artificial neural network

摘要： The effect of soil nutrient content on fruit yield and fruit quality is very important.To explore the effect of soil nutrients on apple quality we investigated 200 fruit samples from 40 orchards in Feng County,Jiangsu Province.Soil mineral elements and fruit quality were measured.The effect of soil nutrient content on fruit quality was analyzed by artificial neural network(ANN)model.The results showed that the prediction accuracy was highest(R2=0.851,0.847,0.885,0.678 and 0.746)in mass per fruit(MPF),hardness(HB),soluble solids concentrations(SSC),titratable acid concentration(TA)and solid-acid ratio(SSC/TA),respectively.The sensitivity analysis of the prediction model showed that soil available P,K,Ca and Mg contents had the greatest impact on the quality of apple fruit.Response surface method(RSM)was performed to determine the optimum range of the available P,K,Ca,and Mg contents in orchards In Feng County,which were 10∼20 mg⋅kg^(−1),170∼200 mg⋅kg^(−1),1000∼1500 mg⋅kg^(−1),and 80∼200 mg⋅kg^(−1),respectively.The research also concluded that improving the content of available P and available Ca in orchard soil was crucial to improve apple fruit quality in Feng County,Jiangsu Province.

摘要： To effectively predict the mechanical dispatch reliability(MDR),the artificial neural networks method combined with aircraft operation health status parameters is proposed,which introduces the real civil aircraft operation data for verification,to improve the modeling precision and computing efficiency.Grey relational analysis can identify the degree of correlation between aircraft system health status(such as the unscheduled maintenance event,unit report event,and services number)and dispatch release and screen out themost closely related systems to determine the set of input parameters required for the prediction model.The artificial neural network using radial basis function(RBF)as a kernel function,has the best applicability in the prediction of multidimensional,small sample problems.Health status parameters of related systems are used as the input to predict the changing trend ofMDR,under the artificial neural network modeling framework.The case study collects real operation data for a certain civil aircraft over the past five years to validate the performance of the model which meets the requirements of the application.The results show that the prediction quadratic error Ep of the model reaches 6.9×10−8.That is to say,in the existing operating environment,the prediction of the number of delay&cancel events per month can be less than once.The accuracy of RBF ANN,BP ANN and GA-BP ANN are compared further,and the results show that RBF ANN has better adaptability to such multidimensional small sample problems.The efforts of this paper provide a highly efficientmethod for theMDR prediction through aircraft system health state parameters,which is a promising model to enhance the prediction and controllability of the dispatch release,providing support for the construction of the civil aircraft operation system.

摘要： Liquefaction is one of the most destructive phenomena caused by earthquakes,which has been studied in the issues of potential,triggering and hazard analysis.The strain energy approach is a common method to investigate liquefaction potential.In this study,two Artificial Neural Network(ANN)models were developed to estimate the liquefaction resistance of sandy soil based on the capacity strain energy concept(W)by using laboratory test data.A large database was collected from the literature.One group of the dataset was utilized for validating the process in order to prevent overtraining the presented model.To investigate the complex influence of fine content(FC)on liquefaction resistance,according to previous studies,the second database was arranged by samples with FC of less than 28%and was used to train the second ANN model.Then,two presented ANN models in this study,in addition to four extra available models,were applied to an additional 20 new samples for comparing their results to show the capability and accuracy of the presented models herein.Furthermore,a parametric sensitivity analysis was performed through Monte Carlo Simulation(MCS)to evaluate the effects of parameters and their uncertainties on the liquefaction resistance of soils.According to the results,the developed models provide a higher accuracy prediction performance than the previously publishedmodels.The sensitivity analysis illustrated that the uncertainties of grading parameters significantly affect the liquefaction resistance of soils.

摘要： In this work, austenitic stainless steel screws employed in a locking compression plate for veterinarian use were investigated. These types of implants are widely utilized in bone fractures healing. Two surgical screws were extracted due to the observation of slight superficial red rust colorizing on one of the screw implants, visual evidence of probable screw rusting. From the same implant, another screw was extracted simultaneously without visual evidence of rusting. In order to characterize and analyze the different behavior of both screws, the chemical composition was characterized by atomic absorption and energy dispersive X-ray spectroscopy (EDS) coupled to a scanning electron microscope (SEM). Also, the screws were studied by metallography, optical microscopy (OM), Vickers microhardness tests, and SEM analysis. On the other hand, a prospection for alloy chemical composition limits of these types of implants was performed based on the Schaeffler-Delong diagram and the ASTM F-138 standard. To analyze the effect of the chemical composition, heat treatment, microstructure, pitting resistance equivalent number (PRE) and stacking fault energy (SFE), a genetic algorithm (GA) and an artificial neural network (ANN) were used. In accordance with the elemental analysis, the surgical screws do not fulfill the ranges of the chemical composition established by the ASTM F-138 standard. Furthermore, there were found differences between the microstructures of the screws. In regard to the prospection, the results of GA and ANN support the proposed chemical composition region on the Schaeffler-Delong diagram. The corrosion failure was associated with severe plastic deformation and the presence of precipitates. The proposal can minimize the cause of failures in these types of austenitic stainless steel implants.

摘要： BACKGROUND Acute kidney injury(AKI)has serious consequences on the prognosis of patients undergoing liver transplantation.Recently,artificial neural network(ANN)was reported to have better predictive ability than the classical logistic regression(LR)for this postoperative outcome.AIM To identify the risk factors of AKI after deceased-donor liver transplantation(DDLT)and compare the prediction performance of ANN with that of LR for this complication.METHODS Adult patients with no evidence of end-stage kidney dysfunction(KD)who underwent the first DDLT according to model for end-stage liver disease(MELD)score allocation system was evaluated.AKI was defined according to the International Club of Ascites criteria,and potential predictors of postoperative AKI were identified by LR.The prediction performance of both ANN and LR was tested.RESULTS The incidence of AKI was 60.6%(n=88/145)and the following predictors were identified by LR:MELD score>25(odds ratio[OR]=1.999),preoperative kidney dysfunction(OR=1.279),extended criteria donors(OR=1.191),intraoperative arterial hypotension(OR=1.935),intraoperative massive blood transfusion(MBT)(OR=1.830),and postoperative serum lactate(SL)(OR=2.001).The area under the receiver-operating characteristic curve was best for ANN(0.81,95%confidence interval[CI]:0.75-0.83)than for LR(0.71,95%CI:0.67-0.76).The root-mean-square error and mean absolute error in the ANN model were 0.47 and 0.38,respectively.CONCLUSION The severity of liver disease,pre-existing kidney dysfunction,marginal grafts,hemodynamic instability,MBT,and SL are predictors of postoperative AKI,and ANN has better prediction performance than LR in this scenario.

摘要： Prediction of power output plays a vital role in the installation and operation of photovoltaic modules.In this paper,two photovoltaic module technologies,amorphous silicon and copper indium gallium selenide installed outdoors on the rooftop of the University of Dodoma,located at 6.5738°S and 36.2631°E in Tanzania,were used to record the power output during the winter season.The average data of ambient temperature,module temperature,solar irradiance,relative humidity,and wind speed recorded is used to predict the power output using a non-linear autoregressive artificial neural network.We consider the Levenberg-Marquardt optimization,Bayesian regularization,resilient propagation,and scaled conjugate gradient algorithms to understand their abilities in training,testing and validating the data.A comparison with reference to the performance indices:coefficient of determination,root mean square error,mean absolute percentage error,and mean absolute bias error is drawn for both modules.According to the findings of our investigation,the predicted results are in good agreement with the experimental results.All the algorithms performed better,and the predicted power out of both modules using the Bayesian regularization algorithm is observed to exhibit good processing capabilities compared to the other three algorithms that are evident from the measured performance indices.

摘要： In the present study,modified Ibarra,Medina and Krawinkler moment-rotation parameters are used for modeling the uncertainties in concrete moment frame structures.Correlations of model parameters in a component and between two structural components were considered to analyze these uncertainties.In the first step,the structural collapse responses were obtained by producing 281 samples for the uncertainties using the Latin hypercube sampling(LHS)method,considering the probability distribution of the uncertainties and performing incremental dynamic analyses.In the second step,281 new samples were produced for the uncertainties by the central composite design(CCD)method without considering the probability distribution of the uncertainties and calculating the structural collapse responses.Then,using the response surface method(RSM)and artificial neural network(ANN)for the two simulation modes,structural collapse responses were predicted.The results indicated that the collapse responses at levels of 0 to 100%obtained from the two simulations have a high correlation coefficient of 98%.This suggests that random variables can be simulated without considering the probability distribution of uncertainties,by performing uncertainty analysis to determine structural collapse responses.

摘要： Agriculture and farming are mainly dependent on weather especially in Malaysia as it received heavy rainfall throughout the years. An efficient crop or tree management system with a weather forecast needed for suitable planning of farming operation. Radial Basis Function Neural Network (RBFNN) algorithm was used in this study to predict rainfall and the main focus of this study is to analyze the factor that affects the performance of neural model. This study found that the model works better the more hidden nodes and the optimum learning rate is 0.01 with the RMSE 49% and the percentage accuracy is 57%. Besides that, it is found that the meteorology data also affect the model performance. Future research can be conducted to improve the rainfall forecast of this study and improve the tree management system.

摘要： Landslides are considered as one among many phenomena jeopardizing human beings as well as their constructions.To prevent this disastrous problem,researchers have used several approaches for landslide susceptibility modeling,for the purpose of preparing accurate maps marking landslide prone areas.Among the most frequently used approaches for landslide susceptibility mapping is the Artificial Neural Network(ANN)method.However,the effectiveness of ANN methods could be enhanced by using hybrid metaheuristic algorithms,which are scarcely applied in landslide mapping.In the current study,nine hybrid metaheuristic algorithms,genetic algorithm(GA)-ANN,evolutionary strategy(ES)-ANN,ant colony optimization(ACO)-ANN,particle swarm optimization(PSO)-ANN,biogeography based optimization(BBO)-ANN,gravitational search algorithm(GHA)-ANN,particle swarm optimization and gravitational search algorithm(PSOGSA)-ANN,grey wolves optimization(GWO)-ANN,and probability based incremental learning(PBIL)-ANN have been used to spatially predict landslide susceptibility in Algiers’Sahel,Algeria.The modeling phase was done using a database of 78 landslides collected utilizing Google Earth images,field surveys,and six conditioning factors(lithology,elevation,slope,land cover,distance to stream,and distance to road).Initially,a gamma test was used to decrease the input variable numbers.Furthermore,the optimal inputs have been modeled by the mean of hybrid metaheuristic ANN techniques and their performance was assessed through seven statistical indicators.The comparative study proves the effectiveness of the co-evolutionary PSOGSA-ANN model,which yielded higher performance in predicting landslide susceptibility compared to the other models.Sensitivity analysis using the stepby-step technique was done afterward,which revealed that the distance to the stream is the most influential factor on landslide susceptibility,followed by the slope factor which ranked second.Lithology and the distance to road have demonstrated a moderate effect on landslide susceptibility.Based on these findings,an accurate map has been designed to help land-use managers and decision-makers to mitigate landslide hazards.

摘要： The accumulation of undesirable deposits on the heat exchange surface represents a critical issue in industrial heat exchangers.Taking experimental measurements of the fouling is relatively difficult and,often,this method does not lead to precise results.To overcome these problems,in the present study,a new approach based on an Artificial Neural Network(ANN)is used to predict the fouling resistance as a function of specific measurable variables in the phosphoric acid concentration process.These include:the phosphoric acid inlet and outlet temperatures,the steam temperature,the phosphoric acid density,the phosphoric acid volume flow rate circulating in the loop.Some statistical accuracy indices are employed simultaneously to justify the interrelation between these independent variables and the fouling resistance and to select the best training algorithm allowing the determination of the optimal number of hidden neurons.In particular,the BFGS quasi-Newton back-propagation approach is found to be the most performing of the considered training algorithms.Furthermore,the best topology ANN for the shell and tube heat exchanger is obtained with a network consisting of one hidden layer with 13 neurons using a tangent sigmoid transfer function for the hidden and output layers.This model predicts the experimental values of the fouling resistance with AARD%=0.065,MSE=2.168×10^(−11),RMSE=4.656×10^(−6)and r^(2)=0.994.

摘要： In this study, the artificial neural network(ANN) and the multiple regression (MLR) model havebeen developed to predict the weight unevenness ofcotton yarn. The developed models were assessed byverifying correlation coefficient (R), mean squareerror (MSE), and mean absolute error (MAE) of testdata prediction. The results indicated that the ANNmode has better performance in comparison with thelinear regression model. The correlation coefficient ofthe ANN model is greater than that of linearregression model, whereas the MSE, MAE andMaximum error of ANN model are all lower than thatof the multiple regression model. Thus, the ANNmodel was found to be more accurate than MLRmodel and the prediction errors of ANN model waslow. Therefore, it is concluded that the ANN modelswere effectively predicting the.

摘要： In this study, the artificial neural network(ANN) and the multiple regression (MLR) model havebeen developed to predict the weight unevenness ofcotton yarn. The developed models were assessed byverifying correlation coefficient (R), mean squareerror (MSE), and mean absolute error (MAE) of testdata prediction. The results indicated that the ANNmode has better performance in comparison with thelinear regression model. The correlation coefficient ofthe ANN model is greater than that of linearregression model, whereas the MSE, MAE andMaximum error of ANN model are all lower than thatof the multiple regression model. Thus, the ANNmodel was found to be more accurate than MLRmodel and the prediction errors of ANN model waslow. Therefore, it is concluded that the ANN modelswere effectively predicting the.

摘要： In this study, the artificial neural network(ANN) and the multiple regression (MLR) model havebeen developed to predict the weight unevenness ofcotton yarn. The developed models were assessed byverifying correlation coefficient (R), mean squareerror (MSE), and mean absolute error (MAE) of testdata prediction. The results indicated that the ANNmode has better performance in comparison with thelinear regression model. The correlation coefficient ofthe ANN model is greater than that of linearregression model, whereas the MSE, MAE andMaximum error of ANN model are all lower than thatof the multiple regression model. Thus, the ANNmodel was found to be more accurate than MLRmodel and the prediction errors of ANN model waslow. Therefore, it is concluded that the ANN modelswere effectively predicting the.

摘要： In this study, the artificial neural network(ANN) and the multiple regression (MLR) model havebeen developed to predict the weight unevenness ofcotton yarn. The developed models were assessed byverifying correlation coefficient (R), mean squareerror (MSE), and mean absolute error (MAE) of testdata prediction. The results indicated that the ANNmode has better performance in comparison with thelinear regression model. The correlation coefficient ofthe ANN model is greater than that of linearregression model, whereas the MSE, MAE andMaximum error of ANN model are all lower than thatof the multiple regression model. Thus, the ANNmodel was found to be more accurate than MLRmodel and the prediction errors of ANN model waslow. Therefore, it is concluded that the ANN modelswere effectively predicting the.

摘要： A computer-based automatic recognition of is the development trend of the plant taxonomy,this paperpresents a classifier design of plant species based on artificial neural network.The experiments carried out thepreprocessing and feature extraction on the leaf images,then design three different plant species classifiers basedon the different artificial neural network models. By adjusting the parameters of the artificial neural network tomake the learning and training get the best results.Experimental results show that classifiers of plant speciesbased artificial neural network all can achieve recognition rate of more than 80%, the classification result is good,artificial neural network is feasible in plant species classification, The experimental result is a theoreticalfoundation for the further research of plant automatic classification system.

摘要： A computer-based automatic recognition of is the development trend of the plant taxonomy,this paperpresents a classifier design of plant species based on artificial neural network.The experiments carried out thepreprocessing and feature extraction on the leaf images,then design three different plant species classifiers basedon the different artificial neural network models. By adjusting the parameters of the artificial neural network tomake the learning and training get the best results.Experimental results show that classifiers of plant speciesbased artificial neural network all can achieve recognition rate of more than 80%, the classification result is good,artificial neural network is feasible in plant species classification, The experimental result is a theoreticalfoundation for the further research of plant automatic classification system.

摘要： A computer-based automatic recognition of is the development trend of the plant taxonomy,this paperpresents a classifier design of plant species based on artificial neural network.The experiments carried out thepreprocessing and feature extraction on the leaf images,then design three different plant species classifiers basedon the different artificial neural network models. By adjusting the parameters of the artificial neural network tomake the learning and training get the best results.Experimental results show that classifiers of plant speciesbased artificial neural network all can achieve recognition rate of more than 80%, the classification result is good,artificial neural network is feasible in plant species classification, The experimental result is a theoreticalfoundation for the further research of plant automatic classification system.

摘要： A computer-based automatic recognition of is the development trend of the plant taxonomy,this paperpresents a classifier design of plant species based on artificial neural network.The experiments carried out thepreprocessing and feature extraction on the leaf images,then design three different plant species classifiers basedon the different artificial neural network models. By adjusting the parameters of the artificial neural network tomake the learning and training get the best results.Experimental results show that classifiers of plant speciesbased artificial neural network all can achieve recognition rate of more than 80%, the classification result is good,artificial neural network is feasible in plant species classification, The experimental result is a theoreticalfoundation for the further research of plant automatic classification system.

摘要： Predicting the plant water quality parameters using conventional experimental techniques is a timeconsuming step and is also an obstacle in the way of efficient control of such processes. In this work，artificialneural network (ANN)and ANN&PCA (principal component analysis)hybrid model were used in order todevelop a model that was able to predict the water quality parameters，such as BOD，COD,SS，TN，TP. Here thefeed-forward back-propagation neural network (FBNN)model was chosen to model the wastewater treatmentplant，which is the South Vastewater Treatment Plant (WWTP)at Korea，Busan City. The tan-sigmoid functionwas used as activation function to transfer signal at the neural network. And the Levenberg-Marquart algorithmwas used as learning algorithm to train neural network. All the 357 data sets，which were collected from the plantduring 2005，divided into 200 data sets and other 157 data sets，were used for model training and validation,respectively. The ANN and the hybrid models for prediction of water quality parameters in the primary settlementtank (PST)effluent and secondary settlement tank (SST)effluent are presented here。

摘要： Predicting the plant water quality parameters using conventional experimental techniques is a timeconsuming step and is also an obstacle in the way of efficient control of such processes. In this work，artificialneural network (ANN)and ANN&PCA (principal component analysis)hybrid model were used in order todevelop a model that was able to predict the water quality parameters，such as BOD，COD,SS，TN，TP. Here thefeed-forward back-propagation neural network (FBNN)model was chosen to model the wastewater treatmentplant，which is the South Vastewater Treatment Plant (WWTP)at Korea，Busan City. The tan-sigmoid functionwas used as activation function to transfer signal at the neural network. And the Levenberg-Marquart algorithmwas used as learning algorithm to train neural network. All the 357 data sets，which were collected from the plantduring 2005，divided into 200 data sets and other 157 data sets，were used for model training and validation,respectively. The ANN and the hybrid models for prediction of water quality parameters in the primary settlementtank (PST)effluent and secondary settlement tank (SST)effluent are presented here。