Performance comparison of training algorithms for the estimation of B?hme abrasion resistance using neural networks

Natural stones used as floor and wall coverings are exposed to many different abrasive forces,so it is essential to choose suitable materials for wear resistance in terms of the life of the structure.The abrasion resistance of natural stones can be determined in the laboratory by applying the B?hme abrasion resistance(BAR)test.However,the direct analysis of BAR in the laboratory has disadvantages such as wasting time and energy,experimental errors,and health impacts.To eliminate these disadvantages,the estimation of BAR using artificial neural networks(ANN)was proposed.Different natural stone samples were collected from Türkiye,and uniaxial compressive strength(UCS),flexural strength(FS),water absorption rate(WA),unit volume weight(UW),effective porosity(n),and BAR tests were carried out.The outputs of these tests were gathered and a data set,consisting of a total of 105 data,was randomly divided into two groups:testing and training.In the current study,the success of three different training algorithms of Levenberg-Marquardt(LM),Bayesian regularization(BR),and scaled conjugate gradient(SCG)were compared for BAR prediction of natural stones.Statistical criteria such as coefficient of determination(R~2),mean square error(MSE),mean square error(RMSE),and mean absolute percentage error(MAPE),which are widely used and adopted in the literature,were used to determine predictive validity.The findings of the study indicated that ANN is a valid method for estimating the BAR value.Also,the LM algorithm(R~2=0.9999,MSE=0.0001,RMSE=0.0110,and MAPE=0.0487)in training and the BR algorithm(R~2=0.9896,MSE=0.0589,RMSE=0.2427,and MAPE=1.2327)in testing showed the best prediction performance.It has been observed that the proposed method is quite practical to implement.Using the artificial neural networks method will provide an advantage in similar laborintensive experimental studies.

Stochastic Computational Heuristic for the Fractional Biological Model Based on Leptospirosis

The purpose of these investigations is to find the numerical outcomes of the fractional kind of biological system based on Leptospirosis by exploiting the strength of artificial neural networks aided by scale conjugate gradient,called ANNs-SCG.The fractional derivatives have been applied to get more reliable performances of the system.The mathematical form of the biological Leptospirosis system is divided into five categories,and the numerical performances of each model class will be provided by using the ANNs-SCG.The exactness of the ANNs-SCG is performed using the comparison of the reference and obtained results.The reference solutions have been obtained by using theAdams numerical scheme.For these investigations,the data selection is performed at 82%for training,while the statics for both testing and authentication is selected as 9%.The procedures based on the recurrence,mean square error,error histograms,regression,state transitions,and correlation will be accomplished to validate the fitness,accuracy,and reliability of the ANNs-SCG scheme.

Numerical Computation of SEIR Model for the Zika Virus Spreading

The purpose of this study is to present the numerical performancesand interpretations of the SEIR nonlinear system based on the Zika virusspreading by using the stochastic neural networks based intelligent computingsolver. The epidemic form of the nonlinear system represents the four dynamicsof the patients, susceptible patients S(y), exposed patients hospitalized inhospital E(y), infected patients I(y), and recovered patients R(y), i.e., SEIRmodel. The computing numerical outcomes and performances of the systemare examined by using the artificial neural networks (ANNs) and the scaledconjugate gradient (SCG) for the training of the networks, i.e., ANNs-SCG.The correctness of the ANNs-SCG scheme is observed by comparing theproposed and reference solutions for three cases of the SEIR model to solvethe nonlinear system based on the Zika virus spreading dynamics throughthe knacks of ANNs-SCG procedure based on exhaustive experimentations.The outcomes of the ANNs-SCG algorithm are found consistently in goodagreement with standard numerical solutions with negligible errors. Moreover,the procedure’s constancy, dependability, and exactness are perceived by usingthe values of state transitions, error histogram measures, correlation, andregression analysis.

Indian stock market prediction using artificial neural networks on tick data

Introduction:Nowadays,the most significant challenges in the stock market is to predict the stock prices.The stock price data represents a financial time series data which becomes more difficult to predict due to its characteristics and dynamic nature.Case description:Support Vector Machines(SVM)and Artificial Neural Networks(ANN)are widely used for prediction of stock prices and its movements.Every algorithm has its way of learning patterns and then predicting.Artificial Neural Network(ANN)is a popular method which also incorporate technical analysis for making predictions in financial markets.Discussion and evaluation:Most common techniques used in the forecasting of financial time series are Support Vector Machine(SVM),Support Vector Regression(SVR)and Back Propagation Neural Network(BPNN).In this article,we use neural networks based on three different learning algorithms,i.e.,Levenberg-Marquardt,Scaled Conjugate Gradient and Bayesian Regularization for stock market prediction based on tick data as well as 15-min data of an Indian company and their results compared.Conclusion:All three algorithms provide an accuracy of 99.9%using tick data.The accuracy over 15-min dataset drops to 96.2%,97.0%and 98.9%for LM,SCG and Bayesian Regularization respectively which is significantly poor in comparison with that of results obtained using tick data.

Computational Stochastic Investigations for the Socio-Ecological Dynamics with Reef Ecosystems

The motive of this work is to present a computational design using the stochastic scaled conjugate gradient(SCG)neural networks(NNs)called as SCGNNs for the socio-ecological dynamics(SED)with reef ecosystems and conservation estimation.The mathematical descriptions of the SED model are provided that is dependent upon five categories,macroalgae M(v),breathing coral C(v),algal turf T(v),the density of parrotfish P(v)and the opinion of human opinion X(v).The stochastic SCGNNs process is applied to formulate the SEDmodel based on the sample statistics,testing,accreditation and training.Three different variations of the SED have been provided to authenticate the stochastic SCGNNs performance through the statics for training,accreditation,and testing are 77%,12%and 11%,respectively.The obtained numerical performances have been compared with the Runge-Kutta approach to solve the SEDmodel.The reduction of mean square error(MSE)is used to investigate the numericalmeasures through the SCGNNs for solving the SED model.The precision of the SCGNNs is validated through the comparison of the results and the absolute error performances.The reliability of the SCGNNs is performed by using the correlation values,state transitions(STs),error histograms(EHs),MSE measures and regression analysis.