Evolution Performance of Symbolic Radial Basis Function Neural Network by Using Evolutionary Algorithms

Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.

Nonparametric Statistical Feature Scaling Based Quadratic Regressive Convolution Deep Neural Network for Software Fault Prediction

The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.

Estimation of Weibull Distribution Parameters for Wind Speed Characteristics Using Neural Network Algorithm

Harvesting the power coming from the wind provides a green andenvironmentally friendly approach to producing electricity. To facilitate theongoing advancement in wind energy applications, deep knowledge aboutwind regime behavior is essential. Wind speed is typically characterized bya statistical distribution, and the two-parameters Weibull distribution hasshown its ability to represent wind speeds worldwide. Estimation of Weibullparameters, namely scale (c) and shape (k) parameters, is vital to describethe observed wind speeds data accurately. Yet, it is still a challenging task.Several numerical estimation approaches have been used by researchers toobtain c and k. However, utilizing such methods to characterize wind speedsmay lead to unsatisfactory accuracy. Therefore, this study aims to investigatethe performance of the metaheuristic optimization algorithm, Neural NetworkAlgorithm (NNA), in obtaining Weibull parameters and comparing itsperformance with five numerical estimation approaches. In carrying out thestudy, the wind characteristics of three sites in Saudi Arabia, namely HaferAl Batin, Riyadh, and Sharurah, are analyzed. Results exhibit that NNA hashigh accuracy fitting results compared to the numerical estimation methods.The NNA demonstrates its efficiency in optimizing Weibull parameters at allthe considered sites with correlations exceeding 98.54.

Fully Distributed Learning for Deep Random Vector Functional-Link Networks

In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.

Linearization Learning Method of BP Neural Networks

Feedforward multi layer neural networks have very strong mapping capability that is based on the non linearity of the activation function, however, the non linearity of the activation function can cause the multiple local minima on the learning error surfaces, which affect the learning rate and solving optimal weights. This paper proposes a learning method linearizing non linearity of the activation function and discusses its merits and demerits theoretically.

Study on Decision Method of Neutral Point Grounding Mode for Medium-Voltage Distribution Network

The neutral grounding mode of medium-voltage distribution network decides the reliability, overvoltage, relay protection and electrical safety. Therefore, a comprehensive consideration of the reliability, safety and economy is particularly important for the decision of neutral grounding mode. This paper proposes a new decision method of neutral point grounding mode for mediumvoltage distribution network. The objective function is constructed for the decision according the life cycle cost. The reliability of the neutral point grounding mode is taken into account through treating the outage cost as an operating cost. The safety condition of the neutral point grounding mode is preserved as the constraint condition of decision models, so the decision method can generate the most economical and reliable scheme of neutral point grounding mode within a safe limit. The example is used to verify the feasibility and effectiveness of the decision method.

Calculation method of ship collision force on bridge using artificial neural network

Ship collision on bridge is a dynamic process featured by high nonlinearity and instantaneity. Calculating ship-bridge collision force typically involves either the use of design-specification-stipulated equivalent static load, or the use of finite element method (FEM) which is more time-consuming and requires supercomputing resources. In this paper, we proposed an alternative approach that combines FEM with artificial neural network (ANN). The radial basis function neural network (RBFNN) employed for calculating the impact force in consideration of ship-bridge collision mechanics. With ship velocity and mass as the input vectors and ship collision force as the output vector, the neural networks for different network parameters are trained by the learning samples obtained from finite element simulation results. The error analyses of the learning and testing samples show that the proposed RBFNN is accurate enough to calculate ship-bridge collision force. The input-output relationship obtained by the RBFNN is essentially consistent with the typical empirical formulae. Finally, a special toolbox is developed for calculation efficiency in application using MATLAB software.

COATES GRAPH APPROACH FOR GENERATING SYMBOLIC NETWORK FUNCTION

In this paper, symbolic code matrix ,constant matrix and count matrix are defined .The first twomatrices are used to describe the elemental expression of augmented matrix and the nede admittance equa-tion is thus obtained. The third matrix is used to obtain the incoming degree matrix, and according to thematrix all the 1- factors of the Coates graph are given. By using the data code, the determinant is expandedand the same items in the expansion are merged. Thus the symbolic network function in which no term can-cellation occurs is generated.

MODIFIED DOUBLE-GRAPH DECOMPOSITION ANALYSIS FOR FINDING SYMBOLIC NETWORK FUNCTIONS

The concepts of complementary cofactor pairs, normal double-graphs and feasible torn vertex seta are introduced. By using them a decomposition theorem for first-order cofactor C(Y) is derived. Combining it with the modified double-graph method, a new decomposition analysis-modified double-graph decomposition analysis is presented for finding symbolic network functions. Its advantages are that the resultant symbolic expressions are compact and contain no cancellation terms, and its sign evaluation is very simple.

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.

Analysis of Electronic Circuits with the Signal Flow Graph Method

In this work a method called “signal flow graph (SFG)” is presented. A signal-flow graph describes a system by its signal flow by directed and weighted graph;the signals are applied to nodes and functions on edges. The edges of the signal flow graph are small processing units, through which the incoming signals are processed in a certain form. In this case, the result is sent to the outgoing node. The SFG allows a good visual inspection into complex feedback problems. Furthermore such a presentation allows for a clear and unambiguous description of a generating system, for example, a netview. A Signal Flow Graph (SFG) allows a fast and practical network analysis based on a clear data presentation in graphic format of the mathematical linear equations of the circuit. During creation of a SFG the Direct Current-Case (DC-Case) was observed since the correct current and voltage directions was drawn from zero frequency. In addition, the mathematical axioms, which are based on field algebra, are declared. In this work we show you in addition: How we check our SFG whether it is a consistent system or not. A signal flow graph can be verified by generating the identity of the signal flow graph itself, illustrated by the inverse signal flow graph (SFG−1). Two signal flow graphs are always generated from one circuit, so that the signal flow diagram already presented in previous sections corresponds to only half of the solution. The other half of the solution is the so-called identity, which represents the (SFG−1). If these two graphs are superposed with one another, so called 1-edges are created at the node points. In Boolean algebra, these 1-edges are given the value 1, whereas this value can be identified with a zero in the field algebra.

Application of Nonlinear Predictive Control Based on RBF Network Predictive Model in MCFC Plant

This paper described a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). A detailed mechanism model of output voltage of a MCFC was presented at first. However, this model was too complicated to be used in a control system. Consequently, an off line radial basis function (RBF) network was introduced to build a nonlinear predictive model. And then, the optimal control sequences were obtained by applying golden mean method. The models and controller have been realized in the MATLAB environment. Simulation results indicate the proposed algorithm exhibits satisfying control effect even when the current densities vary largely.

Localized characteristics of lump and interaction solutions to two extended Jimbo–Miwa equations

We focus on the localized characteristics of lump and interaction solutions to two extended Jimbo–Miwa equations.Based on the Hirota bilinear method and the test function method,we construct the exact solutions to the extended equations including lump solutions,lump–kink solutions,and two other types of interaction solutions,by solving the underdetermined nonlinear system of algebraic equations for associated parameters.Finally,analysis and graphical simulation are presented to show the dynamical characteristics of our solutions and the interaction behaviors are revealed.

NEW PERIODIC SOLUTIONS OF ITO'S 5th-ORDER mKdV EQUATION AND ITO'S 7th-ORDER mKdV EQUATION

Based on the modified Jocobi elliptic function expansion method and the modified extended tanh function method,a new algebraic method is presented to obtain mu ltiple travelling wave solutions for nonlinear wave equations.By using the metho d,Ito's 5th order and 7th order mKdV equations are studied in detail and more new exact Jocobi elliptic function periodic solutions are found.With modulus m→1 or m→0,these solutions degenerate into corresponding solitary wave s olutions,shock wave solutions and trigonometric function solutions.

Extended Complex tanh-Function Method and Exact Solutions to （2＋1）-Dimensional Hirota Equation

在这篇论文，一个新扩大复杂 tanh 功能方法为构造旅行波浪，非旅行的波浪，和系数函数被介绍“非线性的方程的象 soliton 一样解决方案。这个方法比复杂 tanh 功能方法更强大[混乱， Solitons 和分数维图形 20 (2004 ) 1037 ] 。丰富的新答案(2+1 ) 维的 Hirota 方程被使用这个方法和符号的计算系统枫树获得。

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.

Genetic-Chicken Swarm Algorithm for Minimizing Energy in Wireless Sensor Network

Wireless Sensor Network(WSN)technology is the real-time applica-tion that is growing rapidly as the result of smart environments.Battery power is one of the most significant resources in WSN.For enhancing a power factor,the clustering techniques are used.During the forward of data in WSN,more power is consumed.In the existing system,it works with Load Balanced Cluster-ing Method(LBCM)and provides the lifespan of the network with scalability and reliability.In the existing system,it does not deal with end-to-end delay and deliv-ery of packets.For overcoming these issues in WSN,the proposed Genetic Algo-rithm based on Chicken Swarm Optimization(GA-CSO)with Load Balanced Clustering Method(LBCM)is used.Genetic Algorithm generates chromosomes in an arbitrary method then the chromosomes values are calculated using Fitness Function.Chicken Swarm Optimization(CSO)helps to solve the complex opti-mization problems.Also,it consists of chickens,hens,and rooster.It divides the chicken into clusters.Load Balanced Clustering Method(LBCM)maintains the energy during communication among the sensor nodes and also it balances the load in the gateways.The proposed GA-CSO with LBCM improves the life-span of the network.Moreover,it minimizes the energy consumption and also bal-ances the load over the network.The proposed method outperforms by using the following metrics such as energy efficiency,ratio of packet delivery,throughput of the network,lifetime of the sensor nodes.Therefore,the evaluation result shows the energy efficiency that has achieved 83.56%and the delivery ratio of the packet has reached 99.12%.Also,it has attained linear standard deviation and reduced the end-to-end delay as 97.32 ms.

应用生成对抗网络的地震数据重建和去噪一体化方法

在实际采集过程中,受地形条件和人为因素的影响,地震数据不仅在空间上会出现采样不足或不规则的情况,而且会混入噪声,不利于后续地震数据的处理和解释。通常将重建与去噪分为两个阶段处理,这样往往会引入额外的误差。为此,文中提出了一种基于条件韦氏生成对抗网络(cWGAN)的地震数据重建去噪一体化方法,该方法研究的重点是在缺失道和噪声的混合干扰下,准确提取地震数据的有效特征。首先,以U-Net模型为基本网络结构来构建生成器模型,分级提取地震数据同相轴特征;在判别器模型中引入条件约束,引导生成器优化梯度方向。其次,建立重建和去噪误差描述模型,该模型设计了一体化损失函数,可以兼顾重建与去噪两方面的处理任务。最后,经过合成数据和实际数据测试,证明文中所提的网络模型恢复的地震数据信噪比更高且具有较强鲁棒性。

不确定电液伺服系统的时变输出约束自适应滤波控制

针对电液伺服系统位置跟踪控制中存在的输出约束和不确定性问题,提出一种基于正切型时变障碍Lyapunov函数的输出约束自适应滤波控制方法。构造具有时变约束边界的正切型时变障碍Lyapunov函数,通过时变边界函数的参数设置,使系统输出具有较好的瞬态和稳态性能;设计径向基函数(RBF)神经网络及权重自适应学习律,在线逼近由模型不确定性和未知干扰组成的复合干扰,并将逼近值用于反馈控制;采用二阶指令滤波反步法设计状态反馈控制律和误差补偿机制,避免反步设计中“计算爆炸”的问题,同时消除滤波误差,提高系统位置跟踪精度;依据Lyapunov稳定性理论证明闭环系统中所有误差信号的收敛性。仿真结果表明:系统的稳态误差在所提方法下约为3.48×10^(-8)m,相比于其他控制方法,跟踪误差始终约束在时变的约束边界内,跟踪精度和控制性能均得到提升。

基于改进残差网络的运动目标模糊图像复原方法

传统的残差网络在复原运动目标模糊图像时,在模糊程度较严重的情况下,存在特征提取不充分、噪声干扰等问题,导致恢复出的图像无法完全达到原始图像的清晰度和细节。对此,提出基于改进残差网络的运动目标模糊图像复原方法。对采集到的运动目标模糊图像,采用多损失函数融合方法改进传统残差块结构,构建编码器-解码器网络训练结构,训练损失函数,提升网络的特征学习能力。通过完成训练的网络,输出运动目标模糊图像复原结果。实验结果表明,该方法复原运动目标模糊图像的峰值信噪比高于30 dB,结构相似性高于0.9。