Coupled Neural Networks Research Articles

Coupled Neural Networks and Genetic Algorithms Application in the Field of Mine Fire Extinguishing

Coupled Neural Networks and Genetic Algorithms Application in the Field of Mine Fire Extinguishing

Prediction of spatiotemporal dynamics using deep learning: Coupled neural networks of long short-terms memory, auto-encoder and physics-informed neural networks

Several classic reaction-diffusion models using partial differential equations (PDEs) have been established to elucidate the formation mechanism of vegetation patterns. However, predictive modeling of complex spatiotemporal dynamics using traditional numerical methods can be significantly challenging in many practical scenarios. Physics-Informed Neural Networks (PINNs) provide a new approach to predict the solution of PDEs. However, the generalization of PINNs is not satisfactory when pretrained PINNs is directly used in non-trained space (defined as explorations). This may be attributed to the lack of training in the time dimension. Therefore, a framework (LA-PINNs) is proposed to predict the evolutionary solution of the non-dimensional vegetation-sand model. The framework couples neural networks of Long-Short Terms Memory, Auto-Encoder and Physics-Informed Neural Networks. The predictions of LA-PINNs are much better than those of PINNs. Then we studied the effects of hyperparameters on the accuracy of predictions. Based on training in time dimension by LSTM module and pretraining for quick-training strategy, LA-PINNs can improve the accuracy of explorations.

Adaptive Fixed-time Control for Multiple Switched Coupled Neural Networks

Adaptive Fixed-time Control for Multiple Switched Coupled Neural Networks

MH-DCNet: An improved flow field prediction framework coupling neural network with physics solver

With the development of intelligent computing technology, deep learning methods have provided an efficient solution for rapid flow field prediction in computational fluid dynamics (CFD) problems. However, existing methods have limitations in handling interference among physical variables due to different data distributions, leading to a decline in prediction performance. In this paper, we propose MH-DCNet, an improved flow field prediction framework that couples a neural network with a physics solver. Specifically, to address the data distribution problem, we design a multi-head deep convolutional neural network that decouples the prediction of physical variables through multiple encoders and decoders. We also develop a hybrid loss function by introducing the mean structural similarity to better capture the complex spatial structures and distribution features of flow fields. We evaluate MH-DCNet with unseen geometries and various flow conditions. Experimental results show that MH-DCNet outperforms other advanced models in efficiency and generalization capability. It accelerates the prediction process by 2.35 times compared to the CFD method while meeting the convergence constraints.

Synchronization of Coupled Neural Networks With Constant Time-Delay Using Sampled-Data Information.

In this article, a synchronization control method is studied for coupled neural networks (CNNs) with constant time delay using sampled-data information. A distributed control protocol relying on the sampled-data information of neighboring nodes is proposed. Lyapunov functional is constructed to analyze the synchronization of CNNs with constant time delay. Using Park's integral inequality and improved free-weight matrix integral inequality, sufficient conditions are provided for CNNs to achieve synchronization with less conservatism. In addition, the maximum sampling interval is determined by transforming the sufficient conditions into an optimization problem, and an aperiodic sampling control technique is implemented to reduce the communication energy load. Finally, numerical simulations are provided to demonstrate that the proposed method is capable of achieving synchronization.

Synchronization of Intermittently Coupled Neural Networks With Coupling Delay.

In recent years, the synchronization of coupled neural networks (CNNs) has been extensively studied. However, existing results heavily rely on assuming continuous couplings, overlooking the prevalence of intermittent couplings in reality. In this article, we address for the first time the synchronization challenge posed by intermittently CNNs (ICNNs) with coupling delay. To overcome the difficulties arising from intermittent couplings, we put forward a general piecewise delay differential inequality to characterize the dynamics during both coupled intervals and decoupled intervals. Based on the proposed inequality, we establish delay-independent synchronization criteria (DISCs) for ICNNs, enabling them to tackle general coupling delay. Notably, unlike previous studies, the achievement of synchronization in our approach does not rely on external control. Furthermore, for ICNNs that synchronize only under small delays, we formulate non-linear matrix inequality (LMI)-based delay-dependent synchronization criteria (DDSCs) that are computationally efficient and do not require delay differentiability. Finally, we provide illustrative examples to demonstrate our theoretical results.

Exponential Synchronization of Coupled Neural Networks with Hybrid Delays and Stochastic Distributed Delayed Impulses

Exponential Synchronization of Coupled Neural Networks with Hybrid Delays and Stochastic Distributed Delayed Impulses

A Comprehensive Study on Image Segmentation Using Pulse-Coupled Neural Networks

Pulse-Coupled Neural Network (PCNN) operates as a matrix of neurons, each uniquely corresponding to a pixel in the image being processed. Unlike traditional neural networks, PCNN does not require any training, making it highly suitable for image segmentation tasks. However, the complexity of PCNN arises from its numerous parameters, making parameter selection a challenging endeavor. In this work, we introduce a simplified PCNN architecture that includes an automatic parameter determination method. This approach is specifically designed for binary image segmentation and has been tested on various images, yielding results with distinct and desirable features. The proposed network iterates only four times, enhancing its efficiency. During pre-processing, RGB images are converted to HSV color space, and the V component undergoes further processing. This component is first filtered using an averaging filter, followed by a sharpening filter. The parameters for the PCNN are then generated automatically, eliminating the need for manual selection and making the network highly suitable for real-time image processing. The performance of the proposed network has been verified through tests on a variety of images. Key Words: Neural Networks, Pulse Coupled Neural Networks, Image Processing

Synchronization of Neural Networks Involving Distributed-Delay Coupling: A Distributed-Delay Differential Inequalities Approach.

In this article, we address the synchronization issue for coupled neural networks (CNNs) with mixed couplings by way of the delayed impulsive control, where the delay is distributed. Particularly, mixed couplings comprise the current-state coupling and the distributed-delay coupling, where influences on network connections caused by the past information of CNNs over a certain period are considered. First, we propose a novel array of delayed impulsive differential inequalities involving distributed-delay-dependent impulses, where distributed delays can be relatively larger. Second, we apply such delayed inequalities to analyze the problem of synchronization for CNNs with two different topologies. Sufficient criteria and distributed-delay-dependent impulsive controller are derived thereby. Furthermore, using techniques of matrix decomposition, several low-dimensional criteria are set out, which are appropriate for applications of large scale CNNs. Finally, a numerical example of CNNs with both the current-state coupling and the distributed-delay coupling involving three cases, are exhibited to exemplify the validity and the efficiency of the obtained theoretical results.

Practical Fixed-Time Bipartite Synchronization of Uncertain Coupled Neural Networks Subject to Deception Attacks via Dual-Channel Event-Triggered Control.

This article investigates the practical fixed-time synchronization of uncertain coupled neural networks via dual-channel event-triggered control. Contrary to some previous studies, the bipartite synchronization of signed graphs representing cooperative and antagonistic interactions is studied. The communication channel is introduced into deception attacks, which are described by Bernoulli's stochastic variables. Based on the concept of two channels, event-triggered mechanisms are designed for sensor-to-controller and controller-to-actuator channels to reduce communication consumption and controller update consumption as much as possible. Lyapunov and comparison theories are used to derive synchronization criteria and explicit expression of settling time. An example of Chua's circuit system is presented to demonstrate the feasibility of the obtained theoretical results.

Vehicle detection in varied weather conditions using enhanced deep YOLO with complex wavelet

Traffic congestion is prevalent in many major and medium-sized cities throughout different countries in contemporary society. In traffic images, various multi-sized vehicles are tightly clustered together and obstructed from one another. Identifying vehicles in such instances is crucial for urban traffic surveillance, safety monitoring, and legal concerns but it also presents major challenges. The remarkable detection accuracy and efficiency of deep learning-based systems have led to their recent and extensive use in vehicle identification. There are significant advanced YOLO models with different backbone architectures and frameworks developed for vehicle detection. Yet, the performance of YOLO variants are facing the challenges of handling false detection against occluded and densely sophisticated scenarios. The proposed model is developed to address such types of limitations, for example; dynamic illumination, noisy images, and scale sensitivity to improve the vehicle detection rate in different traffic scenarios and varying weather conditions. The proposed study employs an improved YOLOv4 to identify moving vehicles in different lighting conditions including daylight, cloudy, rainy, and night. For hybridization, three techniques are utilized such as the Multiscale Retinex, Dual tree complex wavelet transform (DTCWT), and Pulse Coupled Neural Networks (PCNN). The DTCWT is employed for multiscale decomposition and to denoise the complex high frequency subband information, then the denoised subbands are reconstructed into a denoised image. The Multiscale retinex is utilized to reduce the halo artifacts on high-contrast edges and maintain the balance with dynamic range compression and color reproduction. The synchronizing pulse burst property of PCNN is used to detect the isolated noisy pixels and modify the detected noisy pixels. From the results it is worth noting that the developed model surpasses state-of-the-art methods in sunny, night, cloudy, and rainy modes. The proposed method using the DTCWT technique can detect the vehicles with mAP of 91.09% and 35FPS.

Event-Triggered Synchronization of Coupled Neural Networks with Reaction–Diffusion Terms

This paper focuses on the event-triggered synchronization of coupled neural networks with reaction–diffusion terms. At first, an effective event-triggered controller was designed based on time sampling. It is worth noting that the data of the controller for this type can be updated only when corresponding triggering conditions are satisfied, which can significantly reduce the communication burden of the control systems compared to other control strategies. Furthermore, some sufficient criteria were obtained to ensure the event-triggered synchronization of the considered systems through the use of an inequality techniques as well as the designed controller. Finally, the validity of the theoretical results was confirmed using numerical examples.

Lag synchronization for coupled neural networks with multistate or multiderivative couplings

In this paper, two kinds of lag synchronization for coupled neural networks (CNNs) are addressed, that is, the cases with multiple state or derivative couplings. Firstly, several lag synchronization criteria for these two CNNs are derived by selecting proper state feedback controllers. Furthermore, since external disturbances in neural network implementation should not be ignored, the impact of external disturbances on the lag synchronization for CNNs are also further investigated. Lastly, the obtained criteria are verified through two illustrative examples.

Double-layered beam shaping assembly design based on intelligent optimization method coupling neural network and genetic algorithm for BNCT

The beam shaping assembly (BSA) plays a crucial role in the facility of accelerator-based boron neutron capture therapy (AB-BNCT). The quality of the neutron beam utilized for treatment is directly influenced by the design of the BSA. However, conventional step-by-step optimization approaches often encounter challenges in achieving the global optimal solution, as they tend to converge towards local optima. To address this issue, this study proposed an intelligent optimization method that combines neural network and genetic algorithm. The proposed method was applied to optimize a double-layered BSA based on the neutron source resulting from a lithium target bombarding by a 2.8 MeV, 20 mA proton beam. The obtained optimal BSA solution parameters well met the IAEA-TECDOC-1223 report, while also exhibiting significantly higher epithermal neutron flux compared to alternative BSA designs. The performance of the epithermal neutron beam was assessed by calculating the dose distribution and clinical parameters in the Snyder head phantom. The findings suggest that this beam exhibits promising therapeutic potential for treating tumors.

Tradeoff Between Time and Energy Costs for Controlling Stochastic Coupled Neural Networks

Time cost (TC) and energy cost (EC) are two fundamental indicators for evaluating the designed protocols for controlling networked systems. Yet, the relationships of which as well as their dependence on the network topology are far from clear. In this note, we explore this problem with the stochastic synchronization of coupled neural networks. A novel controller is articulated, which switches between the linear feedback control and finite-time feedback control relying on the size of system error. Sufficient criteria for achieving stochastic synchronization are derived, and the analytical estimates of TC and EC for synchronization are further obtained. Especially, we show that a reduction in TC will lead to an increase in EC, i.e., there is a tradeoff between TC and EC. Afterward, we further report that different optimal values of the steepness exponent and control strength should be taken to minimize the total costs of time and energy with the different performance indices.

Finite-Time Synchronization and H∞ Synchronization for Coupled Neural Networks With Multistate or Multiderivative Couplings.

This article investigates the finite-time synchronization (FTS) and H∞ synchronization for two types of coupled neural networks (CNNs), that is, the cases with multistate couplings and with multiderivative couplings. By designing appropriate state feedback controllers and parameter adjustment strategies, some FTS and finite-time H∞ synchronization criteria for CNNs with multistate couplings are derived. In addition, we further consider the FTS and finite-time H∞ synchronization problems for CNNs with multiderivative couplings by utilizing state feedback control approach and selecting suitable parameter adjustment schemes. Finally, two simulation examples are given to demonstrate the effectiveness of the proposed criteria.

Finite-time synchronization for coupled neural networks with time-delay jumping coupling

The finite-time synchronization problem is studied for coupled neural networks (CNNs) with time-delay jumping coupling. Markovian switching topologies, imprecise delay models, uncertain parameters and the unavailable of topology modes are considered in this work. A mode-dependent delay with pre-known conditional probability is built to handle the imprecise delay model problem. A hidden Markov model with uncertain parameters is introduced to describe the mode mismatch problem, and an asynchronous controller is designed. Besides, a set of Bernoulli processes models the random packet dropouts during data communication. Based on Markovian switching topologies, mode-dependent delays, uncertain probabilities and packet dropout, a sufficient condition that guarantees the CNNs reach finite-time synchronization (FTS) is derived. Finally, a numerical example is derived to demonstrate the efficiency of the proposed synchronous technique.

Synchronization in Coupled Neural Networks With Hybrid Delayed Impulses: Average Impulsive Delay-Gain Method.

In this article, we propose a new concept called average impulsive delay-gain (AIDG) for studying the synchronization of coupled neural networks (CNNs). Based on the viewpoints of impulsive control and impulsive perturbation, we establish some globally exponential synchronization criteria for CNNs. Our methods are well-suited for addressing the synchronization problems of systems subject to hybrid delayed impulses with time-varying impulsive delay and gain. Moreover, we prove that the AIDG has both positive and negative effects on synchronization. Compared to existing research, our conclusions are more applicable and less conservative as the considered hybrid delayed impulses involve more flexible cases. Finally, we validate the effectiveness of our proposed results by applying them to small-world and scale-free network models.

Irrigation Zone Delineation by Coupling Neural Networks with Spatial Statistics

Variable rate irrigation (VRI) seeks to increase the efficiency of irrigation by spatially adjusting water output within an agricultural field. Central to the success of VRI technology is establishing homogeneous irrigation zones. In this research, we propose a fusion of statistical modeling and deep learning by using artificial neural networks to map irrigation zones from simple-to-measure predictors. We further couple our neural network model with spatial correlation to capture smooth variations in the irrigation zones. We demonstrate the effectiveness of our model to define irrigation zones for a farm of winter wheat crop in Rexburg, Idaho.

Synchronization of Time-Delay Coupled Neural Networks With Stabilizing Delayed Impulsive Control.

This brief studies the distributed synchronization of time-delay coupled neural networks (NNs) with impulsive pinning control involving stabilizing delays. A novel differential inequality is proposed, where the state's past information at impulsive time is effectively extracted and used to handle the synchronization of coupled NNs. Based on this inequality, the restriction that the size of impulsive delay is always limited by the system delay is removed, and the upper bound on the impulsive delay is relaxed, which is improved the existing related results. By using the methods of average impulsive interval (AII) and impulsive delay, some relaxed criteria for distributed synchronization of time-delay coupled NNs are obtained. The proposed synchronization conditions do not impose on the upper bound of two consecutive impulsive signals, and the lower bound is more flexible. Moreover, our results reveal that the impulsive delays may contribute to the synchronization of time-delay systems. Finally, typical networks are presented to illustrate the advantage of our delayed impulsive control method.