Multiple linear regressions are an important tool used to find the relationship between a set of variables used in various scientific experiments. In this article we are going to introduce a simple ...method of solving a multiple rectilinear regressions (MLR) problem that uses an artificial neural network to find the accurate and expected output from MLR problem. Different artificial neural network (ANN) types with different architecture will be tested, the error between the target outputs and the calculated ANN outputs will be investigated. A recommendation of using a certain type of ANN based on the experimental results will be raised.
Display omitted
•Performance of passive still, active still, and condenser is studied.•Distilling systems are modeled by different artificial intelligence-based models.•Accumulated productivity of ...active still is improved by 53.21%.•Artificial neural network unified with Harris Hawks optimizer is the best model.•In the best model, R2 is 0.97 and 0.98 for active and passive stills, respectively.
In this paper, a new productivity prediction model of active solar still was developed depending on improving the performance of the traditional artificial neural networks using Harris Hawks Optimizer. This optimizer simulates the behavior of Harris Hawks to catch their prey, and this method is used to determine the optimal parameters of artificial neural networks. The proposed model, called Harris Hawks Optimizer – artificial neural network, is compared with two other models named support vector machine and traditional artificial neural network, in addition to the experimental-based behavior of the solar still. The models were applied to predict the yield of three different distillation systems, namely, passive solar still, active solar still, and active solar still integrated with a condenser. Experimentally, the productivity of the active distiller integrated with the condenser was increased by 53.21% at a fan speed of 1350 rpm. The performance of the models was assessed using different statistical criteria such as root mean square error, coefficient of determination, and others. Among the three models, Harris Hawks Optimizer – artificial neural network had the best accuracy in predicting the solar still yield compared with the real experimental results.
•We extended IRT with perceived novelty and socio-demographic variables.•A two-staged SEM-ANN approach was used to rank the normalized importance.•The ANN model predicts m-wallet resistance with 76.4 ...% accuracy.•Education and perceived novelty have negative effects on m-wallet resistance.•Usage, risk, value & tradition barriers have positive effects on m-wallet resistance.
The advancement in mobile technology has enabled the application of the mobile wallet or m-wallet as an innovative payment method to substitute the traditional functions of the physical wallet. However, because of pro-innovation bias, scholars have a focus on the adoption of technology and very little attention has been given to the resistance of innovation, especially in the m-wallet context. This study addressed this absence by examining the inhibitors of m-wallet innovation adoption through the lens of innovation resistance theory (IRT). By applying a sophisticated two-staged structural equation modeling-artificial neural network (SEM-ANN) approach, we successfully extended the IRT by integrating socio-demographics and perceived novelty. The study has unveiled the noncompensatory and nonlinear relationships between the predictors and m-wallet resistance. Significant predictors from SEM analysis were taken as the ANN model’s input neurons. According to the normalized importance obtained from the multilayer perceptrons of the feed-forward-back-propagation ANN algorithm, we found significant effects of education, income, usage barrier, risk barrier, value barrier, tradition barrier, and perceived novelty on m-wallet innovation resistance. The ANN model can predict m-wallet innovation resistance with an accuracy of 76.4 %. We also discussed several new and useful theoretical and practical implications for reducing m-wallet innovation resistance among consumers.
Display omitted
•The effects of nanofluid and nano-PCM cooling method was proposed and investigated.•An experimental analysis on hybrid PV/T is carried out.•The artificial neural networks is trained ...by the experimental data.•The electrical efficiency of PV/T compared with PV, is 13.32% and 8.07%, respectively.
In this paper, a Photovoltaic/Thermal (PV/T) system was proposed, built and tested. Three various types of cooling were proposed: tank filled with water and water flows through the cooling pipes, tank filled with PCM and water flows through the cooling pipes, and tank filled with PCM/nano-SiC and nanofluid (water-SiC) flows through the cooling pipes. The three proposed systems results were compared with conventional PV. According to the results, it was found that nano-PCM and nanofluid improved the electrical current from 3.69 A to 4.04, and the electrical efficiency from 8.07% to 13.32%, compared with conventional PV. In addition, three Artificial Neural Network (ANN), MLP, SOFM and SVM methods were implemented using the experimental results. The results indicate that the output of the network is in good agreement with the experimental results and published works.
•RCA percentage, cement content and slump were used as parameters to build CCD plan.•The RSM and ANN models were used for predicting compressive strength at 7, 28 and 56 days.•The prediction model ...based on ANN exhibits higher precision on the prediction compared with the RSM model.
This study aims at predicting and modeling the 7; 28 and 56 days compressive strength of a concrete containing concrete’s recycled coarse aggregates and that, for different range of cement content and slump. To achieve this, the response surface methodology (RSM) and the artificial neural networks (ANN) approaches were used for three variable processes modeling (cement content in the range of 300 to 400 kg/m3, percentage of recycled coarse aggregate from 0 to 100% and slump from 5 to 12 ± 1 cm). The results indicate that the compressive strength of recycled concrete at 7, 28 and 56 days is strongly influenced by the cement content, %RCA and slump (p < 0.01). It is found that the compressive strength at 7, 28 and 56 days decreases from 22.62 to 18.56, 34.91 to 28.70 and 37.77 to 32.26 respectively with increasing in RCA from 0 to 100% at middle levels of cement content and slump. The results in statistical terms; relative percent deviation (RDP), mean squared error (MSE), root mean square error (RMSE), determination coefficient (R2) and adjusted coefficient (R2adj), reveals that the both approaches ANN and RSM are a powerful tools for the prediction of the compressive strength. Furthermore, ANN and RSM models are very well correlated with experimental data. However, artificial neural network model shows better accuracy.
We present a deep energy method for finite deformation hyperelasticitiy using deep neural networks (DNNs). The method avoids entirely a discretization such as FEM. Instead, the potential energy as a ...loss function of the system is directly minimized. To train the DNNs, a backpropagation dealing with the gradient loss is computed and then the minimization is performed by a standard optimizer. The learning process will yield the neural network's parameters (weights and biases). Once the network is trained, a numerical solution can be obtained much faster compared to a classical approach based on finite elements for instance. The presented approach is very simple to implement and requires only a few lines of code within the open-source machine learning framework such as Tensorflow or Pytorch. Finally, we demonstrate the performance of our DNNs based solution for several benchmark problems, which shows comparable computational efficiency such as FEM solutions.
•First machine learning based solution of large deformation hyperelasticity problems.•Highly efficient method once the network is trained.•The minimization of the loss function is similar to the classical principle of minimum potential energy of finding the stationary points. .•Traction free boundary conditions are fulfilled automatically.•Lower requirement on the differentiability compared to deep collocation methods.•The constrained optimization is replaced by an unconstrained optimization problem.
Display omitted
•New hybrid decomposition and an effective ensemble learning model for wind speed time series forecasting is proposed.•The AM-FM theory combined with an ensemble of VMD and SSA-LSTM ...is an original and powerful approach presented in this paper to wind speed forecasting.•Introducing the ensemble-learning model based on VMD and SSA, showing that it acts as an effective way for achieving reliable and stable forecasting.
The intermittent nature of wind can represent an obstacle to get reliable wind speed forecasting, thus many methods were developed to improve the accuracy, due to unstable behavior patterns and the presence of noise signal. In order to overcome this issue, a preprocessing step is desirable to provide more reliable data. Decomposition strategy is reported as the crucial component of this improving task of the wind speed forecasting. It can be applied as the first step or as a recurrent process, and normally the raw wind speed data is decomposed in several signal patterns. Based on this understanding, this paper proposed a combination of two signal decomposition strategies, known as variational mode decomposition (VMD) and singular spectral analysis (SSA), with modulation signal theory. The proposed decomposition approach is further coupled with a long short-term memory neural network (LSTM), the adaptive neuro-fuzzy system (ANFIS), echo state network (ESN), support vector regression (SVR) and Gaussian regression process (GRP) models resulting in new ensemble learning approaches. All results obtained through these ensembles are compared between them and demonstrated an error stabilization behavior, ability decomposing the wind speed into uncorrelated components, reducing the errors from one up to twelve steps-ahead forecasting. In general terms, the results indicate that ensembles learning framework are robust and reliable to applications in wind speed forecasting task.
In this study, the results of forecasting of the gas demand obtained with the use of artificial neural networks are presented. Design and training of MLP (multilayer perceptron model) was carried out ...using data describing the actual natural gas consumption in Szczecin (Poland). In the model, calendar (month, day of month, day of week, hour) and weather (temperature) factors, which have a pronounced effect on gas consumption by individual consumers and small industry, were considered. The results of forecasts with the use of MLP models differing in the number of neurons in the hidden layer and in the size of the data set used in the training process were compared. MLP networks with the higher quality were used for the preparation of gas consumption forecast for the additional input data, which was not previously used in the training process. It was found that MLP 22-36-1 model can be successfully used to predict gas consumption on any day of the year and any hour of the day.
•Analysis of seasonal and diurnal variation of gas consumption by recipients.•Influence of selected calendar and weather factors on the size of gas consumption.•Design and training of MLP model for forecasting hourly demand for gas in the city.•Verification of the forecast results obtained from model developed on actual data.
•Extreme learning machine (ELM) was used to predict the compressive strength of High strength concrete.•The developed ELM model is compared with BP model.•The ELM model has good prediction accuracy ...and fast learning speed.•The results show the potential use of ELM for predicting the compressive strength.
Compressive strength is a major and significant mechanical property of concrete which is considered as one of the important parameters in many design codes and standards. Early and accurate estimation of it can save in time and cost. In this study, extreme learning machine (ELM) was used to predict the compressive strength of high-strength concrete (HSC). ELM is a relatively new method for training artificial neural networks (ANN), showing good generalization performance and fast learning speed in many regression applications. ELM model was developed using 324 data records obtained from laboratory experiments. The compressive strength was modeled as a function of five input variables: water, cement, fine aggregate, coarse aggregate, and superplasticizer. The performance of the developed ELM model was compared with that of ANN model trained by using back propagation (BP) algorithm. The simulation results show that the proposed ELM model has a strong potential for predicting the compressive strength of HSC.