Estimation of Tsunami Run-up Height by Three Artificial Neural Network Methods

Tsunami ran-up height is a significant parameter for dimensions of coastal structures. In the present study, tsunami run-up heights are estimated by three different Artificial Neural Network （ANN） models, i.e. Feed Forward Back Propagation （FFBP）, Radial Basis Functions （RBF） and Generalized Regression Neural Network （GRNN）. As the input for the ANN configuration, the wave height （H） values are employed. It is shown that the tsunami ran-up height values are closely approximated with all of the applied ANN methods. The ANN estimations are slightly superior to those of the empirical equation. It can be seen that the ANN applications are especially significant in the absence of adequate number of laboratory experiments. The results also prove that the available experiment data set can be extended with ANN simulations. This may be helpful to decrease the burden of the experimental studies and to supply results for comparisons.

Simultaneous Determination of Iron and Manganese in Water Using Artificial Neural Network Catalytic Spectrophotometric Method

A new analytical method using Back-Propagation (BP) artificial neural network and kinetic spectrophotometry for simultaneous determination of iron and magnesium in tap water, the Yellow River water and seawater is established. By conditional experiments, the optimum analytical conditions and parameters are obtained. Levenberg-Marquart (L-M) algorithm is used for calculation in BP neural network. The topological structure of three-layer BP ANN network architecture is chosen as 15-16-2 (nodes). The initial value of gradient coefficient μ is fixed at 0.001 and the increase factor and reduction factor of μ take the default values of the system. The data are processed by computers with our own programs written in MATLAB 7.0. The relative standard deviation of the calculated results for iron and manganese is 2.30% and 2.67% respectively. The results of standard addition method show that for the tap water, the recoveries of iron and manganese are in the ranges of 98.0%-104.3% and 96.5%-104.5%, and the RSD is in the range of 0.23%-0.98%; for the Yellow River water (Lijin district of Shandong Province), the recoveries of iron and manganese are in the ranges of 96.0%-101.0% and 98.7%-104.2%, and the RSD is in the range of 0.13%-2.52%; for the seawater in Qingdao offshore, the recoveries of iron and manganese are in the ranges of 95.3%-104.8% and 95.3%-104.7%, and the RSD is in the range of 0.14%-2.66%. It is found that 21 common cations and anions do not interfere with the determination of iron and manganese under the optimum experimental conditions. This method exhibits good reproducibility and high accuracy in the determination of iron and manganese and can be used for the simultaneous determination of iron and manganese in tap water and natural water. By using the established ANN- catalytic spectrophotometric method, the iron and manganese concentrations of the surface seawater at 11 sites in Qingdao offshore are determined and the level distribution maps of iron and manganese are drawn.

Prediction of Superconductivity for Oxides Based on Structural Parameters and Artificial Neural Network Method

Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.

An Artificial Neural Network-Based Response Surface Method for Reliability Analyses of c-φ Slopes with Spatially Variable Soil

This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.

The application of neural networks to comprehensive prediction by seismology prediction method

BP neural networks is used to mid-term earthquake prediction in this paper. Some usual prediction parameters of seismology are used as the import units of neural networks. And the export units of neural networks is called as the character parameter W_0 describing enhancement of seismicity. We applied this method to space scanning of North China. The result shows that the mid-term anomalous zone of W_0-value usually appeared obviously around the future epicenter 1~3 years before earthquake. It is effective to mid-term prediction.

Implementation of Legendre Neural Network to Solve Time-Varying Singular Bilinear Systems

Bilinear singular systems can be used in the investigation of different types of engineering systems.In the past decade,considerable attention has been paid to analyzing and synthesizing singular bilinear systems.Their importance lies in their real world application such as economic,ecological,and socioeconomic processes.They are also applied in several biological processes,such as population dynamics of biological species,water balance,temperature regulation in the human body,carbon dioxide control in lungs,blood pressure,immune system,cardiac regulation,etc.Bilinear singular systems naturally represent different physical processes such as the fundamental law of mass action,the DC motor,the induction motor drives,the mechanical brake systems,aerial combat between two aircraft,the missile intercept problem,modeling and control of small furnaces and hydraulic rotary multimotor systems.The current research work discusses the Legendre Neural Network’s implementation to evaluate time-varying singular bilinear systems for finding the exact solution.The results were obtained from two methods namely the RK-Butcher algorithm and the Runge Kutta Arithmetic Mean(RKAM)method.Compared with the results attained from Legendre Neural Network Method for time-varying singular bilinear systems,the output proved to be accurate.As such,this research article established that the proposed Legendre Neural Network could be easily implemented in MATLAB.One can obtain the solution for any length of time from this method in time-varying singular bilinear systems.

Structural Reliability Analysis Based on Support Vector Machine and Dual Neural Network Direct Integration Method

Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.

Artificial Neural Network Method Based on Expert Knowledge and Its Application to Quantitative Identification of Potential Seismic Sources

In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.

Classifying Heart Disease in Medical Data Using Deep Learning Methods

Recent days, heart ailments assume a fundamental role in the world. The physician gives different name for heart disease, for example, cardiovascular failure, heart failure and so on. Among the automated techniques to discover the coronary illness, this research work uses Named Entity Recognition (NER) algorithm to discover the equivalent words for the coronary illness content to mine the significance in clinical reports and different applications. The Heart sickness text information given by the physician is taken for the preprocessing and changes the text information to the ideal meaning, at that point the resultant text data taken as input for the prediction of heart disease. This experimental work utilizes the NER to discover the equivalent words of the coronary illness text data and currently uses the two strategies namely Optimal Deep Learning and Whale Optimization which are consolidated and proposed another strategy Optimal Deep Neural Network (ODNN) for predicting the illness. For the prediction, weights and ranges of the patient affected information by means of chosen attributes are picked for the experiment. The outcome is then characterized with the Deep Neural Network and Artificial Neural Network to discover the accuracy of the algorithms. The performance of the ODNN is assessed by means for classification methods, for example, precision, recall and f-measure values.

Predicting the 25th solar cycle using deep learning methods based on sunspot area data

It is a significant task to predict the solar activity for space weather and solar physics. All kinds of approaches have been used to forecast solar activities, and they have been applied to many areas such as the solar dynamo of simulation and space mission planning. In this paper, we employ the long-shortterm memory(LSTM) and neural network autoregression(NNAR) deep learning methods to predict the upcoming 25 th solar cycle using the sunspot area(SSA) data during the period of May 1874 to December2020. Our results show that the 25 th solar cycle will be 55% stronger than Solar Cycle 24 with a maximum sunspot area of 3115±401 and the cycle reaching its peak in October 2022 by using the LSTM method. It also shows that deep learning algorithms perform better than the other commonly used methods and have high application value.

Data-driven fusion and fission solutions in the Hirota–Satsuma–Ito equation via the physics-informed neural networks method

Fusion and fission are two important phenomena that have been experimentally observed in many real physical models.In this paper,we investigate the two phenomena in the(2+1)-dimensional Hirota-Satsuma-Ito equation via the physics-informed neural networks(PINN)method.By choosing suitable physically constrained initial boundary conditions,the data-driven fusion and fission solutions are obtained for the first time.Dynamical behaviors and error analysis of these solutions are investigated via illustratively numerical figures,which show that good results are achieved.It is pointed out that the PINN method adopted here can be effectively used to construct the data-driven fusion and fission solutions for other nonlinear integrable equations.Based on the powerful predictive capability of the PINN method and wide applications of fusion and fission in many physical areas,it is hoped that the data-driven solutions obtained here will be helpful for experts to predict or explain related physical phenomena.

Time Series Neural Network Forecasting Methods

In this paper,the possibility and key problem to construct the neural network time series model and three time series neural network forecasting methods,that is, the nerual network nonlinear time series model,neural network multi-dimension time series models and the neural network combining predictive model,are proposed.These three methods are applied to real problems.The results show that these methods are better than the traditional one.Furthermore,the neural network compared to the traditional method,and the constructed model of intellectual information forecasting system is given.

Deep Learning Applied to Computational Mechanics:A Comprehensive Review,State of the Art,and the Classics

Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.

Fractal Solitons, Arbitrary Function Solutions, Exact Periodic Wave and Breathers for a Nonlinear Partial Differential Equation by Using Bilinear Neural Network Method

This paper extends a method, called bilinear neural network method(BNNM), to solve exact solutions to nonlinear partial differential equation. New, test functions are constructed by using this method. These test functions are composed of specific activation functions of single-layer model,specific activation functions of "2-2" model and arbitrary functions of "2-2-3" model. By means of the BNNM, nineteen sets of exact analytical solutions and twenty-four arbitrary function solutions of the dimensionally reduced p-gB KP equation are obtained via symbolic computation with the help of Maple. The fractal solitons waves are obtained by choosing appropriate values and the self-similar characteristics of these waves are observed by reducing the observation range and amplifying the partial picture. By giving a specific activation function in the single layer neural network model, exact periodic waves and breathers are obtained. Via various three-dimensional plots, contour plots and density plots,the evolution characteristic of these waves are exhibited.

A New Artificial Neural Network Method for Solving Schrodinger Equations on Unbounded Domains

The simulation for particle or soliton propagation based on linear or nonlinear Schrodinger equations on unbounded domains requires the computational domain to be bounded,and therefore,a special boundary treatment such as an absorbing boundary condition(ABC)or a perfectly matched layer(PML)is needed so that the reflections of outgoing waves at the boundary can be minimized in order to prevent the destruction of the simulation.This article presents a new artificial neural network(ANN)method for solving linear and nonlinear Schrodinger equations on unbounded domains.In particular,this method randomly selects training points only from the bounded computational space-time domain,and the loss function involves only the initial condition and the Schrodinger equation itself in the computational domainwithout any boundary conditions.Moreover,unlike standard ANNmethods that calculate gradients using expensive automatic differentiation,this method uses accurate finitedifference approximations for the physical gradients in the Schrodinger equation.In addition,a Metropolis-Hastings algorithm is implemented for preferentially selecting regions of high loss in the computational domain allowing for the use of fewer training points in each batch.As such,the present training method uses fewer training points and less computation time for convergence of the loss function as compared with the standard ANN methods.This new ANN method is illustrated using three examples.

Forecasting available parking space with largest Lyapunov exponents method

The techniques to forecast available parking space(APS) are indispensable components for parking guidance systems(PGS). According to the data collected in Newcastle upon Tyne, England, the changing characteristics of APS were studied. Thereafter, aiming to build up a multi-step APS forecasting model that provides richer information than a conventional one-step model, the largest Lyapunov exponents(largest LEs) method was introduced into PGS. By experimental tests conducted using the same dataset, its prediction performance was compared with traditional wavelet neural network(WNN) method in both one-step and multi-step processes. Based on the results, a new multi-step forecasting model called WNN-LE method was proposed, where WNN, which enjoys a more accurate performance along with a better learning ability in short-term forecasting, was applied in the early forecast steps while the Lyapunov exponent prediction method in the latter steps precisely reflect the chaotic feature in latter forecast period. The MSE of APS forecasting for one hour time period can be reduced from 83.1 to 27.1(in a parking building with 492 berths) by using largest LEs method instead of WNN and further reduced to 19.0 by conducted the new method.

A data-derived soft-sensor method for monitoring effluent total phosphorus

The effluent total phosphorus(ETP) is an important parameter to evaluate the performance of wastewater treatment process(WWTP). In this study, a novel method, using a data-derived soft-sensor method, is proposed to obtain the reliable values of ETP online. First, a partial least square(PLS) method is introduced to select the related secondary variables of ETP based on the experimental data. Second, a radial basis function neural network(RBFNN) is developed to identify the relationship between the related secondary variables and ETP. This RBFNN easily optimizes the model parameters to improve the generalization ability of the soft-sensor. Finally, a monitoring system, based on the above PLS and RBFNN, named PLS-RBFNN-based soft-sensor system, is developed and tested in a real WWTP. Experimental results show that the proposed monitoring system can obtain the values of ETP online and own better predicting performance than some existing methods.

VPVnet:A Velocity-Pressure-Vorticity Neural Network Method for the Stokes’Equations under Reduced Regularity

We present VPVnet,a deep neural network method for the Stokes’equa-tions under reduced regularity.Different with recently proposed deep learning meth-ods[40,51]which are based on the original form of PDEs,VPVnet uses the least square functional of thefirst-order velocity-pressure-vorticity(VPV)formulation([30])as loss functions.As such,onlyfirst-order derivative is required in the loss functions,hence the method is applicable to a much larger class of problems,e.g.problems with non-smooth solutions.Despite that several methods have been proposed recently to reduce the regularity requirement by transforming the original problem into a corresponding variational form,while for the Stokes’equations,the choice of approximating spaces for the velocity and the pressure has to satisfy the LBB condition additionally.Here by making use of the VPV formulation,lower regularity requirement is achieved with no need for considering the LBB condition.Convergence and error estimates have been established for the proposed method.It is worth emphasizing that the VPVnet method is divergence-free and pressure-robust,while classical inf-sup stable mixedfinite elements for the Stokes’equations are not pressure-robust.Various numerical experiments including 2D and 3D lid-driven cavity test cases are conducted to demon-strate its efficiency and accuracy.

Hierarchical Neural Networks Method for Fault Diagnosis of Large-Scale Analog Circuits

A novel hierarchical neural networks (HNNs) method for fault diagnosis of large-scale circuits is proposed. The presented techniques using neural networks(NNs) approaches require a large amount of computation for simulating various faulty component possibilities. For large scale circuits, the number of possible faults, and hence the simulations, grow rapidly and become tedious and sometimes even impractical. Some NNs are distributed to the torn sub-blocks according to the proposed torn principles of large scale circuits. And the NNs are trained in batches by different patterns in the light of the presented rules of various patterns when the DC, AC and transient responses of the circuit are available. The method is characterized by decreasing the over-lapped feasible domains of responses of circuits with tolerance and leads to better performance and higher correct classification. The methodology is illustrated by means of diagnosis examples.

Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images

As a classic deep learning target detection algorithm,Faster R-CNN(region convolutional neural network)has been widely used in high-resolution synthetic aperture radar(SAR)and inverse SAR(ISAR)image detection.However,for most common low-resolution radar plane position indicator(PPI)images,it is difficult to achieve good performance.In this paper,taking navigation radar PPI images as an example,a marine target detection method based on the Marine-Faster R-CNN algorithm is proposed in the case of complex background(e.g.,sea clutter)and target characteristics.The method performs feature extraction and target recognition on PPI images generated by radar echoes with the convolutional neural network(CNN).First,to improve the accuracy of detecting marine targets and reduce the false alarm rate,Faster R-CNN was optimized as the Marine-Faster R-CNN in five respects:new backbone network,anchor size,dense target detection,data sample balance,and scale normalization.Then,JRC(Japan Radio Co.,Ltd.)navigation radar was used to collect echo data under different conditions to build a marine target dataset.Finally,comparisons with the classic Faster R-CNN method and the constant false alarm rate(CFAR)algorithm proved that the proposed method is more accurate and robust,has stronger generalization ability,and can be applied to the detection of marine targets for navigation radar.Its performance was tested with datasets from different observation conditions(sea states,radar parameters,and different targets).