed to demonstrate the quality of the obtained solution and the enhanced performance of the proposed trajectory optimization method. [ABSTRACT FROM AUTHOR]

Heterointerfaces between two insulators play a central role in the study of oxide electronics owing to a spectrum of emergent properties. Manipulating transport of the interface by light can result in significant modulation of the ground state and excite localized states. However, their dynamics and mechanisms of photogenerated carries remain unclear. Here, this study presents the dynamics of carrier density and mobility under and after light illumination by Hall effect over time. It is discovered that the density and mobility after light illumination obey a stretched exponential expression, further indicating that the variation of mobility caused by the electron-electron scattering plays an important role in the recovery process in addition to the reduction of carrier density. Meanwhile, a non-linear Hall resistance at the LaAlO3/SrTiO3 interface under the illumination of a 360 nm laser at low temperature is observed. Furthermore, the gating effect can tune the recovery process after light illumination and induce a disappearance of non-linear Hall resistance. The results provide the experimental support for detailed mechanisms of the nonequilibrium process and developing of all-oxide electronic devices based on heterointerfaces. [ABSTRACT FROM AUTHOR]

This article considers the multi‐consensus recovery for multi‐agent systems (MASs) when the communication network is under cyber‐attack. For distributed control of multi‐consensus, cyber‐attack will invalidate the communication links and seriously affect information interaction between agents, resulting in the destruction of original multi‐consensus. This article considers the design of a recovery topology reconstruction controller, which can ensure the recoverability of original multi‐consensus under cyber‐attack. First, some properties of multi‐consensus of MAS are analyzed. And the cyber‐attack model with the communication link as the attack location is described. Moreover, in order to ensure the simplification of the controller and maintain weak connectivity of original topology under the premise of recovering multi‐consensus, the topology reconstruction controller is further optimized and an optimization algorithm is proposed. Finally, the feasibility and validity of theoretical results are verified by numerical simulations. [ABSTRACT FROM AUTHOR]

In practice, deception attacks, uncertainties, and randomly occurring nonlinearities (RONs) in multi‐agent systems (MASs) are ubiquitous. Consequently, this paper settles the problem of secure consensus tracking control for uncertain MASs with randomly occurring nonlinearities under sensor attacks by adopting adaptive impulsive control methods. Compared with the previous works, a class of state‐dependent sensor attack is firstly considered in the impulsive control. Meanwhile, a novel adaptive algorithm is introduced to deal with unknown system matrices, randomly occurring nonlinearities and uncertain parameters caused by sensor attacks. Sufficient conditions are derived to achieve leader‐following consensus for the MASs by adaptive impulsive control under sensor attacks. Lastly, two simulation examples illustrate the validity of theorems in this paper. [ABSTRACT FROM AUTHOR]

Smartload with series-connected dc electric spring (ES) and noncritical load (NCL) structure can compensate for load voltage and improve the power quality. In this article, a distributed virtual inertial control framework based on model predictive control is proposed for low inertia in the dc microgrid. First, the current prediction model of the ES bidirectional full-bridge dc/dc converter is presented. Based on the virtual inertia control, model predictive control is used to optimize virtual capacitance during the operation. When the system suffers from disturbance, virtual capacitance increases to slow down the change of the dc bus voltage. When disturbance happens, the system can be stabilized quickly by reducing the virtual capacitance. Then, the consensus algorithm based on distributed control is established after defining the NCL voltage deviation rate, which can achieve the balance of NCL voltage deviations, and effectively avoid the more significant voltage deviation in one of NCLs. Furthermore, the small-signal model of the proposed control method is developed, and the influence of the proposed controller on the small-signal stability is described by employing the eigenvalue analysis method. Finally, based on the RT-Lab hardware-in-the-loop simulation system, comparisons and analysis are made to verify the effectiveness of the proposed control method under power step conditions. [ABSTRACT FROM AUTHOR]