Application of feedforward neural network in the study of dissociated gas flow along the porous wall

This paper concerns the use of feedforward neural networks (FNN) for predicting the nondimensional velocity of the gas that flows along a porous wall. The numerical solution of partial differential equations that govern the fluid flow is applied for training and testing the FNN. The equations were solved using finite differences method by writing a FORTRAN code. The Levenberg–Marquardt algorithm is used to train the neural network. The optimal FNN architecture was determined. The FNN predicted values are in accordance with the values obtained by the finite difference method (FDM). The performance of the neural network model was assessed through the correlation coefficient (r), mean absolute error (MAE) and mean square error (MSE). The respective values of r, MAE and MSE for the testing data are 0.9999, 0.0025 and 1.9998 · 10^?5.     

基于最大偏差相似性准则的BP神经网络短期电力负荷预测算法

针对企业电力负荷随机性强、稳定性低、预测精度不理想等问题,提出了一种基于最大偏差相似性准则的BP神经网络短期电力负荷预测算法。首先对最大偏差相似性准则算法进行修改,并提出使用预测日的负荷特征向量与最大偏差相似性准则算法聚类之后的类中心负荷特征的距离来确定预测日的相似日类别;然后将聚类后的相似日类别负荷数据作为BP网络的训练数据,输出预测日起始的连续三天96整点负荷值。实验表明,该方法提出的短期电力负荷预测方法在精度和网络训练时间上都有较大的提升,具有较高的有效性和实用性。     

Modelling of residual stresses in the shot peened material C-1020 by artificial neural network

This study consists of two cases: (i) The experimental analysis: Shot peening is a method to improve the resistance of metal pieces to fatigue by creating regions of residual stress. In this study, the residual stresses induced in steel specimen type C-1020 by applying various strengths of shot peening, are investigated using the electrochemical layer removal method. The best result is obtained using 0.26 mm A peening strength and the stress encountered in the shot peened material is ?276 MPa, while the maximum residual stress obtained is ?363 MPa at a peening strength of 0.43 mm A. (ii) The mathematical modelling analysis: The use of ANN has been proposed to determine the residual stresses based on various strengths of shot peening using results of experimental analysis. The back-propagation learning algorithm with two different variants and logistic sigmoid transfer function were used in the network. In order to train the neural network, limited experimental measurements were used as training and test data. The best fitting training data set was obtained with four neurons in the hidden layer, which made it possible to predict residual stress with accuracy at least as good as that of the experimental error, over the whole experimental range. After training, it was found the R² values are 0.996112 and 0.99896 for annealed before peening and shot peened only, respectively. Similarly, these values for testing data are 0.995858 and 0.999143, respectively. As seen from the results of mathematical modelling, the calculated residual stresses are obviously within acceptable uncertainties.     

Infrared thermometer sensor dynamic error compensation using Hammerstein neural network

A novel dynamic neural network structure based on Hammerstein model is proposed and applied to dynamic error compensation for infrared thermometer sensor in this paper. First, the devices of dynamic calibration for infrared thermometer sensor are designed and the calibration experiments with continuous excitation are carried out. Then, the non-linear inverse system of the sensor dynamic compensator is expressed by a non-linear static subunit followed by a linear dynamic subunit—Hammerstein model. A novel neural network structure is designed, the weights in which are corresponding with the parameters of Hammerstein model. Finally, The iterative algorithm is derived, through which the non-linear static and linear dynamic subunit in Hammerstein model can be optimised and the coefficients of the dynamic compensator are gotten. The dynamic calibration data of the uIRt/c sensor are used to test and the experiment results show that the stabilizing time of the sensor is reduced less than 6 ms from 26 ms and the dynamic characteristic is obviously improved after compensation.     

A neural network theory for constrained optimization

A variety of real-world problems can be formulated into continuous optimization problems with constraint equalities. The real-world problem here can include, for example, the traveling salesman problem, the Dido’s isoperimetric problem, the Hitchcock’s transportation problem, the network flow problem and the associative memory problem. In spite of the significance, there has not yet been developed any robust solving method that works efficiently across a broad spectrum of optimization problems. The recent Hopfield’s neural network method to solve the traveling salesman problem is a potentially promising candidate because of the efficiency due to its parallel processing. His method, however, has certain drawbacks that must be removed away before it can be qualified for an efficient, robust solving method. That is: (a) locally minimum solutions instead of globally minimum; (b) possible infeasible solutions; (c) heuristic choice of network parameters and an initial state; (d) quadratic objective functions instead of arbitrary nonlinear objective functions with arbitrary nonlinear equality constraints; and (e) unorganized mathematical formulation of the network for extension. This paper develops from the Hopfield method an efficient, robust network solving method of the continuous optimization problem with constraint equalities that resolves all the drawbacks except for (a) that has already been resolved by others. The development is mathematically rigorous and thus constitutes a solid foundation of a neural network theory for constrained optimization.     

Continuous blood pressure estimation based on multiple parameters from eletrocardiogram and photoplethysmogram by Back-propagation neural network

The cuff-less continuous blood pressure monitoring provides reliable and invaluable information about the individuals’ health condition. Conventional sphygmomanometer with a cuff measures only the value of the blood pressure intermittently and the measurement process is sometimes inconvenient. In this work, a systematic approach with multi-parameter fusion has been proposed to estimate the non-invasive beat-to-beat systolic and diastolic blood pressure with high accuracy. The methods involve real-time monitoring of the electrocardiogram (ECG) and photoplethysmogram (PPG), and extracting the R peak from the ECG and relevant feature parameters from the synchronous PPG. Also, it covers the creation of the topological model of back-propagation neural network that has fifteen neurons in the input layer, ten neurons in the single interlayer, and two neurons in the output layer, where all the neurons are fully connected. As for the results, the proposed method was validated on the volunteers. The reference blood pressure (BP) is from Finometer (MIDI, Finapres Medical System, Netherlands). The results showed that the mean ± S.D. for the estimated systolic BP (SBP) and diastolic BP (DBP) with the proposed method against reference were −0.41 ± 2.02 mmHg and 0.46 ± 2.21 mmHg, respectively. Thus, the continuous blood pressure algorithm based on Back-Propagation neural network provides a continuous BP with a high accuracy.     

Human lower extremity joint moment prediction: A wavelet neural network approach

Joint moment is one of the most important factors in human gait analysis. It can be calculated using multi body dynamics but might not be straight forward. This study had two main purposes; firstly, to develop a generic multi-dimensional wavelet neural network (WNN) as a real-time surrogate model to calculate lower extremity joint moments and compare with those determined by multi body dynamics approach, secondly, to compare the calculation accuracy of WNN with feed forward artificial neural network (FFANN) as a traditional intelligent predictive structure in biomechanics.To aim these purposes, data of four patients walked with three different conditions were obtained from the literature. A total of 10 inputs including eight electromyography (EMG) signals and two ground reaction force (GRF) components were determined as the most informative inputs for the WNN based on the mutual information technique. Prediction ability of the network was tested at two different levels of inter-subject generalization. The WNN predictions were validated against outputs from multi body dynamics method in terms of normalized root mean square error (NRMSE (%)) and cross correlation coefficient (ρ).Results showed that WNN can predict joint moments to a high level of accuracy (NRMSE < 10%, ρ > 0.94) compared to FFANN (NRMSE < 16%, ρ > 0.89). A generic WNN could also calculate joint moments much faster and easier than multi body dynamics approach based on GRFs and EMG signals which released the necessity of motion capture. It is therefore indicated that the WNN can be a surrogate model for real-time gait biomechanics evaluation.     

Improving the accuracy of prediction of PM10 pollution by the wavelet transformation and an ensemble of neural predictors

The paper presents the application of wavelet transformation and neural network ensemble to the accurate forecasting of the daily average concentration of particulate matter of diameter up to 10 μm (PM₁₀). Few neural predictors are applied: the multilayer perceptron, radial basis function, Elman network and support vector machine as well as one linear ARX model. They are used for prediction in combination with wavelet decomposition, forming many individual prediction results that will be combined in an ensemble. The important role in presented approach fulfills the wavelet transformation and the integration of this ensemble. We have proposed solution applying the additional neural network responsible for the final forecast (integration of all particular prediction results). The numerical experiments for prediction of the daily concentration of the PM₁₀ pollution in Warsaw are presented. They have shown good overall accuracy of prediction in terms of all investigated measures of quality.     

An expert system for detection of breast cancer based on association rules and neural network

This paper presents an automatic diagnosis system for detecting breast cancer based on association rules (AR) and neural network (NN). In this study, AR is used for reducing the dimension of breast cancer database and NN is used for intelligent classification. The proposed AR + NN system performance is compared with NN model. The dimension of input feature space is reduced from nine to four by using AR. In test stage, 3-fold cross validation method was applied to the Wisconsin breast cancer database to evaluate the proposed system performances. The correct classification rate of proposed system is 95.6%. This research demonstrated that the AR can be used for reducing the dimension of feature space and proposed AR + NN model can be used to obtain fast automatic diagnostic systems for other diseases.     

基于卷积长短时记忆网络的CPI预测

针对消费价格指数(CPI)的预测值滞后于真实值的现象,提出一种基于卷积神经网络-长短期记忆(CNN-LSTM)深度网络的CPI预测模型,预测结果相较于传统方法有较小的均方根误差和平均绝对百分比误差,且预测结果的定向精度和Pearson相关系数显著高于传统方法.用卷积神经网络-长短期记忆深度网络学习期货数据的空间特征和时...     

Investigation on thermal performance calculation of two type solar air collectors using artificial neural network

In this study, two types of solar air collectors are constructed and examined experimentally. The types are called as zigzagged absorber surface type and flat absorber surface type called Model I and Model II respectively. Experiments are carried out between 10.00 and 17.00 h in August and September under the prevailing weather conditions of Karabuk (city of the Turkey) for 5 days. Then, thermal performances belongs to experimental systems are calculated by using data obtained from experiments. To estimate thermal performances of solar air collectors an artificial neural network (ANN) model is designed. The measured data and calculated performance values are used at the design of Levenberg–Marquardt (LM) based multi-layer perceptron (MLP) in Matlab nftool module. Calculated values of thermal performances are compared to predicted values. Statistical error analysis is used to evaluate results. Comparing and statistical results demonstrate effectiveness of the proposed ANN. Also reliability of ANN and meaningfulness of input variables are tested via applying stepwise regression method to the data used in designing ANN.     

Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff

This study investigated the effects of upstream stations’ flow records on the performance of artificial neural network (ANN) models for predicting daily watershed runoff. As a comparison, a multiple linear regression (MLR) analysis was also examined using various statistical indices. Five streamflow measuring stations on the Cahaba River, Alabama, were selected as case studies. Two different ANN models, multi layer feed forward neural network using Levenberg–Marquardt learning algorithm (LMFF) and radial basis function (RBF), were introduced in this paper. These models were then used to forecast one day ahead streamflows. The correlation analysis was applied for determining the architecture of each ANN model in terms of input variables. Several statistical criteria (RMSE, MAE and coefficient of correlation) were used to check the model accuracy in comparison with the observed data by means of K-fold cross validation method. Additionally, residual analysis was applied for the model results. The comparison results revealed that using upstream records could significantly increase the accuracy of ANN and MLR models in predicting daily stream flows (by around 30%). The comparison of the prediction accuracy of both ANN models (LMFF and RBF) and linear regression method indicated that the ANN approaches were more accurate than the MLR in predicting streamflow dynamics. The LMFF model was able to improve the average of root mean square error (RMSE_ave) and average of mean absolute percentage error (MAPE_ave) values of the multiple linear regression forecasts by about 18% and 21%, respectively. In spite of the fact that the RBF model acted better for predicting the highest range of flow rate (flood events, RMSE_ave/RBF = 26.8 m³/s vs. RMSE_ave/LMFF = 40.2 m³/s), in general, the results suggested that the LMFF method was somehow superior to the RBF method in predicting watershed runoff (RMSE/LMFF = 18.8 m³/s vs. RMSE/RBF = 19.2 m³/s). Eventually, statistical differences between measured and predicted medians were evaluated using Mann-Whitney test, and differences in variances were evaluated using the Levene's test.     

Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals

The aim of this study is to evaluate the performance of artificial neural networks in predicting earthquakes occurring in the region of Greece with the use of different types of input data. More specifically, two different case studies are considered: the first concerns the prediction of the earthquake magnitude (M) of the following day and the second the prediction of the magnitude of the impending seismic event following the occurrence of pre-seismic signals, the so-called Seismic Electric Signals (SES), which are believed to occur prior to an earthquake, as well as the time lag between the SES and the seismic event itself. The neural network developed for the first case study used only time series magnitude data as input with the output being the magnitude of the following day. The resulting accuracy rate was 80.55% for all seismic events, but only 58.02% for the major seismic events (M ? 5.2 on the Richter scale). Our second case study for earthquake prediction uses SES as input data to the neural networks developed. This case study is separated in two parts with the differentiating element being the way of constructing the missing SES. In the first part, where the missing SES were constructed randomly for all the seismic events, the resulting accuracy rates for the magnitude of upcoming seismic events were just over 60%. In the second part, where the missing SES were constructed for the major seismic events (M ? 5.0 on the Richter scale) only by the use of neural networks reversely, the resulting accuracy rate by predicting only the magnitude was 84.01%, and by predicting both the magnitude and time lag was 83.56% for the magnitude and 92.96% for the time lag. Based on the results we conclude that, when the neural networks are trained by using the appropriate data they are able to generalise and predict unknown seismic events relatively accurately.     

Reliability estimation using a genetic algorithm-based artificial neural network: An application to a load-haul-dump machine

In this study, a neural network-based model for forecasting reliability was developed. A genetic algorithm was applied for selecting neural network parameters like learning rate (η) and momentum (μ). The input variables of the neural network model were selected by maximizing the mean entropy value. The developed model was validated by applying two benchmark data sets. A comparative study reveals that the proposed method performs better than existing methods on benchmark data sets. A case study was conducted on a load-haul-dump (LHD) machine operated at a coal mine in Alaska, USA. Past time-to-failure data for the LHD machine were collected, and cumulative time-to-failure was calculated for reliability modeling. The results demonstrate that the developed model performs well with high accuracy (R² = 0.94) in the failure prediction of a LHD machine.     

Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models

This study investigates the ability of wavelet-artificial neural networks (WANN) for the prediction of short-term daily river flow. The WANN model is improved by conjunction of two methods, discrete wavelet transform and artificial neural networks (ANN) based on regression analyses, respectively. The proposed WANN models are applied to the daily flow data of Vanyar station, on the Ajichai River in the northwest region of Iran, and compared with the ANN and support vector machine (SVM) techniques. Mean square error (MSE), mean absolute error (MAE) and correlation coefficient (R) statistics are used for evaluating precision of the WANN, ANN and SVM models. Comparison results demonstrate that the WANN model performs better than the ANN and SVM models in short-term (1-, 2- and 3-day ahead) daily river flow prediction.

     

Blind equalization using a predictive radial basis function neural network

In this paper, we propose a novel blind equalization approach based on radial basis function (RBF) neural networks. By exploiting the short-term predictability of the system input, a RBF neural net is used to predict the inverse filter output. It is shown here that when the prediction error of the RBF neural net is minimized, the coefficients of the inverse system are identical to those of the unknown system. To enhance the identification performance in noisy environments, the improved least square (ILS) method based on the concept of orthogonal distance to reduce the estimation bias caused by additive measurement noise is proposed here to perform the training. The convergence rate of the ILS learning is analyzed, and the asymptotic mean square error (MSE) of the proposed predictive RBF identification method is derived theoretically. Monte Carlo simulations show that the proposed method is effective for blind system identification. The new blind technique is then applied to two practical applications: equalization of real-life radar sea clutter collected at the east coast of Canada and deconvolution of real speech signals. In both cases, the proposed blind equalization technique is found to perform satisfactory even when the channel effects and measurement noise are strong.     

A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions

A neural network combined to a neural classifier is used in a real time forecasting of hourly maximum ozone in the centre of France, in an urban atmosphere. This neural model is based on the MultiLayer Perceptron (MLP) structure. The inputs of the statistical network are model output statistics of the weather predictions from the French National Weather Service. These predicted meteorological parameters are very easily available through an air quality network. The lead time used in this forecasting is (t + 24) h. Efforts are related to a regularisation method which is based on a Bayesian Information Criterion-like and to the determination of a confidence interval of forecasting. We offer a statistical validation between various statistical models and a deterministic chemistry-transport model. In this experiment, with the final neural network, the ozone peaks are fairly well predicted (in terms of global fit), with an Agreement Index = 92%, the Mean Absolute Error = the Root Mean Square Error = 15 μg m⁻³ and the Mean Bias Error = 5 μg m⁻³, where the European threshold of the hourly ozone is 180 μg m⁻³.To improve the performance of this exceedance forecasting, instead of the previous model, we use a neural classifier with a sigmoid function in the output layer. The output of the network ranges from [0,1] and can be interpreted as the probability of exceedance of the threshold. This model is compared to a classical logistic regression. With this neural classifier, the Success Index of forecasting is 78% whereas it is from 65% to 72% with the classical MLPs. During the validation phase, in the Summer of 2003, six ozone peaks above the threshold were detected. They actually were seven.Finally, the model called NEUROZONE is now used in real time. New data will be introduced in the training data each year, at the end of September. The network will be re-trained and new regression parameters estimated. So, one of the main difficulties in the training phase – namely the low frequency of ozone peaks above the threshold in this region – will be solved.     

ANN based simulation and experimental verification of analytical four- and five-parameters models of PV modules

In this article, artificial neural network (ANN) is adopted to predict photovoltaic (PV) panel behaviors under realistic weather conditions. ANN results are compared with analytical four and five parameter models of PV module. The inputs of the models are the daily total irradiation, air temperature and module voltage, while the outputs are the current and power generated by the panel. Analytical models of PV modules, based on the manufacturer datasheet values, are simulated through Matlab/Simulink environment. Multilayer perceptron is used to predict the operating current and power of the PV module. The best network configuration to predict panel current had a 3–7–4–1 topology. So, this two hidden layer topology was selected as the best model for predicting panel current with similar conditions. Results obtained from the PV module simulation and the optimal ANN model has been validated experimentally. Results showed that ANN model provide a better prediction of the current and power of the PV module than the analytical models. The coefficient of determination (R²), mean square error (MSE) and the mean absolute percentage error (MAPE) values for the optimal ANN model were 0.971, 0.002 and 0.107, respectively. A comparative study among ANN and analytical models was also carried out. Among the analytical models, the five-parameter model, with MAPE = 0.112, MSE = 0.0026 and R² = 0.919, gave better prediction than the four-parameter model (with MAPE = 0.152, MSE = 0.0052 and R² = 0.905). Overall, the 3–7–4–1 ANN model outperformed four-parameter model, and was marginally better than the five-parameter model.     

Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans

PurposeTo compare the diagnostic performances of artificial neural networks (ANNs) and multivariable logistic regression (LR) analyses for differentiating between malignant and benign lung nodules on computed tomography (CT) scans.MethodsThis study evaluated 135 malignant nodules and 65 benign nodules. For each nodule, morphologic features (size, margins, contour, internal characteristics) on CT images and the patient’s age, sex and history of bloody sputum were recorded. Based on 200 bootstrap samples generated from the initial dataset, 200 pairs of ANN and LR models were built and tested. The area under the receiver operating characteristic (ROC) curve, Hosmer–Lemeshow statistic and overall accuracy rate were used for the performance comparison.ResultsANNs had a higher discriminative performance than LR models (area under the ROC curve: 0.955 ± 0.015 (mean ± standard error) and 0.929 ± 0.017, respectively, p < 0.05). The overall accuracy rate for ANNs (90.0 ± 2.0%) was greater than that for LR models (86.9 ± 1.6%, p < 0.05). The Hosmer–Lemeshow statistic for the ANNs was 8.76 ± 6.59 vs. 6.62 ± 4.03 (p > 0.05) for the LR models.ConclusionsWhen used to differentiate between malignant and benign lung nodules on CT scans based on both objective and subjective features, ANNs outperformed LR models in both discrimination and clinical usefulness, but did not outperform for the calibration.     

RBF neural network inferential sensor for process emission monitoring

Inferential sensing, or soft sensing, gained popularity in recent years as an alternative to continuous emission monitoring systems because of its simplicity, reliability, and cost effectiveness as compared to analogous hardware sensors. In this paper we address the problem of NO_x emission using a model of furnace of an industrial boiler, and propose a neural network structure for high performance prediction of NO_x as well as O₂. The studied boiler is 160 MW, gas fired with natural gas, water-tube boiler, having two vertically aligned burners. The boiler model is a 3D problem that involves turbulence, combustion, radiation in addition to NO_x modeling. The 3D computational fluid dynamic model is developed using Fluent simulation package. The model provides calculations of the 3D temperature distribution as well as the rate of formation of the NO_x pollutant, enabling a better understanding on how and where NO_x are produced. The boiler was simulated under various operating conditions. The generated data is then used for initial development and assessment of neural network soft sensors for emission prediction based on the conventional process variable measurements. The performance of the proposed soft sensor is then evaluated using actual data from an industrial boiler. The developed soft sensor achieves comparable accuracy to the continuous emission monitor analyzer, however, with substantial reduction in the cost of equipment and maintenance.