This article investigates the prescribed-time containment control problem for multiple wheeled mobile robots (MWMRs) with unknown control gains. A novel and generalized prescribed-time stability theorem is established, significantly advancing existing frameworks and facilitating controller design. For each follower, a distributed containment observer is developed to ensure that the observer state converges precisely to the convex hull formed by multiple leaders within a prescribed time. This approach effectively transforms the containment control problem into a more tractable tracking control problem, meanwhile enabling local reconstruction of unmeasured neighbor states using available observer outputs. Then, the type-B Nussbaum function is employed to eliminate the effects of the time-varying unknown control coefficient. Based on the developed prescribed-time theorem and the time-varying parametric Lyapunov equation (PLE), the fully actuated controllers are designed for the MWMRs. It can guarantee that the containment errors converge to zero within the prescribed time. Finally, simulation results validate the effectiveness of the proposed method.

Federated heterogeneous graph learning, an extension of federated learning, effectively represents complex multidimensional relationships while maintaining data privacy. In horizontal federated heterogeneous graph learning, data from different parties often vary in topology and semantics, leading to sensitivity to distribution imbalances and increasing topological complexity. These differences hinder models from learning shared representations and cause instability during training. To address these challenges, this paper proposes a novel multi-scale adaptive horizontal federated heterogeneous graph learning method MAFedHGL. A random masking mechanism forces the model to infer missing connections. The model also captures multi-hop and multi-path connections using high-order topology mining, enhancing robustness against structural heterogeneity. Dynamic semantic consistency modeling uses a masking matrix to recover and integrate diverse node attributes, ensuring both global and local semantic consistency. Using clustering coefficients as aggregation weights enables clients with richer structural information to contribute more effectively to the global model, improving adaptability and performance across varying data distributions in horizontal federated heterogeneous graph learning. Extensive experiments on multiple public heterogeneous graph datasets validate that the proposed method outperforms state-of-the-art methods in both performance and robustness across various data distribution scenarios.

Food categorization is pivotal in numerous aspects of everyday life, assisting in the selection of food, managing diets, and addressing essential survival requirements. By leveraging the complementary information of various views, multi-view learning usually achieves superior performance compared to the single-view learning methods. However, characterized by the unrestrained openness of internet platforms and potential inconsistencies in food data collection processes, multi-view features often suffer from data loss, resulting in incomplete multi-view food data. Conventional multi-view clustering methods often falter in effectively capitalizing on the diverse correlations contained in food data, and exhibit limitations in dealing with the noise and irregularities pervading different views. Addressing these challenges, this paper presents the Robust Multi-Graph Contrastive network (RMGC) for multi-view food clustering. RMGC artfully combines multi-view representation learning with multi-graph contrastive regularization, creating a cohesive framework to manage incomplete multi-view data. By developing a multi-view encoding network, RMGC seamlessly blends various views into a cohesive representation, astutely assessing the significance of each view. More importantly, the proposed robust multi-graph contrastive regularization enhances the precision of the learned representation and successfully counteracts the noise and unreliability in multi-view data. The experiments conducted across several multi-view datasets manifest the effectiveness of RMGC, showing its superiority over existing methods. Our method not only making an advancement in food categorization but also contributes to the broader field of multi-view learning, offering innovative solutions for handling incomplete and noisy multi-view data.

This article aims to solve the distributed online convex optimization (DOCO) problems subjected to multiple coupled constraints over time-varying (TV) unbalanced digraphs. The existing global constraint models and coupled constraint models, where the number of constraints is related to the number of nodes, are not sufficient to reflect the characteristics of multiple coupled constrained optimization problems. On account of this drawback, a multiple coupled constraint model is constructed, which contains several coupled constraints, only including a part of all nodes. In addition, practical TV scenarios commonly come with complex network connectivity, which requires diverse matrices for fusing various information. In view of connectivity requirements, a novel TV distributed primal–dual push–pull (TDPP) algorithm, which can convert two types of weight matrices to all onefold row stochastic (RS) matrices, is proposed to tackle multiple coupled constrained problems. Under some general and necessary assumptions and conditions, both desired sublinear dynamic regret and constraint violation can be acquired by a strict theoretical analysis. Finally, two numerical examples are utilized to verify the superiority and validity of the TDPP algorithm compared with similar algorithms.

In this article, we investigate the cluster consensus problem of multiagent systems (MASs) with general linear dynamics and weighted antagonistic interactions under aperiodic denial-of-service (DoS) attacks. First, an event-triggered communication mechanism is designed to efficiently reduce unnecessary message transmission over unreliable networks, where the event-triggered function with dynamically varying thresholds is designed based on the state estimators instead of the real-time states so that continuous communication can be avoided both in controller updates and triggering threshold detection. Then, a novel event-triggered cluster consensus protocol is designed for MASs with DoS attacks and structurally balanced signed digraphs, where Zeno behavior can be strictly excluded by the proposed triggering mechanism. Furthermore, to cope with the structurally unbalanced signed digraph, an improved event-triggered resilient consensus protocol is developed by introducing a pinning control strategy. By utilizing the piecewise Lyapunov functional approach, some sufficient conditions are derived for the cluster consensus under structurally balanced and unbalanced signed digraphs, while the selection principles of event-triggered parameters and resilient controller gains are obtained. Finally, the validity of the theoretical results is verified by practical simulation examples.

Correlation filter (CF)-based approaches have gained widespread attention in the field of unmanned aerial vehicle (UAV) visual tracking due to their light-weight characteristics. However, CFs are prone to generating low-quality response in challenging UAV scenarios, e.g., fast motion and background clutter. In this paper, in order to model the tracker more robustly, we first conduct an effective regularization analysis from the perspectives of response- and background-learning. Specifically, to address response degradation, we propose a module for learning temporal consistency and reversibility of response, supplemented by a novel background-aware module to enhance the ability to learn from negative samples. In addition, we propose a fast coarse-to-fine scale search strategy, which alleviates the challenges in estimating bounding boxes under non-uniform aspect ratios. We have developed two tracker versions, namely RBLT and DeepRBLT, based on the depth of the features. Comprehensive experiments on four UAV benchmarks and one generic benchmark have indicated the superiority of our trackers compared to other state-of-the-art trackers, with enough speed for real-time applications.

Correlation filter (CF)-based approaches have been widely applied in online object tracking tasks for unmanned aerial vehicles (UAVs) due to their high computational efficiency and low memory consumption. One of the key steps is to perform correlation operations between the appearance model (AM) and the filter. However, as the difficulty in controlling the learning rate of the AM, most existing trackers are prone to causing degradation. In this paper, we propose a novel complementary AM (CAM) consisting of a primary model (PM) and a secondary model (SM). Specifically, the learning rates of the PM and SM are approximately complementary, allowing the CAM to consider both past and current information. Moreover, in order to take full advantage of historical information, a CAM-based reversibility reasoning approach is proposed for CF training. It can robustly handle the variations in object appearance. Then we further create a deep tracker by fusing convolutional features which demonstrates more outstanding performance. We also embed the CAM into two advanced trackers to validate the scalability of the CAM. Comprehensive experiments on six challenging UAV tracking benchmarks have indicated the superiority of our method compared to other 36 state-of-the-art CPU- and GPU-based trackers, with a speed of 45 FPS running on a cheap CPU.

This brief is concerned with the problem of kernel adaptive filtering for a complex network. First, a coupled kernel least mean square (KLMS) algorithm is developed for each node to uncover its nonlinear measurement function by using a series of input-output data. Subsequently, an upper bound is derived for the step-size of the coupled KLMS algorithm to guarantee the mean square convergence. It is shown that the upper bound is dependent on the coupling weights of the complex network. Especially, an optimal step size is obtained to achieve the fastest convergence speed and a suboptimal step size is presented for the purpose of practical implementations. Besides, a coupled kernel recursive least square (KRLS) algorithm is further proposed to improve the filtering performance. Finally, simulations are provided to verify the validity of the theoretical results.

Federated Learning ensures that clients can collaboratively train a global model by uploading local gradients, keeping data locally, and preserving the security of sensitive data. However, studies have shown that attackers can infer local data from gradients, raising the urgent need for gradient protection. The differential privacy technique protects local gradients by adding noise. This paper proposes a federated privacy-enhancing algorithm that combines local differential privacy, parameter sparsification, and weighted aggregation for cross-silo setting. Firstly, our method introduces Renyi differential privacy by ´ adding noise before uploading local parameters, achieving local differential privacy. Moreover, we dynamically adjust the privacy budget to control the amount of noise added, balancing privacy and accuracy. Secondly, considering the diversity of clients’ communication abilities, we propose a novel Top-K method with dynamically adjusted parameter upload rates to effectively reduce and properly allocate communication costs. Finally, based on the data volume, trustworthiness, and upload rates of participants, we employ a weighted aggregation method, which enhance the robustness of the privacy framework. Through experiments, we validate the effective trade-off among privacy, accuracy, communication costs and robustness achieved by the proposed method.

Aiming at the problem that measurement model uncertainty restrains navigation accuracy in the celestial/ inertial (CNS/INS) integrated navigation system, a kind of CNS/INS integrated navigation method based on improved adaptive cubature Kalman filter (CKF) is proposed. In order to mitigate the influence of installation error and axis disturbance error of star camera, angular distance between starlight vector of stars and line of sight vector of space targets is employed to establish the measurement model; the measurement noise covariance matrix (MNCM) is estimated online to lower the model uncertainty; adaptive adjustment coefficient is constructed based on squared Mahalanobis distance (SMD) of measurement innovation to adjust forgetting factor online to further improve robustness and adaptability of the method. Simulation results demonstrate that the proposed method can achieve higher navigation accuracy compared to standard and classical method under measurement model mismatch.

Relational databases are widely applied in various industries, such as government departments, medical institutions and enterprises, for data storage and relationship management. It is convenience to data maintenance, however, the data in it maybe vulnerable to be forged or tampered with. Therefore, protecting the copyright of relational databases is a critical issue. Fortunately, watermarking technology can be used to prove copyright ownership. Since the digital watermarking technology can solve this problem effectively, based on semantic, we propose two watermarking approaches with high security and strong robustness for numeric and non-numeric data of relational databases in this paper. On the one hand, we propose a reversible numeric watermarking approach. It performs the replacement operation at the semantic level and retain the statistical characteristics of the data. On the other hand, based on word segmentation and word embedding, the non-numerical attributes of the relational database with natural language are chosen to embed watermark. It is noteworthy that the proposed mechanism can be applied to both Chinese and English with minimum distortion. Additionally, we also propose the virtual splitting of attribute column and the principle of modification minimum to guarantee the capacity of watermark and reduce the data modification rate. Additionally, the BCH (31,16,7) error control code is added to the binary watermark string to improve the detection rate of watermark. Based on the above innovations, the security of watermarking algorithm is improved successfully by double encryption (chaos encryption and hash encryption) with two keys (the user's private key and the attribute column key). The simulation results demonstrate that the proposed two algorithms in this paper have stronger robustness on defensing malicious attacks than previous works.

Magnetic resonance imaging (MRI) reconstruction model based on total variation (TV) regularization can solve some problems, e.g., incomplete reconstruction, blurred imaging, and denoising. However, it has problems such as sensitivity to outliers, poor ability to induce the sparsity of the gradient domain of MR image. In this paper, minimax-concave total variation regularization based on $L_{p}-$norm (MCTV-Lp) is proposed to overcome these drawbacks. Specifically, the TV-Lpregularization is constructed using the exponent ${p}(0\lt{p}\lt 1)$, which is defined as the $L_{p}-$norm of the gradient. Then TV-Lpis combined with the minimax-concave penalty of the $L_{p}-$norm to construct the MCTV-Lp. Finally, the sparse reconstruction model based on minimax-concave total variation (MCTV-SRM) is proposed, where the objective function is formulated as the sum of the regularization of MCTV-Lpand the data-fitting term of $L_{2}-$norm. Moreover, an optimization algorithm based on the alternating direction method of multipliers (ADMM) is given to solve the related optimization problems iteratively. Results on different datasets with different experimental settings show that the proposed method is better adapted to MRI reconstruction and the relative error and PSNR are significantly improved than several typical methods, while can reconstruct MR images with clear details and textures.

This paper studies the distributed federated learning problem when the exchanged information between the server and the workers is quantized. A novel quantized federated averaging algorithm is developed by applying stochastic quantization scheme to the local and global model parameters. Specifically, the server broadcasts the quantized global model parameter to the workers; the workers update local model parameters using their own data sets and upload the quantized version to the server; then the server updates the global model parameter by aggregating all the quantized local model parameters and its previous global model parameter. This algorithm can be interpreted as a quantized variant of the federated averaging algorithm. The convergence is analyzed theoretically for both convex and strongly convex loss functions with Lipschitz gradient. Extensive experiments using realistic data are provided to show the effectiveness of the proposed algorithm.

For large-scale machine learning tasks, distributing data in multiple clients, and using distributed optimization algorithms with a parameter server can accelerate the training process. The federated average algorithm has been widely used for distributed optimization via training local models in parallel and aggregating local models in a server to obtain the global model. To further improve the performance of the federated average algorithm, a novel federated learning algorithm have been proposed in this article by embedding a lazy strategy in the distributed Adam-type algorithm. In the proposed algorithm, the learning rate is adjusted adaptively in local update and lazy update strategy is applied on the second-order momentum of clients to make the learning rate identical. The convergence of the proposed algorithm is provided for both convex and nonconvex loss functions. Experiments have been conducted on MNIST digit recognition data set and CIFAR-10 data set. Experimental results show that the proposed algorithm can significantly reduce the communication overhead, thereby reduce the training time by 60% for CIFAR-10 data set, and the proposed algorithm achieve better performance than the federated average algorithm and its momentum version.

In multitarget tracking systems, it is usually assumed that each measurement is generated with respect to a single target. This is not always true for generating relative state measurements or cross-target information in a coupled fashion. This note is concerned with the problem of distributed filtering for multitarget tracking systems with coupled measurements. By representing the coupling features of the target states in the measurements as a directed graph, a modified Kalman consensus filter (KCF) is proposed for a target-dependent augmented system whose state vector consists of in-going neighborhood targets. To analyze the performance of the modified KCF in a directed graph, a sufficient condition is derived to guarantee the boundedness of the estimation errors in the mean square sense. Numerical studies are provided to verify the applicability of the KCF.

With the development of big data, relational databases are playing an important role in enterprises, military affairs, medical, etc. Moreover, they are vulnerable to piracy, forgery, and tampering. Consequently, the copyright protection of relational databases has become an issue with increasing concern. The use of digital watermarking technology can solve this problem effectively. In this paper, by using Chinese word segmentation and word embedding, the non-numerical attributes of the relational database with Chinese natural language are chosen to embed watermark. The method of the virtual splitting of the attribute column and the principle of modification minimum are proposed to guarantee the watermark capacity and reduce the data modification rate. The simulations are carried out to prove the algorithm has strong robustness to defense malicious attacks.

This paper studies the state estimation problem for nonlinearly coupled complex networks. A variance-constrained state estimator is developed by using the structure of the extended Kalman filter, where the gain matrix is determined by optimizing an upper bound matrix for the estimation error covariance despite the linearization errors and coupling terms. Compared with the existing estimators for linearly coupled complex networks, a distinct feature of the proposed estimator is that the gain matrix can be derived separately for each node by solving two Riccati-like difference equations. By using the stochastic analysis techniques, sufficient conditions are established which guarantees the state estimation error is bounded in mean square. A numerical example is provided to show the effectiveness and applicability of the proposed estimator.

This article studies the problem of state estimation for stochastic systems with unknown inputs. To reduce the communication cost from the sensor to the remote processor, an event‐triggered communication mechanism is proposed in terms of an event generator function for the innovation vectors. The event‐triggered estimator is developed by introducing an input term in the steady‐state Kalman filter for the corresponding nominal system. The input gain matrix is determined by treating the nominal estimator error dynamics as the desired performance. It is shown that the estimation error is bounded in mean square under certain conditions. A numerical example is provided to verify the effectiveness of the proposed estimator.

The problem of interacting multiple model (IMM) estimation for jump Markov linear systems with unknown measurement noise covariance is studied. The system state and the unknown covariance are jointly estimated, where the unknown covariance is modelled as a random matrix according to an inverse‐Wishart distribution. For the IMM estimation with random matrices, one difficulty encountered is the combination of a set of weighted inverse‐Wishart distributions. Instead of using the moment matching approach, this difficulty is overcome by minimising the weighted Kullback–Leibler divergence for inverse‐Wishart distributions. It is shown that a closed‐form solution can be derived for the optimisation problem and the resulting solution coincides with an inverse‐Wishart distribution. Simulation results show that the proposed filter outperforms the previous work using the moment matching approach.

The problem of distributed target tracking using time of arrival and received signal strength with unknown path loss exponent (PLE) is studied. The PLE is modelled as a Markov chain with three states and an adaptive gridding strategy is adopted to adjust the PLE recursively in a bounded interval. Therefore, the target tracking model is formulated as a jump Markov non‐linear system. The interacting multiple model () estimator is applied to derive the target state estimates for each sensor and the covariance intersection approach is used to fuse sensor‐based estimates in a distributed fashion. Simulation results show a promising performance for the proposed filter.

This study is concerned with the problem of filtering and fixed‐lag smoothing for jump Markov non‐linear systems when the mode information can be extracted from an image sensor. Based on the idea of Rao–Blackwellisation, the authors present a general theoretical framework to derive the recursive estimates by employing the particle filtering method. A suboptimal image‐enhanced Rao–Blackwellised particle filter is proposed, in which the mode state is estimated by using random sampling and the continuous state as well as the relevant likelihood function are approximated as Gaussian distributions. The one‐step fixed‐lag smoothing result is also obtained for such systems with lagged mode observations. Performance comparison of the proposed algorithms with the existing methods is provided through a manoeuvring target tracking simulation study.