Inspired by the parts-based representation mechanism in human neural cognition, Non-negative Matrix Factorization (NMF) serves as a fundamental neural network paradigm for feature extraction across information retrieval and computer vision domains. However, since the learning rules of the NMF algorithm only converge to local minima of its objective function, it results in slow convergence and instability. Although significant improvements have been proposed to address these problems, they introduce some other problems such as trivial solutions and high computational cost. Studies have shown that interconnected neurons in the human brain form a neural network, i.e., a dynamical system governed by ordinary differential equations (ODEs), which establishes a nonlinear mapping from external inputs to their associated attractors. In this paper, we propose a novel NMF-based neural model by leveraging this insight. Specifically, we adopt $$sin^2(\cdot )$$ as the activation function of the dynamical system, enabling the global attractor property to guarantee the convergence of the neural model. By imposing a constraint of unique ODE solution on the original NMF cost function, a global attractor is embedded into the existing NMF framework, allowing the proposed model to converge to the global minimum of the dynamic system. In this model, 1) Enhanced nonlinearity strengthens part-based learning performance; 2) The learning rules are non-increasing and stable, converging to global attractors with fewer iterations, greatly boosting performance in image analysis; 3) Its dynamic, multi-layer mechanism better captures the intrinsic structures of samples. The convergence of the algorithm is also analyzed in this paper. Extensive experiments are conducted to demonstrate the effectiveness of the proposed model. Compared with some classic NMF models and the most recently developed NMF related models, test results on four different datasets show that the proposed method can obtain state-of-the-art performance in image clustering with accuracy improvements: 1.31% on ORL, 1.16% on COIL20, 1.16% on Caltech101, and 1.15% on YouTube Faces.

To enhance the performance of a Takagi-Sugeno-Kang fuzzy classifier (TSKFC) on classification tasks, multiple single TSKFC models regarded as blocks to construct a deep TSKFC in series. Moreover, a novel evolutionary algorithm (EA) named hybrid search evolutionary algorithm with competitive behavior (C-SaHSEA) was proposed to search the best architecture of the deep TSKFNN for the different classification tasks. C-SaHSEA is a novel algorithm combined with two search algorithms owning strong exploration and exploitation characteristics separately which can be support to each other to enhance the search ability and stability through the hybrid search. Moreover, self-adaptive update laws for the parameters of mutation and crossover operators were adopted to alleviate the difficulty of complex design and the influence of additional parameters on the search ability. Considering the computation cost of the optimization task of the optimal architecture search, a mechanism called competitive behavior was deployed into the proposed search algorithm. To demonstrate the superiority of the C-SaHSEA, eight EAs was conducted as comparison methods on five test functions. The results of mean fitness and standard deviation fitness demonstrated the search ability and stability of the C-SaHSEA. Then, eight dataset was used to validate the performance improvement of the deep TSKFC optimized by the C-SaHSEA. By comparing with the other nine methods, the high-performance of the optimized deep TSKFC has been improved.

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling. To address these problems, this paper proposes a Latent Feature-oriented Diffusion Probability Model (LDDPM). First, we designed a conditional encoder capable of effectively encoding LR images, reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images. We then employed a normalized flow and multimodal adversarial training, learning from complex multimodal distributions, to model the denoising distribution. Doing so boosts the generative modeling capabilities within a minimal number of sampling steps. Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics, providing a fresh perspective for tackling SISR tasks.

Abstract Mangrove wetlands are important ecosystems in tropical and subtropical coastal areas, providing wind and wave attenuation and embankment protection functions. However, mangrove wetlands worldwide are facing severe loss and degradation. Accurate identification of mangrove wetland extent is crucial for their protection, but traditional methods struggle to meet the requirements of large‐scale, high‐precision identification. Furthermore, field data collection and annotation in wetlands in complex intertidal zones pose challenges, and the lack of high‐quality training samples limits the application of deep learning methods in this field. This paper proposes a novel semantic segmentation framework for mangrove wetlands called mangrove wetland remote sensing image segmentation network based on segment anything model (MW‐SAM) to address these issues. MW‐SAM is based on the pre‐trained SAM and achieves cross‐domain adaptation through parameter‐efficient fine‐tuning techniques. It introduces wetland‐specific prompts, auxiliary branches, semi‐supervised training, and iterative optimization strategies to improve accuracy and tackle the problem of sample scarcity. Moreover, on the mangrove wetland dataset constructed in this paper, MW‐SAM significantly outperforms SAM and other traditional methods. MW‐SAM provides a new technology for monitoring and protecting mangrove wetlands, and the constructed dataset will be made publicly available, which is expected to promote the development of mangrove wetland conservation efforts.

This article focuses on the intralayer-dependent impulsive synchronization of multiple mismatched multilayer neural networks (NNs) with mode-mixed effects. Initially, a novel multilayer NN model that removes the one-to-one interlayer coupling constraint and introduces nonidentical model parameters is first established to meet diverse modeling requirements in complex applications. To help the multilayer target NNs with mismatched connection coefficients and time delays achieve synchronization, the hybrid controller is designed using intralayer-dependent impulsive control and switched feedback control approaches. Furthermore, the mode-mixed effects caused by the intralayer coupling delays and switched intralayer topologies are incorporated into the novel model and analysis method to ensure that the subsystems operating within the current switching interval can effectively use the topology information of the previous switching intervals. Then, a novel analysis framework including super-Laplacian matrix, augmented matrix, and mode-mixed methods is developed to derive the synchronization results. Finally, the main results are verified via the numerical simulation with secure communication.

This article is concerned with the exponential synchronization of coupled memristive neural networks (CMNNs) with multiple mismatched parameters and topology-based probability impulsive mechanism (TPIM) on time scales. To begin with, a novel model is designed by taking into account three types of mismatched parameters, including: 1) mismatched dimensions; 2) mismatched connection weights; and 3) mismatched time-varying delays. Then, the method of auxiliary-state variables is adopted to deal with the novel model, which implies that the presented novel model can not only use any isolated system (regard as a node) in the coupled system to synchronize the states of CMNNs but also can use an external node, that is, not affiliated to the coupled system to synchronize the states of CMNNs. Moreover, the TPIM is first proposed to efficiently schedule information transmission over the network, possibly subject to a series of nonideal factors. The novel control protocol is more robust against these nonideal factors than the traditional impulsive control mechanism. By means of the Lyapunov-Krasovskii functional, robust analysis approach, and some inequality processing techniques, exponential synchronization conditions unifying the continuous-time and discrete-time systems are derived on the framework of time scales. Finally, a numerical example is provided to illustrate the effectiveness of the main results.

This article focuses on the membership-mismatched impulsive exponential stabilization for fuzzy unconstrained multilayer neural networks (MNNs) with node-dependent time-varying delays (NDTVDs). To begin with, this work proposes a novel MNNs model with unconstrained interlayer and intralayer parameters, which may allow nodes in all layers to have inconsistent attributes and structures. Meanwhile, the novel model considers the NDTVDs and removes the strict constraints including node alignment and one-to-one interlayer connection to meet diverse modeling requirements in complex applications. Then, the proposed fuzzy impulsive controller does not need to share the same fuzzy parameters as the fuzzy MNNs model, reducing the implementation complexity of the fuzzy impulsive controller. To derive the main results using the augmented vector form of unconstrained MNNs, the sparse matrix method is proposed to convert the node-dependent delayed MNNs model into an equivalent model with multiple delays. Moreover, the time-dependent Lyapunov function (TDLF) technique is adopted to improve the reliability of the stabilization conditions by fully utilizing the state information of both the current and neighboring impulsive intervals. Finally, the main results are verified using numerical simulation.

This article investigates the problem of relaxed exponential stabilization for coupled memristive neural networks (CMNNs) with connection fault and multiple delays via an optimized elastic event-triggered mechanism (OEEM). The connection fault of the two or some nodes can result in the connection fault of other nodes and cause iterative faults in the CMNNs. Therefore, the method of backup resources is considered to improve the fault-tolerant capability and survivability of the CMNNs. In order to improve the robustness of the event-triggered mechanism and enhance the ability of the event-triggered mechanism to process noise signals, the time-varying bounded noise threshold matrices, time-varying decreased exponential threshold functions, and adaptive functions are simultaneously introduced to design the OEEM. In addition, the appropriate Lyapunov-Krasovskii functionals (LKFs) with some improved delay-product-type terms are constructed, and the relaxed exponential stabilization and globally uniformly ultimately bounded (GUUB) conditions are derived for the CMNNs with connection fault and multiple delays by means of some inequality processing techniques. Finally, two numerical examples are provided to illustrate the effectiveness of the results.

This article addresses the problem of dynamic pinning synchronization of fuzzy-dependent-switched (Fds) coupled memristive neural networks (CMNNs) with mismatched dimensions on time scales. To begin with, the probabilistic coupling delays, time scales, mismatched dimensions, and function projective synchronization rules are considered to design the novel CMNNs to improve the reliability and generalization ability of the model. Then Fds rules and dynamic pinning control (DPC) method are adopted to design the CMNNs, which can effectively promote the information exchange between the switching signals and the fuzzy processes and can improve the utilization of the communication bandwidth between the nodes of CMNNs. Meanwhile, the method of constructing auxiliary state variables is adopted here to deal with the presented model, so that the coupled and isolated systems with different dimensions can realize information exchange and data sharing. This method also provides a solution for researchers by using low-dimensional systems to estimate or synchronize high-dimensional systems. Moreover, by means of Lyapunov–Krasovskii functional, auxiliary orthogonal matrix, and some inequality processing techniques, the conditions of modified function projective synchronization for Fds CMNNs are derived via the DPC on time scales. Finally, two numerical examples are provided to illustrate the effectiveness of the main results.

This article investigates the heterogeneous impulsive synchronization for T-S fuzzy probabilistic coupled delayed neural networks (CDNNs) with mode-dependent parameters and piecewise membership functions. To begin with, a novel CDNNs model with adjustable coupling strength and probabilistic coupling delays is designed to ensure the accuracy of the CDNNs model. Meanwhile, the generalized isolated node with four types of mismatched parameters, named heterogeneous isolated delayed neural network, is first considered to extend the synchronization problem. Then, the mode-dependent fuzzy rules are introduced to design the novel model, which implies that switching signals and fuzzy processes are interdependent and can share information to communicate. To improve the hybrid controller’s reliability, the mode-dependent impulses are also developed here, in which the impulsive effects with different properties can occur at any moment in the switching interval. The exponential synchronization conditions are derived by means of the method of auxiliary state variables, Lyapunov–Krasovskii functional, average switching dwell period, and mode-dependent average impulsive dwell period. Moreover, the improved mode-dependent piecewise approximated membership functions are proposed to reduce the main results’ conservatism. Finally, a numerical example is provided to illustrate the effectiveness of the main results.

Due to the high mobility of communication, channel times can vary rapidly and system performance can be decreased. In this study, pseudo‐random noise is used as the guard interval and the training sequence in the time domain in order to estimate the channel‐based compressive sensing scheme. This scheme reduces the number of pilots in the frequency domain and improves spectrum efficiency. By adequately exploiting the sparse characteristics and temporal correlation of the wireless channel, a low complexity compressive channel estimation scheme is proposed. Firstly, the authors average the successive symbols of the channel impulse response in the coherence time to improve the accuracy of the coarse channel estimation. Secondly, a low complexity partial priori information CoSaMP (PPI‐CoSaMP) algorithm is proposed to accurately estimate the channel state information. Finally, based on the precise time delay, the accurate gains are estimated based on the least‐squares algorithm. The simulation results show that compared with the conventional algorithms, the number of observation points required by the PPI‐CoSaMP algorithm is reduced by at least 25%. Moreover, the proposed scheme is more robust at larger multipath channel delays. The complexity of the proposed scheme is reduced by 51.21% compared with the conventional CoSaMP algorithm.

Ground moving target indication (GMTI) is of great important for surveillance and reconnaissance. The representative GMTI technique of along-track interferometry (ATI) synthetic aperture radar (SAR) does not take into account the fact that the stationary clutter unavoidably corrupts the interferometric phase of the targets. In this paper, we aim at multiple-input and multiple-output (MIMO) SAR-based solution. We proposed a scheme of MIMO SAR which is different from normal MIMO radar for ground moving targets detection and imaging. This approach employs MIMO along-track antenna configuration and waveform diversity. The system schemes, signal models, and waveform diversity are investigated.

To integrate a synthetic aperture radar (SAR) into an operational unmanned airborne vehicle (UAV), it should be as small as possible to meet stringent limitations of size, weight, and power consumption. It appears that the novel combination of millimeter-wave frequency-modulated continuous-wave (FMCW) technology and SAR techniques can provide an optimal solution. However, some efficient techniques should be applied to resolve range/Doppler ambiguities in FMCW UAV SAR systems. As such, a technique of waveform-diversity-based millimeter-wave UAV SAR imaging is presented in this paper. Along with the described system concept and signal model, the performance of the diversified waveforms evaluated by their cross correlations is detailed. As the conventional stop-and-go approximation is not valid for FMCW SAR, a modified wavenumber-domain algorithm with a consideration of continuous antenna motion during transmission and reception is derived. This imaging algorithm is validated with computer simulations. Furthermore, one parallel direct-digital-synthesizer-driven phase-locked-loop synthesizer with adaptive nonlinearity compensation, which has been validated by the experimental results, is proposed to obtain a millimeter-wave FMCW signal with fine frequency linearity.

Bi- and multistatic synthetic aperture radars (SARs) can achieve reduced vulnerability in military systems, especially in directional responsive jamming, and avoid physical attack to radar platforms. In this letter, a technique for jamming bi- and multistatic SAR systems is proposed, which is implemented with a novel transponder. This technique is based on a delayed retransmission of the received radar signal toward the scene. Unlike conventional delayed jamming, here, the jammer's delay time is random in the whole range interval. Moreover, the jamming signal is not retransmitted to the receiver directly but to the areas with targets that need to be protected against being imaged by radar. By this, it is then possible to jam the radar echoes independent of the receiver location