Study on the comprehensive advantage evaluation method of high-tech enterprises based on RBF artificial neural network

This paper designs an intelligent evaluation approach using a Radial Basis Function (RBF) Artificial Neural Network. We based our approach on establishing a comprehensive advantage evaluating index system that offers scientific substance for creating a development plan and the strategic management of high-tech industry and regional clusters of high-tech enterprises. Furthermore, this paper selects some typical high-tech enterprises’ data to make comprehensive training on the network system. Meanwhile, the paper chooses some enterprises as testing samples to test the method, the result of which proves that this method is truly effective. The research of this paper provides a comprehensive advantage evaluating and managing method for high-tech enterprise.

The Role and Place of Artificial Neural Network Architectures Structural Redundancy in the Input Data Prototypes and Generalization Development

Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.

Fractional Order Environmental and Economic Model Investigations Using Artificial Neural Network

The motive of these investigations is to provide the importance and significance of the fractional order(FO)derivatives in the nonlinear environmental and economic(NEE)model,i.e.,FO-NEE model.The dynamics of the NEE model achieves more precise by using the form of the FO derivative.The investigations through the non-integer and nonlinear mathematical form to define the FO-NEE model are also provided in this study.The composition of the FO-NEEmodel is classified into three classes,execution cost of control,system competence of industrial elements and a new diagnostics technical exclusion cost.The mathematical FO-NEE system is numerically studied by using the artificial neural networks(ANNs)along with the Levenberg-Marquardt backpropagation method(ANNs-LMBM).Three different cases using the FO derivative have been examined to present the numerical performances of the FO-NEE model.The data is selected to solve the mathematical FO-NEE system is executed as 70%for training and 15%for both testing and certification.The exactness of the proposed ANNs-LMBM is observed through the comparison of the obtained and the Adams-Bashforth-Moulton database results.To ratify the aptitude,validity,constancy,exactness,and competence of the ANNs-LMBM,the numerical replications using the state transitions,regression,correlation,error histograms and mean square error are also described.

APPLICATION OF HIERARCHY ARTIFICIAL NEURAL NETWORK TO EVALUATE THE EXPLOITATIONCONDITIONS OF SURFACE MINING AREA

It always adopts the direct hierarchy analysis to value the exploitation conditions of surface mining areas. This way has some unavoidable shortcomings because it is mainly under the aid of experts and it is affected by the subjective thinking of the experts. This paper puts forwards a new approach that divides the whole exploitation conditions into sixteen subsidiary systems and each subsidiary system forms a neural network system. The whole decision system of exploitation conditions of surface mining areas is composed of sixteen subsidiary neural network systems. Each neural network is practiced with the data of the worksite, which is reasonable and scientific. This way will be a new decision approach for exploiting the surface mining areas.

Which return regime induces overconfidence behavior?Artificial intelligence and a nonlinear approach

Overconfidence behavior,one form of positive illusion,has drawn considerable attention throughout history because it is viewed as the main reason for many crises.Investors’overconfidence,which can be observed as overtrading following positive returns,may lead to inefficiencies in stock markets.To the best of our knowledge,this is the first study to examine the presence of investor overconfidence by employing an artificial intelligence technique and a nonlinear approach to impulse responses to analyze the impact of different return regimes on the overconfidence attitude.We examine whether investors in an emerging stock market(Borsa Istanbul)exhibit overconfidence behavior using a feed-forward,neural network,nonlinear Granger causality test and nonlinear impulseresponse functions based on local projections.These are the first applications in the relevant literature due to the novelty of these models in forecasting high-dimensional,multivariate time series.The results obtained from distinguishing between the different market regimes to analyze the responses of trading volume to return shocks contradict those in the literature,which is the key contribution of the study.The empirical findings imply that overconfidence behavior exhibits asymmetries in different return regimes and is persistent during the 20-day forecasting horizon.Overconfidence is more persistent in the low-than in the high-return regime.In the negative interest-rate period,a high-return regime induces overconfidence behavior,whereas in the positive interest-rate period,a low-return regime induces overconfidence behavior.Based on the empirical findings,investors should be aware that portfolio gains may result in losses depending on aggressive and excessive trading strategies,particularly in low-return regimes.

Performance Evaluation for College Curriculum Teaching Reform Using Artificial Neural Network

To address the problems of poor performance evaluation and performance management of college curriculum reform,the performance evaluation method of college curriculum reform using artificial neural networks is proposed.First,the performance evaluation index system of college curriculum reform using artificial neural network technology is constructed.Second,the performance evaluation algorithm of college curriculum reform is improved,and the performance evaluation process of college curriculum reform is simplified.The experiment proves that the performance evaluationmethod of college curriculum reform using artificial neural networks has higher practicality than the traditional method and fully meets the research requirements.

Primary Frequency Control Ability Evaluation of Valve Opening in Thermal Power Units Based on Artificial Neural Network

With the development of new energy,the primary frequency control(PFC)is becoming more and more important and complicated.To improve the reliability of the PFC,an evaluation method of primary frequency control ability(PFCA)was proposed.First,based on the coupling model of the coordinated control system(CCS)and digital electro-hydraulic control system(DEH),principle and control mode of the PFC were introduced in detail.The simulation results showed that the PFC of the CCS and DEH was the most effective control mode.Then,the analysis of the CCS model and variable condition revealed the internal relationship among main steam pressure,valve opening and power.In term of this,the radial basis function(RBF)neural network was established to estimate the PFCA.Because the simulation curves fit well with the actual curves,the accuracy of the coupling model was verified.On this basis,simulation data was produced by coupling model to verify the proposed evaluation method.The low predication error of main steam pressure,power and the PFCA indicated that the method was effective.In addition,the actual data obtained from historical operation data were used to estimate the PFCA accurately,which was the strongest evidence for this method.

Development of acidophilus milk via selected probiotics &prebiotics using artificial neural network

Commercial interest in functional foods containing probiotic strains has consistently increased due to the awareness of gut health. Recent advancements are leading to development of synbiotic foods, containing prebiotics and probiotics bearing synergistic effects of the two. Thus, in present study, synbiotic acido- philus milk was developed satisfying functional dairy food properties. Different sets of milk were fermented with probiotic cultures (Lactobacillus acidophilus, Bifidobacterium bifidum, Lactobacillus casei, bioyoghurt culture) singly or in combination, and prebiotics namely inulin (I), oat fibre (O) and honey (H). Obtained 20 synbiotic samples were organoleptically tested, physico-chemically (titrable acidity percentage (TA) &pH) and microbiologically (total viable count (TVC), coliform count and yeast &mold count) analyzed. The incorporation of honey and inulin led to development of sweetened and low calorie sweetened synbiotic acidophilus milk, respectively. Incorporation of B. bifidum increased the flavour of synbiotic acidophilus milk when compared to L. acidophilus as control, where as L. casei culture showed thinner consistency in the product. Addition of prebiotic affected only the sensory scores, whereas the probiotics addition resulted in a marginal variation of pH and TA. TVC of all synbiotic acidophilus milk samples obtained were more than desirable limits for harvesting probiotic effects (】10^10 cfu/ml). Finally, a two layer feed-forward artificial neural network (ANN) was established to predict the sensory evaluation based on inputs of probiotic and prebiotic.

On Improvement of Teaching Quality for a Selected Mathematical Topic Using Artificial Neural Networks Modeling(With a Case Study)

This paper motivated and inspired by an interdisciplinary critical educational issue adopted for a research work approach. It concerned with application of realistic Artificial Neural Networks (ANNs) models integrating reading brain function with multi-sensory cognitive learning theory. Specifically, these models adopted to improve tutoring quality (academic achievement) while teaching children “how to read?” considering the analysis and evaluation of phonics methodology. Herein, quantitative analysis and evaluation of this issue performed by considering two computer aided learning (CAL) packages concerned with a specific selected mathematical topic namely: long division process. Via realistic modeling of packages using (ANNs) based upon associative memory learning paradigm. In more details, at educational field practice; both CAL packages have been applied for teaching children algorithmic steps performing long division processes. Moreover, learning performance evaluation of presented packages considers children outcomes’ achievement after tutoring for suggested Mathematical Topic either with or without associated tutor’s voice. Interestingly, statistical analysis of obtained educational case study results at children classrooms (for both applied packages) versus classical tutoring proved to be in well agreement with obtained after ANNs computer simulation results.

Interaction behavior and load sharing pattern of piled raft using nonlinear regression and LM algorithm-based artificial neural network

In the recent era,piled raft foundation(PRF)has been considered an emergent technology for offshore and onshore structures.In previous studies,there is a lack of illustration regarding the load sharing and interaction behavior which are considered the main intents in the present study.Finite element(FE)models are prepared with various design variables in a double-layer soil system,and the load sharing and interaction factors of piled rafts are estimated.The obtained results are then checked statistically with nonlinear multiple regression(NMR)and artificial neural network(ANN)modeling,and some prediction models are proposed.ANN models are prepared with Levenberg-Marquardt(LM)algorithm for load sharing and interaction factors through backpropagation technique.The factor of safety(FS)of PRF is also estimated using the proposed NMR and ANN models,which can be used for developing the design strategy of PRF.

Numerical Computational Heuristic Through Morlet Wavelet Neural Network for Solving the Dynamics of Nonlinear SITR COVID-19

The present investigations are associated with designing Morlet wavelet neural network(MWNN)for solving a class of susceptible,infected,treatment and recovered(SITR)fractal systems of COVID-19 propagation and control.The structure of an error function is accessible using the SITR differential form and its initial conditions.The optimization is performed using the MWNN together with the global as well as local search heuristics of genetic algorithm(GA)and active-set algorithm(ASA),i.e.,MWNN-GA-ASA.The detail of each class of the SITR nonlinear COVID-19 system is also discussed.The obtained outcomes of the SITR system are compared with the Runge-Kutta results to check the perfection of the designed method.The statistical analysis is performed using different measures for 30 independent runs as well as 15 variables to authenticate the consistency of the proposed method.The plots of the absolute error,convergence analysis,histogram,performancemeasures,and boxplots are also provided to find the exactness,dependability and stability of the MWNN-GA-ASA.

Design of a Computational Heuristic to Solve the Nonlinear Liénard Differential Model

In this study,the design of a computational heuristic based on the nonlinear Liénard model is presented using the efficiency of artificial neural networks(ANNs)along with the hybridization procedures of global and local search approaches.The global search genetic algorithm(GA)and local search sequential quadratic programming scheme(SQPS)are implemented to solve the nonlinear Liénard model.An objective function using the differential model and boundary conditions is designed and optimized by the hybrid computing strength of the GA-SQPS.The motivation of the ANN procedures along with GA-SQPS comes to present reliable,feasible and precise frameworks to tackle stiff and highly nonlinear differentialmodels.The designed procedures of ANNs along with GA-SQPS are applied for three highly nonlinear differential models.The achieved numerical outcomes on multiple trials using the designed procedures are compared to authenticate the correctness,viability and efficacy.Moreover,statistical performances based on different measures are also provided to check the reliability of the ANN along with GASQPS.

Modified artificial neural network model with an explicit expression to describe flow behavior and processing maps of Ti2AlNb-based superalloy

The elevated-temperature deformation behavior of Ti2AlNb superalloy was observed by isothermal compression experiments in a wide range of temperatures(950–1200°C)and strain rates(0.001–10 s^(-1)).The flow behavior is nonlinear,strongly coupled,and multivariable.The constitutive models,namely the double multivariate nonlinear regression model,artificial neural network model,and modified artificial neural network model with an explicit expression,were applied to describe the Ti2AlNb superalloy plastic deformation behavior.The comparative predictability of those constitutive models was further evaluated by considering the correlation coefficient and average absolute relative error.The comparative results show that the modified artificial network model can describe the flow stress of Ti2AlNb superalloy more accurately than the other developed constitutive models.The explicit expression obtained from the modified artificial neural network model can be directly used for finite element simulation.The modified artificial neural network model solves the problems that the double multivariate nonlinear regression model cannot describe the nonlinear,strongly coupled,and multivariable flow behavior of Ti2AlNb superalloy accurately,and the artificial neural network model cannot be embedded into the finite element software directly.However,the modified artificial neural network model is mainly dependent on the quantity of high-quality experimental data and characteristic variables,and the modified artificial neural network model has not physical meanings.Besides,the processing maps were applied to obtain the optimum processing parameters.

NONLINEAR MODELING AND CONTROLLING OF ARTIFICIAL MUSCLE SYSTEM USING NEURAL NETWORKS

The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.

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.

Quantifying the thermal damping effect in underground vertical shafts using the nonlinear autoregressive with external input(NARX) algorithm

As air descends the intake shaft, its infrastructure, lining and the strata will emit heat during the night when the intake air is cool and, on the contrary, will absorb heat during the day when the temperature of the air becomes greater than that of the strata. This cyclic phenomenon, also known as the "thermal damping effect" will continue throughout the year reducing the effect of surface air temperature variation. The objective of this paper is to quantify the thermal damping effect in vertical underground airways. A nonlinear autoregressive time series with external input(NARX) algorithm was used as a novel method to predict the dry-bulb temperature(Td) at the bottom of intake shafts as a function of surface air temperature. Analyses demonstrated that the artificial neural network(ANN) model could accurately predict the temperature at the bottom of a shaft. Furthermore, an attempt was made to quantify typical "damping coefficient" for both production and ventilation shafts through simple linear regression models. Comparisons between the collected climatic data and the regression-based predictions show that a simple linear regression model provides an acceptable accuracy when predicting the Tdat the bottom of intake shafts.

Performance Comparison of Artificial Neural Network Models for Daily Rainfall Prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network （BPN）, cascade-forward back propagation neural network （CBPN）, distributed time delay neural network （DTDNN） and nonlinear autoregressive exogenous network （NARX）, and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor （a taluk of Nilgiris）. Based on the performance analysis, NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.

Application of artificial neural networks in global climate change and ecological research:An overview

Fields that employ artificial neural networks(ANNs)have developed and expanded continuously in recent years with the ongoing development of computer technology and artificial intelligence.ANN has been adopted widely and put into practice by research-ers in light of increasing concerns over ecological issues such as global warming,frequent El Nio-Southern Oscillation(ENSO)events,and atmospheric circulation anomalies.Limitations exist and there is a potential risk for misuse in that ANN model pa-rameters require typically higher overall sensitivity,and the chosen network structure is generally more dependent upon individ-ual experience.ANNs,however,are relatively accurate when used for short-term predictions;despite global climate change re-search favoring the effects of interactions as the basis of study and the preference for long-term experimental research.ANNs remain a better choice than many traditional methods when dealing with nonlinear problems,and possesses great potential for the study of global climate change and ecological issues.ANNs can resolve problems that other methods cannot.This is especially true for situations in which measurements are difficult to conduct or when only incomplete data are available.It is anticipated that ANNs will be widely adopted and then further developed for global climate change and ecological research.

Artificial Neural Network for Combining Forecasts

This paper proposes artificial neural networks (ANN) as a tool for nonlinear combination of forecasts. In this study, three forecasting models are used for individual forecasts, and then two linear combining methods are used to compare with the ANN combining method. The comparative experiment using real--world data shows that the prediction by the ANN method outperforms those by linear combining methods. The paper suggests that the ANN combining method can be used as- an alternative to conventional linear combining methods to achieve greater forecasting accuracy.

Parameters optimization and nonlinearity analysis of grating eddy current displacement sensor using neural network and genetic algorithm

A grating eddy current displacement sensor(GECDS) can be used in a watertight electronic transducer to realize long range displacement or position measurement with high accuracy in difficult industry conditions.The parameters optimization of the sensor is essential for economic and efficient production.This paper proposes a method to combine an artificial neural network(ANN) and a genetic algorithm(GA) for the sensor parameters optimization.A neural network model is developed to map the complex relationship between design parameters and the nonlinearity error of the GECDS,and then a GA is used in the optimization process to determine the design parameter values,resulting in a desired minimal nonlinearity error of about 0.11%.The calculated nonlinearity error is 0.25%.These results show that the proposed method performs well for the parameters optimization of the GECDS.