Object detection is crucial in remote sensing, surveillance, and autonomous driving. Detecting small objects remains challenging due to limited pixels, redundant backgrounds, and noise from viewpoint and illumination variations. To address these, we propose ESGN-YOLO, a lightweight model with three improvements. The Efficient Feature Fusion Module (EFFM) enhances multi-scale and directional feature extraction. The Shift-Wise Convolution (SWC) Bottleneck refines fine-grained features and suppresses background redundancy. The Group Normalisation Scale Head (GNSH) further improves detection accuracy and efficiency. Experiments on VisDrone2019 and RS STOD show ESGN-YOLO achieves superior [email protected] (34.5% and 76%) with a compact size (3.7M parameters) and moderate computational cost (12.3 GFLOPs). Fast inference confirms its practicality for real-time UAV deployment and small-object detection under resource-constrained conditions.

Neuromorphic sensors offer sparse outputs with low-power consumption, but it remains limited to process their spike-based data. To address this, the photosensitive FitzHugh-Nagumo (FHN) neuronal circuit is designed, and it encodes light stimuli into distinct firing spikes. The sensor based on this neuron thus achieves low-cost, sparse-output response to brightness changes. Theoretically, the neuronal system has different periodic and chaotic solutions, which are derived by the variational approach and bifurcation analysis. The neuron energy oscillation is determined by a capacitor, an inductor and a memristor. Numerically, the photosensitive neuron exhibits approximately symmetric firing patterns with changing light stimuli, and the firing modes are effectively regulated by amplitude and offset control. Moreover, the implemented neuromorphic light sensor successfully encodes varying brightness into distinct spiking patterns. These results pave the way for developing bio-inspired, event-based systems that achieve end-to-end integration from perception to actuation.

The Iterative Closest Point (ICP) algorithm suffers from sensitivity to outliers and tendency to local optima in point cloud fine registration. In this paper, we introduce a global and robust ICP framework called Granular-Ball Iterative Closest Point with MultiKernel Correntropy (GRICP). This approach transforms the point cloud into a granular ball cloud and employs MultiKernel Correntropy (MKC) as the loss function, which is designed to smooth out the effects of noise points and provide global information for registration. Specifically, we propose a coarse-grained representation of the point cloud using the granular ball model, which adaptively captures the coarse-grained features of the data and converts the point cloud into a multi-granularity ball cloud. The normal points within each granular ball help mitigate the influence of noise points. To ensure that ICP finds the globally optimal transformation, MKC is introduced to measure the distribution of registration errors, thereby offering global insights for ICP to achieve the optimal solution. The transformations based on MKC and the granular ball cloud are then derived. Extensive experiments on both simulated and real-world datasets demonstrate that GRICP delivers superior registration performance, particularly in scenarios involving large rotation offsets, partial overlaps, and Gaussian noise.

The event camera, benefiting from its high dynamic range and low latency, provides performance gain for low-light image enhancement. Unlike frame-based cameras, it records intensity changes with extremely high temporal resolution, capturing sufficient structure information. Currently, existing event-based methods feed a frame and events directly into a single model without fully exploiting modality-specific advantages, which limits their performance. Therefore, by analyzing the role of each sensing modality, the enhancement pipeline is decoupled into two stages: visibility restoration and structure refinement. In the first stage, we design a visibility restoration network with amplitude-phase entanglement by rethinking the relationship between amplitude and phase components in Fourier space. In the second stage, a fusion strategy with dynamic alignment is proposed to mitigate the spatial mismatch caused by the temporal resolution discrepancy between two sensing modalities, aiming to refine the structure information of the image enhanced by the visibility restoration network. In addition, we utilize spatial-frequency interpolation to simulate negative samples with diverse illumination, noise and artifact degradations, thereby developing a contrastive loss that encourages the model to learn discriminative representations. Experiments demonstrate that the proposed method outperforms state-of-the-art models.

The Iterative Closest Point (ICP) method, primarily used for transformation estimation, is a crucial technique in 3D signal processing, especially for point cloud fine registration. However, traditional ICP is prone to local optima and sensitive to noise, especially when there is no good initialization. Based on the observation that registration errors typically exhibit a multimodal distribution under large rotational offsets and noisy environments, the MultiKernel Correntropy (MKC), which can estimate the registration error distribution, is introduced to provide global information for ICP. Moreover, since MKC consists of multiple Gaussian kernels, it can effectively resist most of the noise. A MultiKernel Correntropy based Iterative Closest Point (MKCICP) is proposed. Extensive experiments on both simulated and real-world datasets show that MKCICP achieves better performance compared to other related methods in challenging scenarios involving large rotational angles, low partial overlap, and high noise levels.

With the development of computer vision, the task of vision-based intrusion detection has been widely applied to various important fields such as intelligent monitoring, autonomous driving, and security. Previous vision-based intrusion detection tasks aim at detecting whetherpedestriansinvade a restricted Area-of-Interest (AoI) from a static or dynamic view. However, for real application scenarios, we need to detect whether various types of intrusion objects, not just pedestrians, intrude into the AoI of dynamic view, and the fine-grained categories of intrusion objects need to be accurately given, such a dynamic-viewmulti-category fine-grainedintrusion detection (namely MF-ID) task is important but not yet explored. In this paper, we propose a new benchmark and approach to address this task. Firstly, due to the current lack of relevant benchmark, we develop a new publicly available dataset Cityintrusion-Multicategory, conduct statistical analysis on this dataset, and design three evaluation metrics. Secondly, we propose an end-to-end framework MF-YOLOV5, with five improvements: (1) We modify YOLOV5 to make it more suitable for our task, with a lower branch for object detection and an upper branch for segmenting AoI. (2) A new multi-category fine-grained loss (MFLoss) is designed to improve the fine-grained classification capability. (3) We improve the YOLOV5 C3 modules by enhancing the ability of cross-channel interaction. (4) A detection layer for the tiny objects is integrated into the network to improve its ability of detecting tiny objects. (5) A lightweight module with bottleneck transformer is introduced to reduce the network parameters. Finally, comprehensive experiments and comparisons demonstrate the validity of the proposed approach, and MF-YOLOV5 can reach the level of current SOTA, with 97.46% Miou, 55.29% [email protected] and 42.97% MF-IDAcc. The relevant datasets and codes are available at https://ieee-dataport.org/documents/mf-id-1.Note to Practitioners—The motivation of this paper is to address the pitfall of the dynamic-view intrusion detection system. The existing methods mainly focus on pedestrian intrusion detection in dynamic view, ignoring the more practical and valuable task of multi-category fine-grained intrusion detection (MF-ID). Based on this, we propose a new benchmark and an advanced approach to meet the requirement of MF-ID task in dynamic view. Extensive experiments show that the proposed approach can not only reach promising performance but also maintain a high real-time intrusion detection speed. The proposed approach can be deployed in realistic scenes, e.g., autonomous driving, intelligent monitoring, security, and intelligent transportation management. In future research, we will explore a more comprehensive benchmark and more efficient approach for intrusion detection.

Social engineering malware, which exploits both technical and human vulnerabilities, presents challenging for individuals and organizations. However, existing studies typically focus on either technical or human vulnerabilities through case studies or questionnaires, ignoring their combined importance in mitigating such threats. This study pioneers the introduction of a mathematical model to analyze and mitigate the dynamics associated with these combined vulnerabilities. To achieve this, this study proposes an innovative framework, which integrates (a) acoupled malware-opinion dynamics modelto capture the interplay between both types of vulnerabilities, and (b) anoptimal impulse control approachto strategically mitigatingsocial engineering malware. Within this framework, we define an optimization problem, aimed at balancing control costs and malware severity. We derive theoretical conditions for optimal impulse strategies that achieve this balance and develop an iterative algorithm, the convergence and scalability of which have been empirically validated. Experimental results on three real-world social networks and synthetic scale-free networks demonstrate that our strategies consistently achieve an optimal balance by minimizing total expenses, including control costs and losses associated with malware. This finding underscores the effectiveness of routine patching and ongoing security awareness training in standard cybersecurity practices. Further experiments indicate that the strategic, early, and frequent deployment of patches in specific scenarios can effectively reduce unnecessary losses, enhancing overall cybersecurity resilience.

Self-attention mechanisms have revolutionized natural language processing and computer vision. However, in point cloud analysis, most existing methods focus on point convolution operators for feature extraction, but fail to model long-range and hierarchical dependencies. To overcome above issues, in this paper, we present PointAttention, a novel network for point cloud feature representation and propagation. Specifically, this architecture uses a two-stage Learnable Self-attention for long-range attention weights learning, which is more effective than conventional triple attention. Furthermore, it employs a Hierarchical Learnable Attention Mechanism to formulate momentous global prior representation and perform fine-grained context understanding, which enables our framework to break through the limitation of the receptive field and reduce the loss of contexts. Interestingly, we show that the proposed Learnable Self-attention is equivalent to the coupling of two Softmax attention operations while having lower complexity. Extensive experiments demonstrate that our network achieves highly competitive performance on several challenging publicly available benchmarks, including point cloud classification on ScanObjectNN and ModelNet40, and part segmentation on ShapeNet-Part.

Two types of multiweighted coupled memristive neural networks (CMNNs) with adaptive couplings are introduced in this article, and the fixed-time passivity (FXTP) and fixed-time synchronization (FXTS) of such networks are considered. First, under the developed adaptive scheme, a sufficient condition to guarantee the FXTP for multiweighted CMNNs with adaptive couplings is obtained. Second, the FXTP, fixed-time input-strict passivity and fixed-time output-strict passivity for multiweighted CMNNs with adaptive couplings and coupling delays are investigated by devising an appropriate state feedback controller. Third, applying the Lyapunov functional method, it establishes the FXTS criteria for the two kinds of networks presented. Finally, numerical examples are provided to demonstrate the effectiveness of the derived results.

In recent years, memristors have attracted much attention in the fields of nonvolatile memory, logic operation and neuromorphic computing. As a new type of two-terminal passive electronic component similar to sandwich structure, its main resistance mechanism is the formation and fracture of metal or oxygen vacancy conductive filaments. Traditional clustering algorithms own strong sensitivity to different parameter selection, including partition clustering algorithm and density clustering algorithm. In view of the non-volatile characteristics of memristor and the In-memory computing characteristics of memristive circuit, this paper designs a new memristive clustering paradigm, and further verifies the feasibility and effectiveness of the proposed analog circuit to improve the performance of clustering parameters by exploring the data mining and image segmentation problems of these two types of clustering algorithms.

Vision-based intrusion detection has many applications in life environments, e.g., security, intelligent monitoring, and autonomous driving. Previous works improve the performance of intrusion detection under unknown environments by introducing unsupervised domain adaptation (UDA) methods. However, these works do not fully fulfill the practical requirements due to the performance gap between UDA and fully supervised methods. To address the problem, we develop a new and vital active domain adaptation intrusion detection task, namely Ada-iD. Our aim is to query and annotate the most informative samples of the target domain at the lowest possible cost, striving for a balance between achieving high performance and keeping low annotation expenses. Specifically, we propose a multi-task joint active domain adaptation intrusion detection framework, namely ADAID-YOLO. It consists of a lower branch for detection and an upper branch for segmentation. Further, three effective strategies are designed to better achieve the Ada-iD task: 1) An efficient Dynamic Diffusion Pseudo-Labeling method (DDPL) is introduced to get Pseudo ground truth to help identify areas of uncertainty in segmentation. 2) An Enhanced Region Impurity and Prediction Uncertainty sampling strategy (Enhanced-RIPU) is proposed to better capture the uncertainty of the segmentation region. 3) A Multi-Element Joint sampling strategy (MEJ) is designed to calculate the uncertainty of the detection comprehensively. Finally, comprehensive experiments and comparisons are conducted on multiple dominant intrusion detection datasets. The results show that our method can outperform other classic and promising active domain adaptation methods and reach current SOTA performance, even surpassing the performance of UDA and full supervision on Normal-Foggy with only 0.1% and 10% data annotation, respectively. Available code: https://github.com/1012537710/Ada-iD.

Abstract The Echo state network (ESN) is an efficient recurrent neural network that has achieved good results in time series prediction tasks. Still, its application in time series classification tasks has yet to develop fully. In this study, we work on the time series classification problem based on echo state networks. We propose a new framework called forward echo state convolutional network (FESCN). It consists of two parts, the encoder and the decoder, where the encoder part is composed of a forward topology echo state network (FT-ESN), and the decoder part mainly consists of a convolutional layer and a max-pooling layer. We apply the proposed network framework to the univariate time series dataset UCR and compare it with six traditional methods and four neural network models. The experimental findings demonstrate that FESCN outperforms other methods in terms of overall classification accuracy. Additionally, we investigated the impact of reservoir size on network performance and observed that the optimal classification results were obtained when the reservoir size was set to 32. Finally, we investigated the performance of the network under noise interference, and the results show that FESCN has a more stable network performance compared to EMN (echo memory network).

With the rapid development of edge devices, the deployment of AI on these devices has become a focal point for researchers. Moreover, the emergence of multimodal neural networks has facilitated the development and application of brain-inspired cognitive and recognition systems. However, the limited storage and computing resources of edge devices, along with the robustness issues of computational circuits, pose significant challenges in implementing AI systems with brain-inspired recognition capabilities on edge devices. To address this, we propose a memristor-based brain-inspired recognition (MBR) system, which can mimic the brain’s information processing mechanism without additional cross-modal processing, making its behavior more akin to human responses. In addition, the proposed MBR system is implemented using the multimodal in-memory computing (IMC) framework and validated the robustness and effectiveness of the proposed system through simulation analyzing. Furthermore, the multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) tasks are implemented on the MBR system with only one single training process. The results demonstrate the proposed system achieves superior performance compared to most existing baseline methods. Lastly, since the MBR system relies on memristor-based matrix multiplication, it emerges as one of the promising solutions for edge-based brain-inspired recognition applications.

Low-light image enhancement aims to obtain a normal-light image by adjusting the illumination of a low-light image. The existing methods do not fully explore the prior information hidden in low-light images, which raises the problems of detail loss and color distortion. To alleviate these issues, we propose a multi-prior collaborative network (MPC-Net) with transformer for low-light image enhancement. It extracts the indispensable prior information to facilitate high-quality image enhancement. Specifically, a pre-trained high-level vision model is employed to extract coarse texture and structure, which is then refined through a proposed self-distillation module to obtain compact representation for texture and structure. Furthermore, we design a color branch consisting of negative residual blocks and a pyramid structure to solve for noise-free color prior, aiming to provide the enhancer with a modeling mechanism for color information. Finally, a transformer-based multi-prior fusion module is developed to aggregate the content and prior information. Extensive experiments show that the proposed MPC-Net achieves superior performance on three referenced datasets and four no-referenced datasets. Our code is available at: https://github.com/Shecyy/MPC-Net.

This article is primarily concerned with the quasi-projective synchronization phenomenon between the a leader node and response nodes of an observer-based delayed dynamical network (DDN) instead of complete synchronization because of projective functional factor and parameters mismatch. First, a novel observer-based drive-response dynamical network (DN) with time-varying discrete-distributed delays and parameters mismatch is constructed to study its synchronization phenomena by introducing projective functional factor. Then, in order to obtain the sufficient criteria of quasi-projective synchronization for this system, the special impulsive control strategies and the definition of matrix measure are introduced in this article. After that, by the different impulsive phenomena and the properties of the projective functional factor, appropriate Lyapunov functional, Cauchy matrix, and inequality techniques are used to discuss and derive quasi-projective synchronization conditions of this observer-based delayed DN. In addition, some conclusions of synchronization for special DNs models are given as corollaries. Finally, an example with one leader node and four different response nodes and its corresponding simulation figures are given to demonstrate the obtained results.

Although multiscroll attractors in dissipative chaotic systems (DCSs) have complex properties, they may be subject to reconstruction attacks in the field of information security. Conservative chaotic systems (CCSs) have no attractors and can effectively resist this danger. To obtain grid-scroll conservative chaotic flows with complex dynamical behaviors, this article proposes a symmetric sine function constrained by piecewise linear functions (Sin-PLF). Then, a 4-D Hamiltonian conservative chaotic system (HCCS) with line equilibrium and grid-scroll chaotic flows is presented by replacing the state variables with the Sin-PLF. Single-, two-, and three-directional controllable multiscroll chaotic flows are found in the system, and the stationary points of the Hamiltonian function are used to analyze the generation mechanism of these scrolls. Besides, the initial offset-boosted behavior is also found, which generates coexisting chaotic flows and coexisting quasiperiodic flows in single-, two-, and three-directions. Based on the FPGA board, the multiscroll chaotic flows in the 4-D HCCS are acquired experimentally to verify their feasibility. Finally, potential applications of the proposed grid-scroll CCS are shown through a simple pseudorandom number generator (PRNG).

A memristive stateful logic circuit can provide a non-von Neumann computing architecture for integrating computation and storage. However, the stateful logic circuit based on memristors presents challenges in terms of computational complexity, reconfigurability, crossbar array compatibility, and sneak path problems. In this article, we propose a fully memristive circuit structure, which realizes all 16 Boolean logic operations with the same circuit topology. Because of the use of the same logic variable for input and output, no additional circuitry is required for logic cascading, which is beneficial to enable complicated computing tasks. The proposed stateful logic operations are experimentally demonstrated within Cu/CuI/Pt memristor crossbar array. The application of the presented logic design is further extended to a one-transistor–one-memristor (1T1M) crossbar array, overcoming the sneak path problem. Moreover, stateful logic operations can be performed in columns, rather than solely in rows, improving the computing capability and flexibility of the 1T1M array. The feasibility and reliability of this logic design in a 1T1M array are verified using two case studies of the adder–subtractor combination and the multiplexer. Our presented logic design shows superior performance in logic completeness, computational complexity, reconfigurability, logic cascading, parallel computing, and sneak path, which opens up an avenue for next-generation in-memory computing.

Due to the ability to store data and process information, the memristor-based neuromorphic system has attracted extensive attention. Its efficient parallel computing approach allows it to implement neural networks in hardware. However, due to the limitation of the range of memristor conductance, it is difficult to represent high-precision weights in memristive neural network. During the off-chip learning, it is crucial to find an efficient weight quantization scheme and map it to the memristor array. Therefore, a hybrid weight quantization strategy that combines uniform and non-uniform quantization is proposed to overcome these problems. Specifically, the curve fitting of pulse modulation for tantalum oxide-based memristor is carried out, and the mapping rules of weights are proposed to simplify the process of reading verification. Furthermore, the hybrid quantization strategy is proposed and applied to a multilayer perceptron and a convolutional neural network , respectively. The effectiveness and robustness of the hybrid quantization scheme are verified in the MNIST dataset. Experiments show that the proposed hybrid quantization scheme can achieve 99.26% accuracy at 4 bits and tolerate 20% noise interference. The simulation results in this paper also provide an effective solution for the hardware implementation of memristive neural networks .

With the introduction of neuron coverage as a testing criterion for deep neural networks (DNNs), covering more neurons to detect more internal logic of DNNs became the main goal of many research studies. While some works had made progress, some new challenges for testing methods based on neuron coverage had been proposed, mainly as establishing better neuron selection and activation strategies influenced not only obtaining higher neuron coverage, but also more testing efficiency, validating testing results automatically, labeling generated test cases to extricate manual work, and so on. In this article, we put forward Test4Deep, an effective white-box testing DNN approach based on neuron coverage. It is based on a differential testing framework to automatically verify inconsistent DNNs' behavior. We designed a strategy that can track inactive neurons and constantly triggered them in each iteration to maximize neuron coverage. Furthermore, we devised an optimization function that guided the DNN under testing to deviate predictions between the original input and generated test data and dominated unobservable generation perturbations to avoid manually checking test oracles. We conducted comparative experiments with two state-of-the-art white-box testing methods DLFuzz and DeepXplore. Empirical results on three popular datasets with nine DNNs demonstrated that compared to DLFuzz and DeepXplore, Test4Deep, on average, exceeded by 32.87% and 35.69% in neuron coverage, while reducing 58.37% and 53.24% testing time, respectively. In the meantime, Test4Deep also produced 58.37% and 53.24% more test cases with 23.81% and 98.40% fewer perturbations. Even compared with the two highest neuron coverage strategies of DLFuzz, Test4Deep still enhanced neuron coverage by 4.34% and 23.23% and achieved 94.48% and 85.67% higher generation time efficiency. Furthermore, Test4Deep could improve the accuracy and robustness of DNNs by merging generated test cases and retraining.

Subspace learning is a popular machine learning method that has been frequently applied for gas sensor calibration; however, there are the following limitations in the latent subspace learning process: 1) the existence of data distribution differences is not considered and 2) ignoring the inherent information of the original space, such as discriminative information and structure information. To overcome these issues, we design a novel domain correction latent subspace learning (DCLSL) algorithm for gas sensor drift compensation by integrating subspace learning and domain adaptation into a unified framework in this study. First, domain correction is applied to alleviate the distribution difference before and after sensor drift by exploiting the mean distribution discrepancy criterion. Second, for better-local representation and classification results, we consider both discriminative information of the source data and structural information of the target data, revealing the intrinsic geometric structure in the latent subspace and forming a compact intraclass and interclass separated discriminative data layout. In addition, to improve the consistency of features and labels, we use a projection term, a reconstruction term, and a regularization term to simultaneously implement joint learning of the label space and the latent subspace and impose a row-sparsity constraint to enhance the model robustness to noise. Inspired by non-negative matrix factorization, we skillfully adopt multiplication update rules and thus solve the proposed optimization problem. Finally, we conduct experiments for different drift compensation tasks on two common gas sensor datasets, and the results are encouraging.

Conservative chaotic systems (CCSs) have unique advantages over dissipative chaotic systems (DCSs) in the fields of secure communication and pseudo-random number generators (PRNGs), etc. However, there are relatively fewer reports on CCSs than DCSs. To this end, this paper proposes an effective method for constructing a family of Hamiltonian conservative chaotic systems (HCCSs) by letting any three of the four sub-bodies denoted by 4D generalized Euler equations share a rotation axis. From theoretical analysis to experimental verification, one of the proposed HCCSs is studied thoroughly to demonstrate the effectiveness of this method. The example system has an infinite number of equilibrium points, which belong to either centers or saddles, resulting in hidden chaos. Besides, through the bifurcation diagram, parametric chaotic set, and Lyapunov exponent, richly dynamic behaviors related to parameters are displayed. Moreover, the 3D phase portraits verify that the Hamiltonian energy is conservative. Numerous energy-related coexisting orbits are discovered in this system, such as the coexistence of quasi-periodic orbits, chaotic orbits, and chaotic quasi-periodic orbits. Furthermore, the breadboard-based circuit is implemented to illustrate the HCCS’s physical feasibility. Finally, the PRNG based on the HCCS has excellent randomness in terms of NIST and TESTU01 test results.

Capsule network (CapsNet) is a novel neural network architecture that overcame the drawback of loss of poses and position caused in convolutional neural networks and achieves better results than convolutional neural networks in some tasks. However, CapsNet computing efficiency needs to be improved. This paper uses the lightweight network method to design the structure of the capsule network reconstruction layer and proposes a lightweight capsule network, DSC-CapsNet, which can effectively improve network computing efficiency and keep network performance. Moreover, the memristor-based circuit structure corresponding to the main operation part of DSC-CapsNet was developed to enable a high-speed method of inference. It provides a modern approach to hardware deployment in terminal applications.

The memristor-based neuromorphic computing system (NCS) with emerging storage and computing integration architecture has drawn extensive attention. Because of the unique nonvolatility and programmability, the memristor is an ideal nano-device to realize neural synapses in VLSI circuit implementation of neural networks. However, in the hardware implementation, the performance of the memristive neural network is always affected by quantization error, writing error, and conductance drift, which seriously hinders its applications in practice. In this paper, a novel weight optimization scheme combining quantization and Bayesian inference is proposed to alleviate this problem. Specifically, the weight deviation in the memristive neural network is transformed into the weight uncertainty in the Bayesian neural network, which can make the network insensitive to unexpected weight changes. A quantization regularization term is designed and utilized during the training process of the Bayesian neural network, reducing the quantization error and improving the robustness of the network. Furthermore, a partial training method is raised to extend the applicability of the proposed scheme in large-scale neural networks. Finally, the experiments on a Multilayer Perceptron and LeNet demonstrate that the proposed weight optimization scheme can significantly enhance the robustness of memristive neural networks.

Fractal and chaos are two major phenomena in nonlinear systems. A few combinations of chaos with fractal for generating multiscroll attractors are reported. Thus, based on Chua multiscroll chaotic systems, a novel multiring chaotic system is proposed via Julia multifractal processes. The main purpose of this work is to make up for the deficiency of various fractal processes to further improve the performance of chaotic systems. A new class of multiscroll attractors is generated by combining different fractal processes, including symmetrical multiring attractor, separated multiring attractor, and nested multiring attractor. Furthermore, dynamic behaviors of the fractal chaotic system are analyzed by means of Lyapunov exponents and bifurcation diagram to indicate that the system exhibits chaotic characteristics. Experiments on the spectrum entropy (SE) complexity and image encryption performance demonstrate the good performance of the proposed fractal-based attractors. To verify the feasibility of multiring chaotic system, the various fractal-based attractors generated are implemented by micro controller unit (MCU), and the separated multiring attractors are observed on the digital oscilloscope.

With the emergence of complex correntropy, the maximum complex correntropy criterion (MCCC) has been applied to the complex-domain adaptive filtering. The MCCC uses the fixed point method to find the optimal solution, which provides good robustness in the non-Gaussian noise environment, especially for the impulse noise. However, the convergence analysis for the fixed point method is limited to the real-domain filtering. In this letter, we provide the convergence analysis of fixed point based MCCC algorithm in complex-domain filtering. First, by using the matrix inversion lemma, we rewrite the MCCC algorithm to a gradient-like version. In addition, we provide two computationally efficient versions of MCCC. Then, we provide the stability analysis and obtain the excess mean square error for MCCC. Finally, simulation results confirm the correctness of the convergence analysis in this letter.

A recent surge of research on deep convolutional neural network (DCNN) has given a challenge on existing computation architecture which has the flows in speed and memory bottleneck. In the pretreatment of deep learning, mask operation is frequently used to remove noise or fetch information. However, under data-intensive conditions, applying mask frequently can put an extremely heavy memory/communication burden on computing system. An efficient substrate of DCNN for ameliorating mask operation is urgently needed. In this paper, we present a self-renewing mask circuit (SRMC) to alleviate/solve earlier problems. First, a new approach to apply mask is presented based on computation-in-memory architecture that implements high-performance processor and high-density memory in the same physical location. Second, we designed the peripheral circuit which can provide self-renewing function to further avoid the data exchange with an external space. As opposed to most other computational element, which calculates two 1-bit data, the proposed SRMC storage multibit value and calculate several of them parallel. The calculating ability of SRMC is significantly superior to those of computational element in general architectures. Moreover, mean filter and edge detector are implemented to illustrate the effectiveness and scalability of the proposed circuit. Finally, we discussed two possible methods to enhance the practicability of our scheme.

In this paper, the maximum correntropy (MC) criterion is used as the cost function in the online sequential extreme learning machine (OS-ELM) algorithm and constraint OS-ELM (COS-ELM) algorithm, generating the proposed OS-ELM based on maximum correntropy (OS-ELM-MC) and COS-ELM based on maximum correntropy (COS-ELM-MC). In comparison with OS-ELM and COS-ELM, the proposed OS-ELM-MC and COS-ELM-MC present superior performance in non-Gaussian noise environments and almost the same performance in Gaussian noise environments. As an important parameter, the hidden node number is also discussed by simulations in this paper. Simulations on the examples of Mackey-Glass (MG) chaotic time series prediction and nonlinear regression validate the efficiency of the proposed OS-ELM-MC and COS-ELM-MC.

In this brief, hybrid impulsive and adaptive feedback controllers are simultaneously exerted on a general delayed memristive neural network (MNN) model to formulate a novel impulsive controlled MNN (IMNN) model with variable delays. By means of Lyapunov-Razumikhin technique and other analytical ways, several new stability criteria of the proposed IMNN model are obtained. In addition, by choosing appropriate impulses and external inputs, the convergence speed of IMNN can be increased, which implies that its dynamic behaviors will be optimized. Finally, the effectiveness of the obtained results is illustrated by one numerical example.

The memristor has been extensively studied in electrical engineering and biological sciences as a means to compactly implement the synaptic function in neural networks. The cellular neural network (CNN) is one of the most implementable artificial neural network models and capable of massively parallel analog processing. In this paper, a novel memristive multilayer CNN (Mm-CNN) model is presented along with its performance analysis and applications. In this new CNN design, the memristor crossbar circuit acts as the synapse, which realizes one signed synaptic weight with a pair of memristors and performs the synaptic weighting compactly and linearly. Moreover, the complex weighted summation is executed in an efficient way with a proper design of Mm-CNN cell circuits. The proposed Mm-CNN has several merits, such as compactness, nonvolatility, versatility, and programmability of synaptic weights. Its performance in several image processing applications is illustrated through simulations.

In this brief, we establish a novel complex-valued memristive recurrent neural network (CVMRNN) to study its stability. As a generalization of real-valued memristive neural networks, CVMRNN can be separated into real and imaginary parts. By means of M -matrix and Lyapunov function, the existence, uniqueness, and exponential stability of the equilibrium point for CVMRNNs are investigated, and sufficient conditions are presented. Finally, the effectiveness of obtained results is illustrated by two numerical examples.

A radial basis function (RBF) neural network control algorithm can effectively improve the robotic manipulators' performance against a large amount of uncertainty. The adaptive law can be derived by using the Lyapunov method so that the stability of robotic manipulator control system and the weight self-adaptive convergence of RBF neural networks will be guaranteed. Meanwhile, system fluctuations and even overshot phenomenon under every start-up process, which are caused by the system's convergence from the given nonoptimal initial weight value to the optimal weight value, can be avoided by using memristors to remember the optimal weight after the system's first operation. According to the above analysis, this correspondence paper designs a kind of RBF neural network control algorithm based on spintronic memristors, and then analyzes its theoretical derivation process and core design idea. Finally, the system simulation model, which uses a two-link robotic manipulator as control object, is built to prove the algorithm's validity and feasibility. Simulation results show that the proposed algorithm can satisfy the effect of presupposition.

Image fusion algorithm is a key technology to eliminate noise through combining each image with different weight. Recently, convergence and convergence speed are two exiting problems which attract more and more attention. In this paper, we originally propose a image fusion algorithm based on neural network. Firstly, the linearly constrained least square(LCLS) model which can deal with image fusion problem is introduced. In addition, in order to handle LCLS model, we adopt the penalty function technique to construct a neural network. The proposed algorithm has a simpler structure and faster convergence speed. Lastly, simulation results show this fusion algorithm which has great ability to remove different noise.

A novel memristor-based hyperchaotic system is proposed and studied in this paper. The memristor is nonlinear memory element intrinsically, which has the potential application for generating complex dynamics in nonlinear circuit to reduce system power consumption and circuit size. As the non-linear part of a system, the HP memristor is introduced to a four-dimensional system. Chaotic attractors, Lyapunov exponent spectrum, Lyapunov dimension, power spectrum, Poincaré map and bifurcation with respect to various circuit parameter, are considered and observed, which together demonstrate the rich chaotic dynamical behaviors of the system. Finally, the circuit in SPICE are designed for the proposed memristive hyperchaotic system. The SPICE experimental results are consistent with the numerical simulation results, which verifies the feasibility of the memristor hyperchaotic system.

Cellular nonlinear/neural network (CNN) has been recognized as a powerful massively parallel architecture capable of solving complex engineering problems by performing trillions of analog operations per second. The memristor was theoretically predicted in the late seventies, but it garnered nascent research interest due to the recent much-acclaimed discovery of nanocrossbar memories by engineers at the Hewlett-Packard Laboratory. The memristor is expected to be co-integrated with nanoscale CMOS technology to revolutionize conventional von Neumann as well as neuromorphic computing. In this paper, a compact CNN model based on memristors is presented along with its performance analysis and applications. In the new CNN design, the memristor bridge circuit acts as the synaptic circuit element and substitutes the complex multiplication circuit used in traditional CNN architectures. In addition, the negative differential resistance and nonlinear current-voltage characteristics of the memristor have been leveraged to replace the linear resistor in conventional CNNs. The proposed CNN design has several merits, for example, high density, nonvolatility, and programmability of synaptic weights. The proposed memristor-based CNN design operations for implementing several image processing functions are illustrated through simulation and contrasted with conventional CNNs. Monte-Carlo simulation has been used to demonstrate the behavior of the proposed CNN due to the variations in memristor synaptic weights.

This paper presents a novel mathematical model for the TiO2thin-film memristor device discovered by Hewlett-Packard (HP) labs. Our proposed model considers the boundary conditions and the nonlinear ionic drift effects by using a piecewise linear window function. Four adjustable parameters associated with the window function enable the model to capture complex dynamics of a physical HP memristor. Furthermore, we realize synaptic connections by utilizing the proposed memristor model and provide an implementation scheme for a small-world multilayer neural network. Simulation results are presented to validate the mathematical model and the performance of the neural network in nonlinear function approximation.

This article addresses an iterative learning control (ILC) design for a class of linear discrete-time systems with multiple time delays. In order to improve the tracking performance, we introduce a P-type high-order iterative learning algorithm that makes use of information from several previous iterations. An initial state learning scheme is proposed to eliminate the effect of the initialization error on the final tracking error. Furthermore, we establish a sufficient condition to ensure asymptotic convergence. A simulation example is also provided to illustrate the effectiveness of the proposed result.

This paper focuses on the hybrid effects of parameter uncertainty, stochastic perturbation, and impulses on global stability of delayed neural networks. By using the Ito formula, Lyapunov function, and Halanay inequality, we established several mean-square stability criteria from which we can estimate the feasible bounds of impulses, provided that parameter uncertainty and stochastic perturbations are well-constrained. Moreover, the present method can also be applied to general differential systems with stochastic perturbation and impulses.