Search

This paper studies the decentralized stochastic optimization problem over an undirected network, where each agent owns its local private functions made up of two non-smooth functions and an expectation-valued function. A decentralized stochastic primal–dual algorithm is proposed, by combining the variance-reduced method and the stochastic approximation method. The local gradients are estimated by using the mean of a variable number of sample gradients and the stochastic error decreases with the number of samples in the stochastic approximation process. The highlight of this paper is the extension of the primal–dual algorithm to the stochastic optimization problems. The effectiveness of the proposed algorithm and the correctness of the theory are verified by numerical experiments. [ABSTRACT FROM AUTHOR]

Label distribution learning represents the relevance of labels to samples using description degree, which can provide richer semantic information, thus finding wider applications. Exploiting label correlations is an effective approach to narrow down the hypothesis space of label distribution learning models. In existing works that utilize low-rank assumptions or label linear dependence to mine correlations, it is assumed that a label can be linearly expressed by other labels. However, this assumption can only be satisfied when there are linear dependency relationships between labels, thus the label correlation obtained by such methods is subject to certain distortion. To address this issue, this paper assumes that labels can be linearly represented by the same set of bases. The correlation between labels is represented by sharing common bases. Specifically, the paper employs matrix factorization to extract bases that can be used to represent all labels. And then designs a label distribution learning algorithm based on the property of sharing the same set of bases of the ground truth label distribution and predict label distribution. The effectiveness of the algorithm is verified through experimental validation. Generally speaking, the algorithm presented in this paper achieves optimal performance at 73.15% of the cases, with the best average ranking. In the two-tailed t -test, the algorithm in this paper exhibits statistical superiority compared to all comparison algorithms. [ABSTRACT FROM AUTHOR]

Object detection is a basic vision task that accompanies people's daily lives all the time. The development of object detection technology has experienced an evolution from traditional-based algorithms to deep learning-based algorithms, which has made a qualitative leap in both detection accuracy and detection speed. With the advancement of deep learning, object detection techniques are increasingly becoming a part of everyday life, with the YOLO series of algorithms being extensively applied in various industries. In this paper, we initially present the frequently utilized datasets and evaluation criteria for object detection. Subsequently, we delve into the evolution of traditional object detection algorithms, highlighting two-stage and one-stage approaches through illustrative examples of classical methods. We also conduct a comprehensive summary and analysis of the detection results obtained by these methods. In addition, we introduce object detection applications in daily life, as well as the importance and some difficulties of these applications. Finally, we analyze and summarize the difficulties and challenges facing the task of object detection, and we look forward to the future development direction of object detection. • This survey is an extended version of our paper in ICIC2023. • We review the development and challenges of object detection. • We present the application of object detection and make prospects for the future. [ABSTRACT FROM AUTHOR]

• The different variants of firefly algorithm are classified and analyzed to summarize the latest research and developments related to nature-inspired computing in the most general sense. • This review has proved that firefly algorithms can be practically applied within every problem domain. Moreover, this review has presented to researchers new technological trends and design challenges they have to cope with, while designing systems using this algorithm. Firefly algorithm (FA) is one of the popular algorithms of Swarm Intelligence domain. The literature has expanded significantly in the past few years. This paper provides a timely review of the FA and its new variants. The different variants of FA are classified and analyzed. The applications and case studies in the rapidly evolving domain are also reviewed and summarized in detail here. The problems to be further solved and future research directions of firefly algorithms will be given at the end of this paper. [ABSTRACT FROM AUTHOR]

The distributed online convex optimization problem with time-varying constraints for multi-agent networks is addressed in this article. The purpose is to optimize a sequence of time-varying global cost functions defined as the accumulated values of local cost functions, also attempt to meet the requirement of a sequence of time-varying coupled constraint functions which denote the sum of local constraint functions. Cost functions and constraint functions are unknown to agents beforehand. It is supposed that each agent in the network communicates with its neighbours through a uniformly strongly connected sequence of time-varying directed communication topologies. This paper proposes the bandit distributed primal-dual mirror descent push-sum (BDPDMDPS) algorithm constructed by bandit primal-dual, mirror descent and push-sum methods. Operational performance of the presented algorithm is measured by expected regret and expected constraint violation, both of which are proved to be sublinear with respect to the total iteration span T in this paper. Finally, a numerical simulation example is shown, which confirms the results for expected regret and expected constraint violation of BDPDMDPS algorithm. [ABSTRACT FROM AUTHOR]

Since most of the rainy scene datasets used for training single image rain removal (SIRR) algorithms are constructed by blending artificial rain streaks with source images, it is difficult for a machine trained with such datasets to understand the patterns of real or realistic rain streaks. So, several studies have been attempted to build a real rainy scene dataset. However, since collecting real rainy scenes itself requires significant costs, the real rainy scene datasets provided by some studies cover only very limited rainy environment(s). This paper presents a new approach to synthesize realistic rainy scenes using GAN, which is a world-first attempt as far as we know. The proposed method builds a representation space to which rain streaks of multiple styles are smoothly mapped by learning the distributions of various rain datasets. The representation space allows control over the generated rain streaks. Also, the proposed method can synthesize multiple rainy scenes per clean (source) scene simultaneously, thereby a synthesized rain image dataset (SyRa) (Dataset can be found here: https://github.com/jaewoong1/SyRa-Synthesized%5fRain%5fdataset) consisting of 11 K clean images and 55 K rainy images was constructed. Finally, this paper provides benchmarking results of several SIRR methods trained with SyRa. This result will be very useful for developing SIRR algorithms that can cope well with the actual rain environment. [ABSTRACT FROM AUTHOR]

Time-variant Yang-Baxter-like matrix equation (YBLME) with the disturbances of noises is the hotspot in various scientific disciplines. The existing research, either can not handle the noise, or rely on the build-in numerical algorithm provided by MATLAB. Therefore, it is necessary to further study the digital-computer discrete solution of this problem. In this paper, the authors propose a noise-handling ten-instant discrete solution for the time-variant YBLME. By defining the matrix-form error function, Zhang neural network (ZNN) is exploited to design the continuous-time noise-handling ZNN model. For potential digital hardware (i.e., digital computer) realization, a discrete-time ZNN-based noise-handling ten-instant (DTZNH10i) algorithm, which is capable of handling three types of noises, is proposed on the basis of a Zhang time discretization (ZTD) formula. The convergence and precision of the proposed DTZNH10i algorithm are investigated and discussed. Theoretical analyses show the correctness and effectiveness of the proposed algorithm. The paper offers three examples of time-variant YBLME with disturbances of constant, linear, and bounded random noises to illustrate the efficacy and convergence of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper is concerned with the problem of dynamic event-triggered bipartite consensus control for nonlinear multi-agent systems based on signed networks. A new dynamic event-triggered control mechanism is proposed, whereby an adjustment variable is introduced to dynamically schedule the triggering frequency, enabling the minimization of the triggering times while ensuring system performance. Based on the designed event-triggered control algorithm, sufficient conditions are derived to guarantee that bipartite consensus can be reached by the considered nonlinear multi-agent system. Furthermore, it is proved that Zeno behavior will not occur. Numerical examples are provided in this paper to verify the effectiveness of the proposed control algorithm. The simulation results reveal that, compared with the static event-triggered mechanism and the traditional dynamic event-triggered mechanism, the proposed event-triggered algorithm can further reduce the triggering times and enhance the flexibility of the event-triggered mechanism. [ABSTRACT FROM AUTHOR]

General use quadcopters have been under development for over a decade but many of their potential applications are still under evaluation and have not yet been adopted in many of the areas that could benefit from their use. While the current generation of quadcopters use a mature set of control algorithms, the next steps, especially as autonomous features are developed, should involve a more complex learning capability to be able to adapt to unknown circumstances in a safe and reliable way. This paper provides baseline quadcopter control models learnt using eight general reinforcement learning (RL) algorithms in a simulated environment, with the object of establishing a reference performance, both in terms of precision and generation cost, for a simple set of trajectories. Each algorithm uses a tailored set of hyperparameters while, additionally, the influence of random seeds is also studied. While not all algorithms converge in the allocated computing budget, the more complex ones are able to provide stable and precise control models. This paper recommends the use of the TD3 algorithm as a reference for comparison with new RL algorithms. Additional guidance for future work is provided based on the weaknesses identified in the learning process, especially regarding the strong dependence of agent performance on random seeds. • Quadcopter control models learnt using model-free reinforcement learning algorithms. • Trained and tested in a simulated environment using OpenAI gym and pybullet. • Trained using small displacements, tested on trajectories unknown to the agent. • TD3 algorithm shows the most consistent performance. • All algorithms show strong dependence on the random seed selection. [ABSTRACT FROM AUTHOR]

This paper investigates fully distributed scaled non-negative edge-consensus problems of networked systems with actuator saturation and unmeasurable internal states. By using the adaptive control method, output-feedback-based low-gain technique, and graph theory, a new adaptive algorithm is designed to obtain scaled edge-consensus conditions, under which the difficulties caused by the constraints on edge states and controllers are overcome. There are three interesting characteristics that any global information of networks is not used in this paper's algorithm and result, including the number of vertexes and edges; the feasible solutions of the scaled edge-consensus conditions exist and can be easily obtained; the convergence rate of the controller is adjustable. Furthermore, the designed algorithm is expanded in the cases without actuator saturation. Finally, three examples are given to verify the theoretical results. [ABSTRACT FROM AUTHOR]

The process of aligning one image, in the coordinate system of another is called registration. Image registration is vital in the medical domain and is used for diagnosis, therapy planning, and treatment of diseases. Due to its huge applicability and importance, medical image registration has emerged to be a separate domain of research. Beginning from the invasive landmark based registration, innumerable algorithms have been proposed to register two images of the human physiology. However, a breakthrough in the literature occurred when an information theory based measure, mutual information was used to register two images. Since then a large number of new algorithms have developed, which use mutual information for fully automatic registration of medical images. This paper is a survey of these algorithms. Beginning from its development, it discusses about some of the major works done on mutual information based image registration. Some comparative studies with other algorithms have also been discussed. The paper ends with a discussion of the developments in medical image registration algorithms post mutual information, which primarily include deep neural network (DNN) based algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a control framework for intelligent surgical robots under the Remote Center of Motion (RCM). The goal of a surgical robot is to assist surgeons in performing complex surgeries. RCM constraint implies that the surgical tip attached to the end-effector of the surgical robot does not slide away from the point of the incision while performing surgery. Implementation of a control algorithm to comply with RCM constraints is a complicated task because of the nonlinear model of the surgical robots and stringent conditions of accuracy imposed by the patient's safety. This paper proposes an optimization-driven approach to perform the surgical maneuver under RCM constraints. We then applied a bio-inspired optimization algorithm to solve the problem efficiently. For testing the performance of ZNNBAS, we used MATLAB to simulate a surgical procedure. A 7-DOF surgical robot (KUKA LBR IIWA 7) was used as a test bench for running the simulations. The simulation results show that the ZNNBAS is comparable with BAS, PSO, and GA and efficiently and robustly performed the task commanded maneuvers while enforcing the RCM constraints. [ABSTRACT FROM AUTHOR]

Dynamic networks are popularly used to describe networks that change with time. Although there have been a large number of research works on understanding dynamic networks using link prediction, node classification and community detection, there is rare work that is specially designed to address the challenge of big network size of dynamic networks. To this end, we study in this paper an emerging and challenging problem of network coarsening in dynamic networks. Network coarsening refers to a class of network "zoom-out" operations where node pairs and edges are grouped together for efficient analysis on big networks. However, existing network coarsening approaches can only handle static networks where network structure weights have been predefined before the coarsening calculation. Under the observation that big networks are highly dynamic and naturally change over time, we consider in this paper to embed information diffusion data which reflect the dynamics of networks for network coarsening. Specifically, we present a new Semi-NetCoarsen approach that jointly maximizes the likelihood of observing the information diffusion data and minimizes the network regularization with respect to the predefined network structural data. The learning function is convex and we use the accelerated proximal gradient algorithm to obtain the global optimal solution. We conduct experiments on two synthetic and five real-world data sets to validate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

• The paper provides a robust regression method for interval-valued variables. • The objective function of the method considers the full interval information. • The computation of the sum of squares errors uses exponential-type kernel functions. • Outliers have a small weight for both center and radius parameter estimates. • Applications on synthetic and real data sets corroborate the proposed method. Interval-valued data are needed to manage either the uncertainty related to measurements, or the variability inherent to the description of complex objects representing group of individuals. A number of regression methods suitable to interval variables describing variability of complex objects are already available. However, less attention has been given to methods that, simultaneously, take into account the full interval information and are resistant to interval outlier observations, even with the frequent presence of atypical observations on interval-valued data sets. This paper proposes a new robust linear regression method for interval variables, where the presence of outliers either in the center or in the radius penalize both the center and the radius regression models. Moreover, the interval observations with outliers on both center and radius are more penalized than those observations with outliers only in the center (or in the radius). Besides, this paper provides a suitable iterative algorithm to estimate the parameters of the proposed method. The algorithm estimates the parameters of the center (or of the radius) model taking into account both information of the center and the radius. The convergence and time complexity of the iterative algorithm are also presented. Finally, the performance of the new method is compared with some previous robust regression approaches and evaluated on synthetic and real interval-valued data sets. [ABSTRACT FROM AUTHOR]

This paper investigates the development of an adaptive cooperative control scheme for the consensus of uncertain nonlinear multi-agent systems subjected to uncertain time-varying control direction, disturbances, and dead-zone nonlinearity. The dead-zone nonlinearity is described by an uncertain nonlinear function of the control input which can represent a wide class of practical input nonlinearities. It is assumed that no prior knowledge about the uncertain nonlinearities of agents, disturbances, dead-zone parameters, magnitude and sign of the control gain is available. In this paper, a Nussbaum function is used to deal with the unknown time-varying control directions problem and a disturbance-like term in the dead-zone description is approximated by an adaptive TSK-type fuzzy system. Then, by using the dynamic surface control approach and radial-basis function neural network, an adaptive distributed controller is designed for each follower agent. Stability analysis shows that all signals of the closed-loop multi-agent system are semi-globally uniformly ultimately bounded and the consensus error can be made arbitrary small by the proper selection of design parameters. Simulation and comparison results demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

• An analysis of lexicographic optimization for feature selection and data classification. • Cooperative co-evolution for feature selection while the classifier hyperparameters are also being optimized. • Optimization of multiple objectives using a simple evolutionary algorithm. • A new lexicographic ranking methodology to compare the results of different feature selection methods. • Quite good results for real high-dimensional datasets. This paper starts with two hypotheses. The first one is that the simultaneous optimization of the hyperparameters regulating the classifier within a wrapper method, while the best subset of features is being determined, should improve the results with respect to those obtained with a pre-parameterized classifier. The second one is that solving these two problems can be formulated as a lexicographic optimization problem, allowing the use of a simple single-objective evolutionary algorithm to solve this multi-objective problem. The fitness function is of key importance for such wrapper methods. It is responsible for guiding the search towards potentially good solutions and it also consumes most of the runtime. Having these issues in mind, this paper also proposes a new lexicographic fitness function, designed to minimize the runtime of the algorithm and also to avoid over-fitting. Furthermore, the execution time and the quality of the results obtained by the wrapper procedure also depend on some algorithmic hyperparameters: the similarity thresholds used when comparing two different solutions lexicographically and the percentage of data samples used for validation during the training process. Thus, an experimental analysis has been carried out to find adequate values for these hyperparameters. Finally, the lexicographic cooperative co-evolutionary wrapper approach, using the new fitness function proposed in this paper, has been tested with several datasets belonging to the University of California, Irvine (UCI) repository and also with some real high-dimensional datasets, obtaining quite good results, compared to other state-of-the-art wrapper methods. The comparison has also been made lexicographically, with a new methodology proposed in this paper. [ABSTRACT FROM AUTHOR]

Object detection is one of the most important tasks involved in intelligent agriculture systems, especially in pest detection. This paper focuses on a most devastated agricultural disaster: grasshopper plagues. Grasshopper detection and monitoring is of paramount importance in preventing grasshopper plagues. This paper proposes a probabilistic faster R-CNN algorithm with stochastic region proposing, where a probabilistic region proposal network, an image classification network, and an object detection network are integrated to detect and locate grasshoppers. More specifically, in the proposed framework, the probabilistic region proposal network considers attributes (e.g. size, shape) of region proposals and the image classification network identifies the existence of grasshoppers while the object detection network scores recognition confidence for a region proposal. By integrating these three networks, the uncertainty can be passed from end to end, and the final confidence is obtained for each region proposal can be explicitly quantified. To enhance algorithm robustness, a stochastic region proposing algorithm is developed to screen region proposals rather than using a predetermined threshold. The proposed algorithm is validated by recently collected grasshopper datasets. The experimental results demonstrate that the proposed algorithm not only outperforms competing algorithms in terms of average precision (0.91), average missed rate (0.36), and maximum F 1 -score (0.9263), but also reduces the false positive rate of recognising the existence of grasshoppers in an open field. [ABSTRACT FROM AUTHOR]

Person re-identification is to recognize a pedestrian who has been observed at different places in monitoring system, which is done by computer automatically. Important practical significance can be found in this paper on improving the intelligence of monitoring system. There are two challenging problems needed to be solved for person re-identification, which is feature representation and matching. Designing a suitable feature representation method is both challenging and crucial. Ideally, the extracted features should be robust enough to cope with the various situations of the monitoring environment, such as posture difference, illumination changing, and shooting angle difference, etc. There are a lot of challenges for feature matching too, such as small sample size, inter-class confusion, and intra-class variation, etc. In order to meet these challenges, a new person re-identification scheme was put forward in this paper. The following three aspects would be used to describe it. First, an improved BOF feature extraction algorithm based on SURF was put forwarded, SURF algorithm extracts the preliminary feature descriptor and generates visual dictionary, so the influence factors such as illumination and scale invariants can be deal with. And then, covariance descriptor was adopted by the algorithm. It has high robustness, and matching accuracy can be improved too for the case of small sample. Finally, an effective classifier was designed by LIBSVM based on improved BOF algorithm, so the efficiency of the person re-identification algorithm can be improved. The proposed method was compared with the current mainstream algorithm through experiment, and it can be found through the experimental results that it is effective to solve the difficult problems for person re-identification. [ABSTRACT FROM AUTHOR]

Single-object tracking is regarded as a challenging task in computer vision, especially in complex spatio-temporal contexts. The changes in the environment and object deformation make it difficult to track. In the last 10 years, the application of correlation filters and deep learning enhances the performance of trackers to a large extent. This paper summarizes single-object tracking algorithms based on correlation filters and deep learning. Firstly, we explain the definition of single-object tracking and analyze the components of general object tracking algorithms. Secondly, the single-object tracking algorithms proposed in the past decade are summarized according to different categories. Finally, this paper summarizes the achievements and problems of existing algorithms by analyzing experimental results and discusses the development trends. [ABSTRACT FROM AUTHOR]

This paper considers the leader-following consensus problem for delayed neural networks with multi-layer signed digraph topologies. Both structurally balanced and unbalanced topologies are considered. By using the structural balance theory and the pinning control strategy, some sufficient conditions are given to guarantee that the bipartite leader-following consensus can be reached in structurally balanced multi-layer signed neural networks, which depend on the node dynamics and the topology of the multi-layer signed network. In addition, a scheme is designed for selecting the pinning nodes and gains of each layer to achieve bipartite leader-following consensus. When the multi-layer signed network is structurally unbalanced, the asymptotic stability of the neural network is investigated by decomposing the structurally unbalanced network into a structurally balanced subgraph and some special edges. The conditions proposed in this paper are also suitable for addressing the consensus problem of traditional single layer signed neural networks. Numerical examples are given to illustrate the correctness and effectiveness of the proposed theorems and algorithms. [ABSTRACT FROM AUTHOR]

Multi-view clustering has gained soar attention in the field of data mining in recent years. Most multi-view clustering methods are considered to be complete for each view. However, in many applications, some views may contain missing instances, resulting in the incomplete multi-view learning problem. Incomplete views cannot be directly dealt with traditional multi-view clustering methods. In this paper, we propose a One-step multi-view subspace clustering with incomplete views (OMVSC-IV) method based on low-rank matrix factorization to overcome this problem. Specifically, the proposed algorithm uses low-rank matrix factorization to learn a consensus representation matrix, and then combined with the objective function of non-negative embedding and spectral embedding subspace clustering proposed in this paper. The whole process is established into the same objective function for joint optimization and requires no post-processing (e.g., K -means), thus avoiding the defect of being sensitive to initial values. Furthermore, the accuracy, parameter, sensitivity and convergence of the algorithm are studied by experiments. Experimental results on nine data sets show that the proposed algorithm performs superior to some of the latest algorithms. [ABSTRACT FROM AUTHOR]

Graph Neural Networks(GNNs) are powerful methods to analyze the non-Euclidean data. As a dominant type of GNN, Graph Convolutional Networks(GCNs) have wide applications. However, the analysis of the generalization error for GCNs with multilayer is limited. Based on the review of single-layer GCNs, this paper analyzes the generalization error of two-layers GCNs and extends the conclusion to the general GCNs models. Firstly, this paper examines two-layers GCNs and obtains the stability of the GCNs algorithm. And then, based on this algorithmic stability, the generalization stability of multilayer GCNs is obtained. This paper shows that the algorithmic stability of GCNs depends upon the graph filters and its product with node features as well as the training procedure. Furthermore, the generalization error gap of GCNs tends to be enlarged with more layers, which can interpret why GCNs with deeper layers have relatively poorer performance in test datasets. [ABSTRACT FROM AUTHOR]

Analyzing the runtime behaviors of Android apps is crucial for malware detection. In this paper, we attempt to learn the behavior level features of an app from function calls. The challenges of this task are twofold. First, the absence of function attributes hinders the understanding of app behaviors. Second, the graphical representation of function calls cannot be directly processed by classical machine learning algorithms. In this paper, we develop two methods to overcome these challenges. Based on function embedding, we first propose the concept of enhanced function call graphs (E-FCGs) to characterize app runtime behaviors. We then develop a Graph Convolutional Network (GCN) based algorithm to obtain vector representations of E-FCGs. Extensive experiments show that the features learned by our method can achieve surprisingly high detection performance on a variety of classifiers (e.g., LR, DT, SVM, KNN, RF, MLP and CNN), significantly outperforming the traditional static features. [ABSTRACT FROM AUTHOR]

Low rank tensor recovery (LRTR) problem has attracted wide attentions and researches, and has been applied to various fields. In this paper, we mainly consider the nonconvex relaxtion methods for LRTR. Firstly, we newly propose the tensor schatten capped p ( SC p ) norm as a nonconvex surrogate of the tensor tubal rank, which can provide a closer approximation of the tubal rank compared with some existing nonconvex approximations. Secondly, we introduce an implicit Plug-and-Play (PnP)-based regularization into the nonconvex model to further improve the recovered performance. The proposed model is abbreviated as SC p -PnP. Based on the alternating direction method of multipliers, we propose an efficient algorithm to solve SC p -PnP. The convergence of this algorithm is also provided. Finally, extensive experiments on different kinds of datasets show that our method significantly outperforms several state-of-the-art LRTR methods in terms of both quality metrics and visual effects. [ABSTRACT FROM AUTHOR]

As a classical machine learning model, support vector machine (SVM) has attracted much attention due to its rigorous theoretical foundation and powerful discriminative performance. The doubly regularized SVM (DRSVM) is an important variant of SVM based on elastic-net regularization, which considers both the sparsity and stability of the model. To tackle the problems of explosive increases in data dimensions and data volume, the alternating direction method of multipliers (ADMM) algorithm can be used to train the DRSVM model. ADMM is an effective iterative algorithm for solving convex optimization problems by decomposing a large issue into a series of solvable subproblems, which is also well suited for distributed computing. However, lack of guaranteed convergence and slow convergence rate are two critical limitations of ADMM. In this paper, a 3-block ADMM algorithm based on the over-relaxation technique is proposed to accelerate DRSVM training, namely, the over-relaxed DRSVM (O-RDRSVM). The main strategy of the over-relaxation technique is to further append the information from the previous iteration to the next iteration to improve the convergence of ADMM. We also propose a distributed version of O-RDRSVM to handle parallel and distributed computing faster, termed DO-RDRSVM. Moreover, we develop a fast O-RDRSVM algorithm (FO-RDRSVM) and a fast DO-RDRSVM algorithm (FDO-RDRSVM), which further reduce the computational cost of O-RDRSVM and DO-RDRSVM by employing the matrix inversion lemma. The convergence analyses ensure the effectiveness of our algorithms for DRSVM training. Finally, extensive experiments on public datasets demonstrate the advantages of our algorithms in terms of convergence rate and training time while maintaining accuracy and sparsity comparable to those of previous works. [ABSTRACT FROM AUTHOR]

Abstract: This paper studies the problem of expertise matching with various constraints. Expertise matching, which aims to find the alignment between experts and queries, is a common problem in many applications such as conference paper–reviewer assignment, product–reviewer alignment, and product-endorser matching. Most existing methods formalize this problem as an information-retrieval problem and focus on finding a set of experts for each query independently. However, in real-world systems, various constraints are often needed to be considered. For example, in order to review a paper, it is desirable that there is at least one senior reviewer to guide the reviewing process. An important question is: “Can we design a framework to efficiently find the optimal solution for expertise matching under various constraints?” This paper explores such an approach by formulating the expertise matching problem in a constraint-based optimization framework. In the proposed framework, the problem of expertise matching is linked to a convex cost flow problem, which guarantees an optimal solution under various constraints. We also present an online matching algorithm to support incorporating user feedbacks in real time. The proposed approach has been evaluated on two different genres of expertise matching problems, namely conference paper–reviewer assignment and teacher–course assignment. Experimental results validate the effectiveness of the proposed approach. Based on the proposed method, we have also developed an online system for paper–reviewer suggestions, which has been used for paper–reviewer assignment in a top conference and feedbacks from the conference organizers are very positive. [Copyright &y& Elsevier]

The prediction of short term power load owns a great influence on performance of the whole electric system. Raising the result of power load forecasting is always a research spot. This paper proposes a method combined Elman neural network (ENN) and the particle swarm optimization (PSO) for the short-term power load forecasting. Firstly, this paper introduces the principle of ENN and PSO algorithm respectively and analyzes performance of network influenced by parameters of ENN. Then the particle swarm optimization algorithm is applied to searching the optimal learning rate of ENN. To study the capability of the method proposed in this paper, the method is utilized for the short-term power load forecasting, which is suitable to be solved by ENN. Besides, a comparison experiment on this method (PSO–ENN) with general regression neural network (GRNN), the original ENN and the traditional back-propagation neural network (BPNN) is given out to illustrate effectiveness of PSO–ENN. [ABSTRACT FROM AUTHOR]

In this paper, a novel control scheme is developed to solve an optimal containment control problem of unknown continuous-time multi-agent systems. Different from traditional adaptive dynamic programming (ADP) algorithms, this paper proposes an internal reinforcement ADP algorithm (IR-ADP), in which the internal reinforcement signals are added in order to facilitate the learning process. Then a distributed containment control law is designed for each agent with the internal reinforcement signal. The convergence of this IR-ADP algorithm and the stability of the closed-loop multi-agent system are analyzed theoretically. For the implementation of the optimal controllers, three neural networks (NNs), namely internal reinforcement NNs, critic NNs and actor NNs, are utilized to approximate the internal reinforcement signals, the performance indices and optimal control laws, respectively. Finally, some simulation results are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model. [ABSTRACT FROM AUTHOR]

This paper investigates the fully complex mini-batch gradient algorithm for training complex-valued neural networks. Mini-batch gradient method has been widely used in neural network training, however, its convergence analysis is usually restricted to real-valued neural networks and of probability nature. By introducing a new Taylor mean value theorem for analytic functions, in this paper we establish deterministic convergence results for the fully complex mini-batch gradient algorithm under mild conditions. The deterministic convergence here means that the algorithm will deterministically converge, and both the weak convergence and strong convergence will be proved. Benefited from the newly introduced mean value theorem, our results are of global nature in that they are valid for arbitrarily given initial values of the weights. The theoretical findings are validated with a simulation example. [ABSTRACT FROM AUTHOR]

Matrix completion is extensively studied due to its wide applications in science and technology. In this paper, we concentrate our study on the matrix completion problem for image analysis tasks due to their immense importance and pervasive use in many fields. A rich collection of models has been proposed to capture both linear and nonlinear relationships latent in a matrix. Even though nonlinear models possess more powerful matrix completion capabilities than their linear counterparts, these models generally carry higher model complexity and tuning difficulties. To take advantage of the superior discriminative power offered by nonlinear models while curbing its deployment overheads, this paper proposes a novel nonlinear matrix completion model utilizing a deep learning-based approach. In contrast to existing nonlinear models, the new model carefully explores and exploits spatial locality among adjacent matrix elements exhibited in patches of various sizes and locations in a target matrix. Building upon this idea, a new patch-based nonlinear matrix completion algorithm is designed. The algorithm leverages a convolutional neural network to learn the predictive relationship between a matrix element and its surrounding elements through an end-to-end trainable fashion, leading to a capable and easy-to-deploy nonlinear matrix completion solution. To identify an optimal patch size suited for tackling a given matrix completion task without exhaustively enumerating all candidate patch sizes, the new algorithm is coupled with a fast stochastic search procedure, yielding a good trade-off between computational efficiency and accuracy. Extensive experiments are conducted to validate the effectiveness and advantages of the proposed algorithm for nonlinear matrix completion problem in comparison with a series of state-of-the-art algorithms. Experimental results consistently demonstrate the superiority of the new algorithm in completing images with a variety of random and textual noises. [ABSTRACT FROM AUTHOR]

In this paper, we study an important recommendation problem of exploiting users' one-class positive feedback such as "likes", which is usually termed as one-class collaborative filtering (OCCF). For modeling users' preferences beneath the observed one-class positive feedback, the similarity between two users is a key concept of constructing a neighborhood structure with like-minded users. With a well-constructed neighborhood, we can make a prediction of a user's preference to an un-interacted item by aggregating his or her neighboring users' tastes. However, the neighborhood constructed by a typical traditional method is usually asymmetric, meaning that a certain user may belong to the neighborhood of another user but the inverse is not necessarily true. Such an asymmetric structure may result in a less strong neighborhood, which is our major finding in this paper. As a response, we exploit the reciprocal neighborhood among users in order to construct a better neighborhood structure with more high-value users, which is expected to be less influenced by the active users. We then design a corresponding recommendation algorithm called k -reciprocal nearest neighbors algorithm (k -RNN). Extensive empirical studies on two large and public datasets show that our k -RNN performs significantly better than a closely related algorithm with the traditional asymmetric neighborhood and some competitive model-based recommendation methods. [ABSTRACT FROM AUTHOR]

In this paper, we investigate quantized synchronization control problem of memristive neural networks (MNNs) with time-varying delays via super-twisting algorithm. A feedback controller is introduced with quantized method. To enormously reduce the computational complexity of the controller under super-twisting algorithm, two quantized control schemes are proposed with uniform quantizer and logarithmic quantization. We obtain some sufficient conditions of specific control plans to guarantee that the driving MNNs can synchronize with the response MNNs. A neoteric Lyapunov functional is designed to analyze the synchronization problem. Finally, in this paper ending, some illustrative examples are given in support of our results. [ABSTRACT FROM AUTHOR]

• We propose a novel matrix inversion free algorithm for solving the Bayesian linear regression problem with Gaussian priors. • Compared with the conventional gradient based and EM algorithms, our proposed one runs significantly faster while achieving the similar precision performance. • An iterative method from a perspective of latent matrices is proposed for optimal search without breaking the symmetric positive definite manifold constraint. The Bayesian linear regression is a useful tool for many scientific communities. This paper presents a novel algorithm for solving the Bayesian linear regression problem with Gaussian priors, which shares the same spirit as the gradient based methods. In addition, the standard scheme for this task, the Expectation Maximization (EM) algorithm, involves matrix inversions but our proposed algorithm is free of. Numerical experiments demonstrate that the proposed algorithm performs as well as the gradient based and EM algorithms in term of precision, but runs significantly faster than the gradient based and EM algorithms. Due to its matrix-inversion-free nature, the algorithm of this paper is a viable alternative to the competing methods available in the literature. [ABSTRACT FROM AUTHOR]

• Proposed the infimal convolution smoothing technique to approximate the non-differentiable loss function. • Introduced a relaxation factor to transform the non-differentiable loss function into a smooth counterpart. • Provided convergence analysis for the algorithm under the APG and mAPG framework. • Evaluated the effectiveness of the proposed algorithm via numerical experiments. This paper addresses the robust sparse recovery problem in the presence of impulsive measurement noise. In order to overcome the poor performance of ℓ 2 -norm loss function with the outliers under the impulsive noise, we employ the ℓ 1 -norm as the loss function for the residual error, which is less sensitive to outliers in the measurements than the popular ℓ 2 -loss. To rise to the challenges introduced by the non-smooth problem, we first employ two smoothing strategies to approximate the ℓ 1 -norm loss function: one introduces a relaxation factor in the ℓ 1 -norm and the other uses the infimal convolution smoothing technique to transform it into a smooth counterpart. Both of them can approximate the ℓ 1 -norm with arbitrary degree of accuracy and provide a Lipschitz continuous gradient loss function. Then, we employ the accelerated proximal gradient (APG) and monotone APG (mAPG) frameworks for the convex and non-convex regularization functions, respectively. The convergence performance is discussed for generalized regularization penalty. The simulation result demonstrates our conclusions and indicates that the algorithm proposed in this paper can improve the reconstruction quality. [ABSTRACT FROM AUTHOR]

In numerous domains, there is ample evidence indicating that a significant portion of real-world data exhibits temporal variations, such as medical research and meteorological studies. Particularly in the era of big data, not only does the size of data change dynamically but also its dimensions at an unprecedented pace. Consequently, employing traditional methods to handle such dynamic data becomes highly impractical. To address this limitation, this paper proposes an incremental feature selection algorithm tailored for dynamic feature variations. For scenarios involving an increase in features, the novel algorithm efficiently identifies a target subset with effective features. In order to showcase the efficacy of the proposed algorithm, this paper conduct experiments using four commonly used classifiers and five UCI data sets. The experimental results further validate both the feasibility and efficiency of the new approach. [ABSTRACT FROM AUTHOR]

With the enhancement of people's security awareness, transmitting secret information securely has gradually become a demand for the public. Steganography is a technology of representing secret information within another carrier, aiming at transmitting secret information without causing suspicion. Most of the traditional steganographic algorithms hide secret information by modifying the statistical characteristics, which will leave traces to the carriers. Although these modifications are too tiny to be distinguished by human eyes, they can be detected by steganalysis algorithms. Differently, coverless steganography, also written as steganography without embedding, accomplish the process of information hiding by constructing the relationship between secret information and carriers. Due to no modification to the carriers, all of the steganalysis algorithms are expired. In this paper, more than 90 papers are included to provide a review in coverless steganographic algorithms, covering the major development process of coverless image and video steganographic algorithms. The main contribution of the existing methods is summarized. Besides, the current general issues of capacity, robustness, and security are discussed adequately for both image and video algorithms. Especially, the security of coverless steganography is discussed for the first time from theoretical analysis to actual investigation in this review. [ABSTRACT FROM AUTHOR]

• Teaching-learning-based optimization (TLBO) is one of population-based heuristic stochastic swarm intelligent algorithm. • In this paper, a comprehensive survey on the recent advances in TLBO is presented. • Literature survey reveals some interesting challenges and future research directions. Teaching-learning-based optimization (TLBO) algorithm which imitates the teaching–learning process in a classroom, is one of population-based heuristic stochastic swarm intelligent algorithms. TLBO executes through similar iterative evolution processes as utilized by a standard evolutionary algorithm. Unlike traditional evolutionary algorithms and swarm intelligent algorithms, the iterative computation process of teaching–learning-based optimization is divided into two phases and each phase executes iterative learning operation. In this paper, we present a comprehensive survey on the recent advances in TLBO. A review of the current literature reveals intriguing challenges and suggests potential future research directions. [ABSTRACT FROM AUTHOR]

Recently, few studies have been made on the stereophonic acoustic echo cancellation (SAEC) with nonlinear systems. To identify such nonlinear model, the functional link artificial neural network (FLANN) and the widely linear model can provide an approach to explore the SAEC with complex random variable. In this paper, a class of augmented complex-value functional link network (ACFLN) adaptive algorithms is developed. Based on the augmented complex-value functional least-mean-square (ACFLMS) algorithm, we have proposed the recursive augmented complex-value functional least-mean-square (RACFLMS) algorithm designed by a recursive structure. To further reduce its computational complexity and enhance its performance, a novel inverse square root function is employed in its structure of the RACFLMS algorithm. The results of several experiments demonstrate that our approach can effectively model the nonlinear systems and verify the improvement of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Spectral clustering is one of the most important clustering approaches, often yielding performance superior to other clustering approaches. However, it is not scalable to large data sets in its original form due to the computational burden of the required large-matrix eigen-decomposition. In this paper, a two-step spectral clustering algorithm is introduced by extending recent advances of scalable spectral clustering based on low-rank affinity matrix using landmarks. In the first step, a scalable spectral clustering algorithm using raw landmark-based affinity matrix is adopted. In the second step, a novel low-rank affinity matrix is learnt via the probability density estimators, constructed from the estimated clusters as derived from the first step. Since the prior information on cluster labels can be utilised in the second step, this learnt affinity matrix reflects intrinsic pairwise data relationships much better. While the proposed more complicated algorithm results in a higher computational cost than the previous landmark-based spectral research, it can be shown that the associated computational cost still scales well with data size. It is demonstrated that the proposed algorithm is capable of achieving far superior performance than other state-of-the-art algorithms for several benchmark multi-class image data sets. [ABSTRACT FROM AUTHOR]

Almost all systems are inevitably subject to various uncertainties or disturbances from the external environment in practical applications. Taking these factors into consideration, in this paper a distributed algorithm with state noise and gradient disturbance is proposed for solving distributed optimization problem with closed convex set constraint based on multi-agent system under weight-balanced graph. Moreover, based on the gradient tracking and projection methods, the proposed distributed algorithm with gradient tracking can improve the convergence rate by introducing a projection error term and an auxiliary parameter. In contrast to some existing constrained distributed gradient algorithms, the proposed one can make the convergence faster and enhance the performance of convergence. The proposed algorithm is illustrated with two simulation examples to show its effectiveness and robustness. [ABSTRACT FROM AUTHOR]

The proliferation of new energy solutions and the enhanced accessibility of distributed power sources have significantly increased the complexity and variability of microgrid structures. Due to inherent limitations in its operational mode, the traditional centralized optimization method falls short in effectively addressing the economic dispatch problem in contemporary microgrids. In this paper, a distributed optimization method is devised to address the economic dispatch problem of microgrids under directed graphs by leveraging the consensus algorithm of multi-agent systems. We define the incremental cost of each microgrid unit as the consensus variable, achieving convergence through a pioneering combination of event-triggered strategy and predefined-time control theory. This approach not only optimizes resource use but also ensures timely and efficient solution convergence, addressing critical gaps in existing methodologies. This approach enables control over the upper bound of convergence time for optimal solutions by directly adjusting time parameters in the controller under the directed graph. Consequently, it achieves coordinated control of the power output in microgrids within a predefined time while reducing the communication resources between nodes with event-triggered mechanism. The effectiveness of the proposed algorithm is verified through simulation and analysis. • The microgrid model includes flexible load, renewable energy, and power loss for greater realism. • The system's convergence time upper bound can be visualized to achieve coordinated microgrid power control. • A new event-triggered condition for directed graphs prevents continuous agent communication, saving resources. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have achieved considerable success in a variety of tasks, and this success has led to an increase in the importance of the security and robustness of algorithms where DNNs are applied. In fact, previous studies have identified that neural networks are vulnerable to adversarial examples that are generated by adding a small amount of noise to the input images. Detection-based methods that can detect adversarial examples among input images are a popular defense technique against adversarial examples. However, these methods reject the detected adversarial images, making it difficult to use the input image for further analysis. In this study, we propose a novel denoising-based detection method that simultaneously denoises and detects an input image when defending against adversarial examples. Our method primarily analyzes images in the feature maps of the target classifier layers based on the consistency between the Fourier domains. We first generate adversarial examples and train the denoising network by minimizing the similarity between the non-adversarial and denoised adversarial images in the feature maps of the Fourier-transformed layers. The predicted denoised images are then input to the adversarial example detector, which determines whether the images are adversarial by exploring the characteristics of the concatenated input and denoised images. There are three main contributions in this paper: (1) We propose a novel denoising-based detection method that simultaneously denoises and detects an input image when defending against adversarial examples. (2) We improve the denoising method for adversarial examples that reconstructs adversarial examples based on the Fourier-transformed feature maps. (3) We improve the detection method by using denoised images in addition to the input images. We tested our proposed method against the fast gradient sign method, basic iterative method, projected gradient descent, Deepfool, and Carlini and Wagner adversarial attack algorithms on two Canadian Institute for Advanced Research (CIFAR) datasets, i.e., CIFAR-10 and CIFAR-100. Our method, which employed a frequency-based denoising mechanism in combination with a detection mechanism, demonstrated significant accuracy improvements in the denoising and detection performances when compared to other state-of-the-art methods. • We propose a method that simultaneously denoises and detects adversarial images. • We enhance denoising by using Fourier-transformed feature maps to reconstruct images. • We improve detection by using both denoised and original input images. [ABSTRACT FROM AUTHOR]

The distributed nature of Federated Learning (FL) introduces security vulnerabilities and issues related to the heterogeneous distribution of data. Traditional FL aggregation algorithms often mitigate security risks by excluding outliers, which compromises the diversity of shared information. In this paper, we introduce a novel filtering-and-voting framework that adeptly navigates the challenges posed by non-iid training data and malicious attacks on FL. The proposed framework integrates a filtering layer for defensive measures against the intrusion of malicious models and a voting layer to harness valuable contributions from diverse participants. Moreover, by employing Deep Reinforcement Learning (DRL) for dynamic aggregation weight adjustment, we ensure the optimized aggregation of participant data, enhancing the diversity of information used for aggregation and improving the performance of the global model. Experimental results demonstrate that the proposed framework presents superior accuracy over traditional and contemporary FL aggregation methods as diverse models are utilized. It also shows robust resistance against malicious poisoning attacks. • A novel filtering-and-voting framework for secure and optimized performance in FL. • Analytical evaluation with a convergence bound confirms the framework's convergence. • DRL-based weight selection enhances learning from unique knowledge in non-iid data. [ABSTRACT FROM AUTHOR]

In the real world, the sources of text often transcend the boundaries of generative and natural domains, which introduces challenges for existing linguistic steganalysis methods. The typical problem arises from the sample selection bias caused by training solely on a single-source domain, rendering the model incapable of inferencing across the entire generative-natural (GN) space. Moreover, there exists the problem of overlooking the sensitive discrepancies between generative text and natural text, which hampers model fitting. In this paper, we model steganalysis in a brand-new perspective by employing multi-task learning to build the main task and auxiliary tasks in the cross GN domain. The proposed Cross Generative-Natural Domain Multi-task Model (CG-NDMM) can concurrently address the two aforementioned issues through i) modeling steganalysis across the entire GN space, incorporating two auxiliary tasks alongside a main task, and ii) utilizing a feature representation transfer learning strategy to harmonize two sub-networks. Furthermore, we employ diverse steganography algorithms to construct the datasets, which comprise four types of texts (generative-cover, generative-steganographic, natural-cover, and natural-steganographic) derived from two public datasets, Movie and Twitter. The experiments on these datasets demonstrate the effectiveness of the proposed approach, showcasing its substantially superior performance over the comparative baseline methods. [Display omitted] • A cross generative-natural domain multi-task model is proposed for steganalysis. • Transfer learning captures features distinguishing generative text from natural ones. • Multi-task learning reduces sample bias, boosts cross-domain steganalysis performance. [ABSTRACT FROM AUTHOR]

Outlier detection is one of the core problems in the field of data mining. Graph-based approaches are widely acknowledged for their robust performance in outlier detection, yet constructing a comprehensive graph to represent the original data remains challenging. Some methods rely solely on the global distribution of the data, leading to low detection accuracy; in addition, when incorporating the local information of the data, the problem of dangling links may arise. To improve the graph construction process, this paper proposes an outlier detection algorithm based on a hybrid graph (HGOD). First, the neighbors of each object are obtained in an adaptive manner, and a neighborhood graph is created. Subsequently, a global connectivity graph is constructed using a minimum spanning tree. Then, these two graphs are merged into a hybrid graph, and Markov random walks are conducted on it. Finally, outliers are identified based on the converged stationary distribution. The performance of HGOD is evaluated on both real-world and synthetic datasets. The precision and AUC of HGOD algorithm surpasses that of the other seven algorithms. Ablation and analysis experiments further demonstrate that the HGOD algorithm is effective and has outstanding performance in outlier detection. [ABSTRACT FROM AUTHOR]

The integration of Spiking Neural Networks (Maass, 1997) and Transformers (Vaswani et al., 2017) has significantly enhanced performance in the field, achieving substantial improvements while ensuring energy efficiency. This amalgamation bears significant exploratory significance. This paper aims to enhance the network's capacity for extracting temporal information from neuromorphic datasets. By leveraging the Spikformer (Zhou et al., 2023b) architecture, we introduce a novel network named TE-Spikformer. Through thorough analysis, we identified an imbalance in the Average Firing Rates(AFR) of neurons in the layer preceding the classification head across temporal steps. We thoroughly investigate the root cause of this issue, attributing it to the limitations of the network's use of Batch Normalization (BN) (Ioffe and Szegedy, 2015) layer. To address these challenges, we propose a Batch Group Normalization (BGN) layer. While maintaining the stability of temporal characteristics in the data, we also introduce the Spike Spatio-Temporal Attention(SSTA) module to enhance the network's ability to capture temporal information. To validate the effectiveness of our approach, we conducted multiple experiments using neuromorphic datasets, including DVS-CIFAR10, DVS128 Gesture, and N-Caltech101. The experimental results demonstrate that our algorithm consistently outperforms baseline methods, achieving accuracy rates of 99.30%, 89.60%, and 87.42%, respectively, thereby attaining state-of-the-art performance in the field. • Proposed imbalanced average firing rate across time steps. • Analyzed BN layer inadequacy, proposed BGN layer. • Introduced Spike Spatio-Temporal Attention (SSTA) module. • Achieved SOTA results on three popular neuromorphic datasets. [ABSTRACT FROM AUTHOR]

Distributed optimization aims to effectively complete specified tasks through cooperation among multi-agent systems, which has achieved great success in large-scale optimization problems. However, it remains a challenging task to develop an effective distributed algorithm with theoretical guarantees, especially when dealing with nonconvex constraints. More importantly, high-dimensional data often exhibits inherent structures such as sparsity, which if exploited accurately, can significantly enhance the capture of its intrinsic characteristics. In this paper, we introduce a novel d ist r ibut e d sp a rsity constrained optimization framework over the Stiefel m anifold, abbreviated as DREAM. DREAM innovatively integrates the ℓ 2 , 0 -norm constraint and Stiefel manifold constraint within a distributed optimization setting, which has not been investigated in existing literature. Unlike the existing distributed methods, the proposed DREAM not only can extract the similarity information among samples, but also more flexibly determine the number of features to be extracted. Then, we develop an efficient Newton augmented Lagrangian-based algorithm. In theory, we delve into the relationship between the minimizer, the Karush–Kuhn–Tucker point, and the stationary point, and rigorously demonstrate that the sequence generated by our algorithm converges to a stationary point. Extensive numerical experiments verify its superiority over state-of-the-art distributed methods. [ABSTRACT FROM AUTHOR]

Automatically generating a readable sentence that describes the text-contained image is a challenging task. Compared to traditional image captioning algorithms, OCR-based image captioning focuses on reading OCR tokens in images and understanding them with the image content to generate descriptions. However, existing research mainly concentrate on improving the quantity and quality of obtaining OCR tokens and exploring their spatial relationships while lacking investigation into how to effectively join OCR tokens with image content. This paper proposes a cross-region feature fusion with a geometrical relationship Transformer(CFGR-Transformer) for OCR-based image captioning. The network first establishes the associations between the OCR and object regions of the image by constructing relative geometric relationships, including width/height difference, distance, IOU(Intersection over Union), inclusion relationships, and angles offset, and then incorporates intra-region and cross-region features to aggregate entities from different modalities by a multi-head attention mechanism based on relative relationships. Benefiting from the guidance of the relative relationship, visual entities like OCR tokens and object regions can consider multiple relative relationships as the attention weight for feature fusion within each subspace. Extensive experiments conducted on the TextCaps dataset demonstrate the effectiveness of the proposed CFGR-Transformer method. In particular, our results on the online testing of TextCaps achieve an improvement in CIDEr score from 93.0% to 98.2%. [ABSTRACT FROM AUTHOR]

This paper investigates the distributed fixed-time formation problem of unmanned surface vehicles (USVs) in the presence of external disturbances, model uncertainties, input saturation and quantization constraints. To deal with the problem, a fixed-time sliding-mode control algorithm is proposed, where multi-layer neural networks (MNNs) are designed to approximate the unknown dynamics and composite disturbances of the system. The proposed MNNs combine the advantages of fuzzy neural networks (FNNs) and radial basis function neural networks (RBFNNs), exhibiting robust dynamic characteristics. Furthermore, the non-singular fast terminal sliding mode (NFTSM) is integrated into the fixed-time control framework to improve the robustness and speed of convergence for uncertain USV systems. Comparative simulations conducted with USVs demonstrate the superiority and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]