Parametric Stability Criteria for Delayed Recurrent Neural Networks via Flexible Delay-Dividing Method.

This article focuses on investigating the stability issue for recurrent neural networks (RNNs) with interval time-varying delays (TVDs) based on a flexible delay-dividing method with parameters, which are related to the delay derivative. First, an interval of delay is separated into parametric subintervals via the linear combination technique. Then, an establishment of Lyapunov-Krasovskii functional (LKF) is connected to the parameters, and a novel linear technology is suggested to dispose of integral terms in the derivatives of the constructed function. Finally, the validity and advantage of the inferred criteria are interpreted by the comparison of representative simulation examples.

Residual Temporal Convolutional Network With Dual Attention Mechanism for Multilead-Time Interpretable Runoff Forecasting.

As a pivotal subfield within the domain of time series forecasting, runoff forecasting plays a crucial role in water resource management and scheduling. Recent advancements in the application of artificial neural networks (ANNs) and attention mechanisms have markedly enhanced the accuracy of runoff forecasting models. This article introduces an innovative hybrid model, ResTCN-DAM, which synergizes the strengths of deep residual network (ResNet), temporal convolutional networks (TCNs), and dual attention mechanisms (DAMs). The proposed ResTCN-DAM is designed to leverage the unique attributes of these three modules: TCN has outstanding capability to process time series data in parallel. By combining with modified ResNet, multiple TCN layers can be densely stacked to capture more hidden information in the temporal dimension. DAM module adeptly captures the interdependencies within both temporal and feature dimensions, adeptly accentuating relevant time steps/features while diminishing less significant ones with minimal computational cost. Furthermore, the snapshot ensemble method is able to obtain the effect of training multiple models through one single training process, which ensures the accuracy and robustness of the forecasts. The deep integration and collaborative cooperation of these modules comprehensively enhance the model's forecasting capability from various perspectives. Ablation studies conducted validate the efficacy of each module, and through multiple sets of comparative experiments, it is shown that the proposed ResTCN-DAM has exceptional and consistent performance across varying lead times. We also employ visualization techniques to display heatmaps of the model's weights, thereby enhancing the interpretability of the model. When compared with the prevailing neural network-based runoff forecasting models, ResTCN-DAM exhibits state-of-the-art accuracy, temporal robustness, and interpretability, positioning it at the forefront of contemporary research.

Analysis of medical images super-resolution via a wavelet pyramid recursive neural network constrained by wavelet energy entropy.

Recently, multi-resolution pyramid-based techniques have emerged as the prevailing research approach for image super-resolution. However, these methods typically rely on a single mode of information transmission between levels. In our approach, a wavelet pyramid recursive neural network (WPRNN) based on wavelet energy entropy (WEE) constraint is proposed. This network transmits previous-level wavelet coefficients and additional shallow coefficient features to capture local details. Besides, the parameter of low- and high-frequency wavelet coefficients within each pyramid level and across pyramid levels is shared. A multi-resolution wavelet pyramid fusion (WPF) module is devised to facilitate information transfer across network pyramid levels. Additionally, a wavelet energy entropy loss is proposed to constrain the reconstruction of wavelet coefficients from the perspective of signal energy distribution. Finally, our method achieves the competitive reconstruction performance with the minimal parameters through an extensive series of experiments conducted on publicly available datasets, which demonstrates its practical utility.

Performance Degradation Estimation Mechanisms for Networked Control Systems Under DoS Attacks and its Application to Autonomous Ground Vehicle.

This article examines the mechanisms by which aperiodic denial-of-service (DoS) attacks can exploit vulnerabilities in the TCP/IP transport protocol and its three-way handshake during communication data transmission to hack and cause data loss in networked control systems (NCSs). Such data loss caused by DoS attacks can eventually lead to system performance degradation and impose network resource constraints on the system. Therefore, estimating system performance degradation is of practical importance. By formulating the problem as an ellipsoid-constrained performance error estimation (PEE) problem, we can estimate the system performance degradation caused by DoS attacks. We propose a new Lyapunov-Krasovskii function (LKF) using the fractional weight segmentation method (FWSM) to examine the sampling interval and introduce a relaxed, positive definite constraint to optimize the control algorithm. We also propose a relaxed, positive definite constraint that reduces the initial constraints to optimize the control algorithm. Next, we introduce an alternate direction algorithm (ADA) to solve the optimal trigger threshold and design an integral-based event-triggered controller (IETC) to estimate the error performance of NCSs with limited network resources. Finally, we verify the effectiveness and feasibility of the proposed method using the Simulink joint platform autonomous ground vehicle (AGV) model.

Novel adaptive synchronization in finite-time and fixed-time for impulsive complex networks with semi-Markovian switching.

This paper intensively studied the finite-time (FNT) and fixed-time (FXT) synchronization issues for complex networks (CNs) with semi-Markovian switching and impulsive effect. The impulses are assumed to be independent of the semi-Markovian switching. Firstly, a unified FNT and FXT stability criterion of impulsive dynamical system with time-varying delays is extended by comparison principle. Secondly, two novel hybrid control schemes, which are composed of adaptive gain and switching state-feedback are proposed. Thirdly, by employing Kronecker product, Lyapunov-Krasovskii functional and inequality technique, FNT and FXT synchronization criteria for impulsive CNs with semi-Markovian switching are presented in a set of low-dimensional linear matrix inequalities, and the settling times are computed respectively. Finally, simulations are given to verify the proposed adaptive FNT and FXT synchronization criteria.

Observer-Based Adaptive NN Security Control for Switched Nonlinear Systems Against DoS Attacks: An ADT Approach.

In this article, a novel switched observer-based neural network (NN) adaptive control algorithm is established, which addresses the security control problem of switched nonlinear systems (SNSs) under denial-of-service (DoS) attacks. The considered SNSs are described in lower triangular form with external disturbances and unmodeled dynamics. Note that when an attack is launched in the sensor-controller channel, the controller will not receive any message, which makes the standard backstepping controller not workable. To tackle the challenge, a set of NN adaptive observers are designed under two different situations, which can switch adaptively depending on the DoS attack on/off. Further, an NN adaptive controller is constructed and the dynamic surface control method is borrowed to surmount the complexity explosion phenomenon. To eliminate double damage from DoS attacks and switches, a set of switching laws with average dwell time are designed via the multiple Lyapunov function method, which in combination with the proposed controllers, guarantees that all the signals in the closed-loop system are bounded. Finally, an illustrative example is offered to verify the availability of the proposed control algorithm.

Nonfragile power and frequency control in islanded microgrids under abnormal asynchronous stochastic cyber attacks.

In this paper, we focus on the real power sharing and frequency regulation of distributed generators in islanded microgrids with abnormal asynchronous stochastic cyber attacks, which is of great significance to the information security and stable operation of microgrids. Firstly, considering the possible cyber attacks in the communication network, a distributed non-fragile controller with coupled memory delay is proposed according to the nonperiodic sampled-data control. Then, the construction of delay-dependent two-sided looped-functional makes the Lyapunov-Krasovskii functional contain more delay and sampling information and relaxes constraints on free matrices. In addition, based on the enhanced integral inequality technique and the linear convex combination method, a sampling-based consensus protocol is presented to solve the issues of real power sharing and frequency regulation in the islanded microgrids. Finally, to verify the effectiveness and feasibility of the designed control strategy, a modified IEEE 34-bus test system is used for the experiment.

A hybrid event-triggered stabilization approach for switched systems under asynchronous switching and its application.

This paper investigates the stabilization problem of switched systems with mismatched modes by an event-triggered control approach. A hybrid event-triggered scheme (HETS) with a dynamically adjustable threshold is newly proposed, which combines periodic sampling, continuous event-trigger and slow switching. It is assumed that the modes and states of the controller are updated only at each triggering instant, so the situation of asynchronous switching could arise. Compared with the control strategy under static HETS, the proposed hybrid event-triggered control strategy has the advantage of potentially speeding up the stabilization while reducing the communication burden. To ease the analysis, the closed-loop system is accordingly represented as a combination of the switched system with a periodically sampled control input and the one with a continuously event-triggered control input. By considering input delay information in the construction of multiple Lyapunov-Krasovskii functional (LKF), a discontinuous and non-positive definite LKF is developed to establish sufficient conditions on the exponential stability for the closed-loop switched system. The design method of the desired controller and HETS is then provided. Finally, the result obtained in this paper is applied to a networked continuous stirred tank reactors system.

A super-resolution network for medical imaging via transformation analysis of wavelet multi-resolution.

In recent years, deep learning super-resolution models for progressive reconstruction have achieved great success. However, these models which refer to multi-resolution analysis basically ignore the information contained in the lower subspaces and do not explore the correlation between features in the wavelet and spatial domain, resulting in not fully utilizing the auxiliary information brought by multi-resolution analysis with multiple domains. Therefore, we propose a super-resolution network based on the wavelet multi-resolution framework (WMRSR) to capture the auxiliary information contained in multiple subspaces and to be aware of the interdependencies between spatial domain and wavelet domain features. Initially, the wavelet multi-resolution input (WMRI) is generated by combining wavelet sub-bands obtained from each subspace through wavelet multi-resolution analysis and the corresponding spatial domain image content, which serves as input to the network. Then, the WMRSR captures the corresponding features from the WMRI in the wavelet domain and spatial domain, respectively, and fuses them adaptively, thus learning fully explored features in multi-resolution and multi-domain. Finally, the high-resolution images are gradually reconstructed in the wavelet multi-resolution framework by our convolution-based wavelet transform module which is suitable for deep neural networks. Extensive experiments conducted on two public datasets demonstrate that our method outperforms other state-of-the-art methods in terms of objective and visual qualities.

Optimal H∞ tracking control of nonlinear systems with zero-equilibrium-free via novel adaptive critic designs.

In this paper, a novel adaptive critic control method is designed to solve an optimal H∞ tracking control problem for continuous nonlinear systems with nonzero equilibrium based on adaptive dynamic programming (ADP). To guarantee the finiteness of a cost function, traditional methods generally assume that the controlled system has a zero equilibrium point, which is not true in practical systems. In order to overcome such obstacle and realize H∞ optimal tracking control, this paper proposes a novel cost function design with respect to disturbance, tracking error and the derivative of tracking error. Based on the designed cost function, the H∞ control problem is formulated as two-player zero-sum differential games, and then a policy iteration (PI) algorithm is proposed to solve the corresponding Hamilton-Jacobi-Isaacs (HJI) equation. In order to obtain the online solution to the HJI equation, a single-critic neural network structure based on PI algorithm is established to learn the optimal control policy and the worst-case disturbance law. It is worth mentioning that the proposed adaptive critic control method can simplify the controller design process when the equilibrium of the systems is not zero. Finally, simulations are conducted to evaluate the tracking performance of the proposed control methods.

Adaptive fixed-time output synchronization for complex dynamical networks with multi-weights.

This paper addresses fixed-time output synchronization problems for two types of complex dynamical networks with multi-weights (CDNMWs) by using two types of adaptive control methods. Firstly, complex dynamical networks with multiple state and output couplings are respectively presented. Secondly, several fixed-time output synchronization criteria for these two networks are formulated based on Lyapunov functional and inequality techniques. Thirdly, by employing two types of adaptive control methods, fixed-time output synchronization issues of these two networks are dealt with. At last, the analytical results are verified by two numerical simulations.

AutoGMap: Learning to Map Large-Scale Sparse Graphs on Memristive Crossbars.

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., social networks and knowledge graphs) on traditional computing architectures (CPU, GPU, or TPU). But, the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy. To implement the computation or storage of large-scale or batch graphs on memristive crossbars, a natural assumption is that a large-scale crossbar is demanded, but with low utilization. Some recent works question this assumption; to avoid the waste of storage and computational resource, the fixed-size or progressively scheduled "block partition" schemes are proposed. However, these methods are coarse-grained or static and are not effectively sparsity-aware. This work proposes the dynamic sparsity-aware mapping scheme generating method that models the problem with a sequential decision-making model, and optimizes it by reinforcement learning (RL) algorithm (REINFORCE). Our generating model long short-term memory (LSTM), combined with the dynamic-fill scheme generates remarkable mapping performance on the small-scale graph/matrix data (complete mapping costs 43% area of the original matrix) and two large-scale matrix data (costing 22.5% area on qh882 and 17.1% area on qh1484). Our method may be extended to sparse graph computing on other PIM architectures, not limited to the memristive device-based platforms.

Asynchronous control for semi-Markov switching systems with singular perturbation and an improved protocol.

This study addresses the asynchronous control problem for a semi-Markov switching system in the presence of singular perturbation and an improved triggering protocol. To decrease the occupation of network resources, an improved protocol is skillfully established by adopting two auxiliary offset variables. Unlike the existing protocols, the established improved protocol is capable of arranging information transmission with more degrees of freedom, thereby reducing the communication frequency and maintaining control performance. Apart from the reported hidden Markov model, a nonhomogeneous hidden semi-Markov model is used to handle the mode mismatch between the systems and controllers. Benefiting from Lyapunov techniques, parameter-dependent sufficient conditions are devised to ensure a stochastically stable subject to a predetermined performance. Finally, the validity and practicability of the theoretical results are verified via a numerical example and a tunnel diode circuit model.

Sedimentary structures of microbial carbonates in the fourth member of the Middle Triassic Leikoupo Formation, Western Sichuan Basin, China.

In recent years, abundant natural gas has been found in microbial carbonates in the fourth member of the Leikoupo Formation in Western Sichuan Basin. In this study, from the observation of 626 microbial thin sections, four types of microbial carbonates are classified based on the differences of mesostructures. Among them, thrombolites and stromatolites are subdivided into eight types based on the differences of microstructures. Six types of microbial microstructure association (MSA) are identified, and are mainly developed in microbial mounds. The energy of sedimentary environment and hydrodynamic conditions of them from low to high is MSA-5, MSA-1, MSA-6, MSA-3, MSA-4 and MSA-2. Because of the arid climate in the Annie Period, a restricted platform are developed in the upper sub-member of the Leikoupo Formation in Western Sichuan Basin, and the sedimentary facies are lagoon (gypsiferous lagoon or salt lake in evaporate conditions), microbial mounds, shoals, inner platform shoals and open sea from the east to the west. Microbial microstructures not only affect the pore evolution of microbial carbonate reservoirs, but also affect the diagenesis of microbial carbonate reservoirs of the fourth member of the Leikoupo Formation.

Relaxed Exponential Stabilization for Coupled Memristive Neural Networks With Connection Fault and Multiple Delays via Optimized Elastic Event-Triggered Mechanism.

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.

Mode-Dependent Adaptive Event-Triggered Control for Stabilization of Markovian Memristor-Based Reaction-Diffusion Neural Networks.

This article focuses on the design of a mode- dependent adaptive event-triggered control (AETC) scheme for the stabilization of Markovian memristor-based reaction-diffusion neural networks (RDNNs). Different from the existing works with completely known transition probabilities, partly unknown transition probabilities (PUTPs) are considered here. The switching conditions and values of memristive connection weights are all correlated with Markovian jumping. A mode-dependent AETC scheme is newly proposed, in which different adaptive event-triggered mechanisms will be applied for different Markovian jumping modes and memristor switching modes. For each given mode, the corresponding event-triggered mechanism can efficiently reduce the number of transmission signals by adaptively adjusting the threshold. Thus, the mode-dependent AETC scheme can effectively save the limited network communication resources for the considered system. Based on the proposed control scheme, a new stabilization criterion is set up for Markovian memristor-based RDNNs with PUTPs. Meanwhile, a memristor-dependent AETC scheme is devised for memristor-based RDNNs. Finally, simulation results are presented to verify the effectiveness and superiority of the analysis results.

Multiobjective Reinforcement Learning-Based Neural Architecture Search for Efficient Portrait Parsing.

This article dedicates to automatically explore efficient portrait parsing models that are easily deployed in edge computing or terminal devices. In the interest of the tradeoff between the resource cost and performance, we design the multiobjective reinforcement learning (RL)-based neural architecture search (NAS) scheme, which comprehensively balances the accuracy, parameters, FLOPs, and inference latency. Finally, under varying hyperparameter configurations, the search procedure emits a bunch of excellent objective-oriented architectures. The combination of two-stage training with precomputing and memory-resident feature maps effectively reduces the time consumption of the RL-based NAS method, so that we complete approximately 1000 search iterations in two GPU days. To accelerate the convergence of the lightweight candidate architecture, we incorporate knowledge distillation into the training of the search process. This also provides a reasonable evaluation signal to the RL controller that enables it to converge well. In the end, we conduct full training with outstanding Pareto-optimal architectures, so that a series of excellent portrait parsing models (with only approximately 0.3M parameters) is received. Furthermore, we directly transfer the architectures searched on CelebAMask-HQ (Portrait Parsing) to other portrait and face segmentation tasks. Finally, we achieve the state-of-the-art performance of 96.5% MIOU on EG1800 (portrait segmentation) and 91.6% overall F1 -score on HELEN (face labeling). That is, our models significantly surpass the artificial network on the accuracy, but with lower resource consumption and higher real-time performance.

Compact and Stable Memristive Visual Geometry Group Neural Network.

As edge computing platforms need low power consumption and small volume circuit with artificial intelligence (AI), we design a compact and stable memristive visual geometry group (MVGG) neural network for image classification. According to characteristics of matrix-vector multiplication (MVM) using memristor crossbars, we design three pruning methods named row pruning, column pruning, and parameter distribution pruning. With a loss of only 0.41% of the classification accuracy, a pruning rate of 36.87% is obtained. In the MVGG circuit, both the batch normalization (BN) layers and dropout layers are combined into the memristive convolutional computing layer for decreasing the computing amount of the memristive neural network. In order to further reduce the influence of multistate conductance of memristors on classification accuracy of MVGG circuit, the layer optimization circuit and the channel optimization circuit are designed in this article. The theoretical analysis shows that the introduction of the optimized methods can greatly reduce the impact of the multistate conductance of memristors on the classification accuracy of MVGG circuits. Circuit simulation experiments show that, for the layer-optimized MVGG circuit, when the number of multistate conductance of memristors is 25 = 32 , the optimized circuit can basically achieve an accuracy of the full-precision MVGG. For the channel-optimized MVGG circuit, when the number of multistate conductance of memristors is 22 = 4 , the optimized circuit can basically achieve an accuracy of the full-precision MVGG.

Approximate Optimal Control for Nonlinear Systems With Periodic Event-Triggered Mechanism.

This article investigates the approximate optimal control problem for nonlinear affine systems under the periodic event triggered control (PETC) strategy. In terms of optimal control, a theoretical comparison of continuous control, traditional event-based control (ETC), and PETC from the perspective of stability convergence, concluding that PETC does not significantly affect the convergence rate than ETC. It is the first time to present PETC for optimal control target of nonlinear systems. A critic network is introduced to approximate the optimal value function based on the idea of reinforcement learning (RL). It is proven that the discrete updating time series from PETC can also be utilized to determine the updating time of the learning network. In this way, the gradient-based weight estimation for continuous systems is developed in discrete form. Then, the uniformly ultimately bounded (UUB) condition of controlled systems is analyzed to ensure the stability of the designed method. Finally, two illustrative examples are given to show the effectiveness of the method.