Combination Of Multiple Neural Networks Research Articles

Do Chinese Photovoltaic Products Have Trade Potential in RCEP Countries? A BP Neural-Network-Improved Trade Gravity Model Analysis

China plays an important role in the global trade of photovoltaic products, and the RCEP agreement provides more opportunities and possibilities for China. This paper develops an improved trade gravity model with BP neural networks to estimate trade potentials, and the following conclusions are obtained: (1) The BP neural network is a more effective estimation method than traditional pooled regression, fixed effects, and random effects, and the combination of multiple neural networks for prediction can lead to higher robustness and accuracy. (2) The potential of China’s trade in PV products to RCEP countries is relatively mature, but the scale of trade in PV products between China and Japan and other countries may still be further expanded. (3) China’s trade potential for different regions in the RCEP agreement changed historically in different processes, with China’s trade potential for the Oceania region declining, while its trade potential for the East and Southeast Asia region increased in recent years.

A New Multichannel Parallel Network Framework for the Special Structure of Multilead ECG.

Electrocardiogram (ECG) contains the rhythmic features of continuous heartbeat and morphological features of ECG waveforms and varies among different diseases. Based on ECG signal features, we propose a combination of multiple neural networks, the multichannel parallel neural network (MLCNN-BiLSTM), to explore feature information contained in ECG. The MLCNN channel is used in extracting the morphological features of ECG waveforms. Compared with traditional convolutional neural network (CNN), the MLCNN can accurately extract strong relevant information on multilead ECG while ignoring irrelevant information. It is suitable for the special structures of multilead ECG. The Bidirectional Long Short-Term Memory (BiLSTM) channel is used in extracting the rhythmic features of ECG continuous heartbeat. Finally, by initializing the core threshold parameters and using the backpropagation algorithm to update automatically, the weighted fusion of the temporal-spatial features extracted from multiple channels in parallel is used in exploring the sensitivity of different cardiovascular diseases to morphological and rhythmic features. Experimental results show that the accuracy rate of multiple cardiovascular diseases is 87.81%, sensitivity is 86.00%, and specificity is 87.76%. We proposed the MLCNN-BiLSTM neural network that can be used as the first-round screening tool for clinical diagnosis of ECG.

Adaptive Deep Learning-Based Air Quality Prediction Model Using the Most Relevant Spatial-Temporal Relations

Air pollution has become an extremely serious problem, with particulate matter having a significantly greater impact on human health than other contaminants. The small diameter of fine particulate matter (PM2.5) allows it to penetrate deep into the alveoli as far as the bronchioles, interfering with a gas exchange within the lungs. Long-term exposure to particulate matter has been shown to cause the cardiovascular disease, respiratory disease, and increase the risk of lung cancers. Therefore, forecasting air quality has also become important to help guide individual actions. This paper aims to forecast air quality for up to 48 h using a combination of multiple neural networks, including an artificial neural network, a convolutional neural network, and a long-short-term memory to extract spatial-temporal relations. The proposed predictive model considers various meteorology data from the previous few hours as well as information related to the elevation space to extract terrain impact on air quality. The model includes trends from multiple locations, extracted from correlations between adjacent locations, and among similar locations in the temporal domain. Experiments employing Taiwan and Beijing data sets show that the proposed model achieves excellent performance and outperforms current state-of-the-art methods.

Prediction of Combustion Efficiency Using Multiple Neural Networks

In order to improve the generalisation capability of neural network based models, combining multiple neural networks (MNN) is proposed in this paper with the application of predicting the combustion efficiency from the boiler. This is due to the fact that single feed forward artificial neural networks (FANN) lack of the robustness due to the overfitting of the models. Combination of MNN was introduced and researchers concentrate on how overfitting can be avoided by combining the single FANN. In this study, the individual FANN are trained using different training data sets and /or from different initial weights, then combined. Instead of choosing the best single FANN model among the networks, all the neural networks are combined. It can also be described as architecture of network consisting of several sub-models and a mechanism which combines the outputs of these sub-models. In this study bootstrap application or bootstrap technique were apply to replicate the initial raw data or to create different training and testing data sets. Bootstrap basically relate or deals with the sampling to create random data sets for training and testing. By creating an equal number of bad and good data sampling, it actually improves the generalisation capability of FANN. The simple averaging method was applied in combining the MNN. The data for modelling was taken from energy management handbook with total of 66 data points where the training and testing consist of 39 samples data while unseen data consist of 27 samples data. The result shows that the MNN combination with simple averaging method did slightly improved the model prediction of the combustion efficiency by using two inputs which are stack temperaturerise, dT and also the excess air. The coefficient of determination, r2, and root mean squared error (RMSE) forunseen data for MNN are 0.9999 and 0.0105.

AIR POLLUITON INDEX PREDICTION USING MULTIPLE NEURAL NETWORKS

Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN) is shown to be able to predict the Air Pollution Index (API) with a Mean Squared Error (MSE) and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-robust nature of single FANN, a selective combination of Multiple Neural Networks (MNN) is introduced using backward elimination and a forward selection method. The results show that both selective combination methods can improve the robustness and performance of the API prediction with the MSE and R2 of 0.1614 and 0.8210 respectively. This clearly shows that it is possible to reduce the number of networks combined in MNN for API prediction, without losses of any information in terms of the performance of the final API prediction model.

Improving water quality index prediction in Perak River basin Malaysia through a combination of multiple neural networks

ABSTRACTThis paper proposes a method for the real-time prediction of water quality index (WQI) by excluding the biological oxygen demand and chemical oxygen demand, which are not measured in real time, from the model inputs. In this study, feedforward artificial neural networks are used to model the WQI in Perak River basin Malaysia due to its capability in modelling nonlinear systems. The results show that the developed single feedforward neural network model can predict WQI very well with the coefficient of determination R2 and mean squared error (MSE) of 0.9090 and 0.1740 on the unseen validation data, respectively. In addition to that, the aggregation of multiple neural networks in predicting the WQI further improves the prediction performance on the unseen validation data. Forward selection and backward elimination selective combination methods are used to combine multiple neural networks and both methods lead to 6 and 5 networks being combined with R2 and MSE of 0.9340, 0.9270 and 0.1156, 0.1256, respectively. It is clearly shown that combining multiple neural networks does improve the performance for WQI prediction.

Combination of Multiple Neural Networks to Solve Travelling Salesman Problem using Genetic Algorithm

this paper, the already recognized NP Complete problem which is Travelling Salesman Problem which is also known as TSP, is addressed and its performance is analyzed. For a large and complex data set, a particular neural network is needed to focus on a particular component of the problem, after which combining of all the networks together is required. The basic ideology behind this multiple neural network arrangement is that, n-independently different neural networks are trained separately and then their respective outputs (generated independently) are combined together to form the resultant classifier. A new combining technique (for combining outputs of multiple neural networks into one) has been proposed and utilized for evidence blend in the simulation part of the method. Its performance is analyzed on the bases of simulation and it shows some notably enhanced outcomes.

Prediction of product formation in 2-keto-l-gulonic acid fermentation through Bayesian combination of multiple neural networks

As the key precursor for l-ascorbic acid synthesis, 2-keto-l-gulonic acid (2-KGA) is widely produced by the mixed culture of Bacillus megaterium and Ketogulonicigenium vulgare. In this study, a Bayesian combination of multiple neural networks is developed to obtain accurate prediction of the product formation. The historical batches are classified into three categories with a batch classification algorithm based on the statistical analysis of the product formation profiles. For each category, an artificial neural network is constructed. The input vector of the neural network consists of a series of time-discretized process variables. The output of the neural network is the predicted product formation. The training database for each neural network is composed of both the input–output data pairs from the historical bathes in the corresponding category, and all the available data pairs collected from the batch of present interest. The prediction of the product formation is practiced through a Bayesian combination of three trained neural networks. Validation was carried out in a Chinese pharmaceutical factory for 140 industrial batches in total, and the average root mean square error (RMSE) is 2.2% and 2.6% for 4h and 8h ahead prediction of product formation, respectively.

OPTIMUM NUMBERS OF SINGLE NETWORK FOR COMBINATION IN MULTIPLE NEURAL NETWORKS MODELING APPROACH FOR MODELING NONLINEAR SYSTEM

This paper is focused on finding the optimum number of single networks in multiple neural networks combination to improve neural network model robustness for nonlinear process modeling and control. In order to improve the generalization capability of single neural network based models, combining multiple neural networks is proposed in this paper. By studying the optimum number of network that can be combined in multiple network combination, the researcher can estimate the complexity of the proposed model then obtained the exact number of networks for combination. Simple averaging combination approach is implemented in this paper which is applied to nonlinear process models. It is shown that the optimum number of networks for combination can be obtained hence enhancing the performance of the proposed model.

Selective combination of multiple neural networks for improving model prediction in nonlinear systems modelling through forward selection and backward elimination

Combining multiple neural networks appears to be a very promising approach in improving neural network generalisation since it is very difficult, if not impossible, to develop a perfect single neural network. In the building of an aggregated neural network model, a number of individual networks are developed from different data sets and/or different training algorithms. In this paper, individual networks are developed from bootstrap re-samples of the original training and testing data sets. Instead of combining all the developed networks, this paper proposes two selective combination techniques: forward selection and backward elimination. These two techniques essentially combine those individual networks that, when combined, can significantly improve model generalisation. In forward selection, individual networks are gradually added into the aggregated network until the aggregated network error on the original training and testing data sets cannot be further reduced. In backward elimination, all the individual networks are initially aggregated and some of the individual networks are then gradually eliminated until the aggregated network error on the original training and testing data sets cannot be further reduced. The proposed techniques are applied to dynamic nonlinear process modelling and classification of diabetes database. Application results demonstrate that the proposed techniques can significantly improve model generalisation and perform better than aggregating all the individual networks and the heuristic selective combination method where networks with better performance on the training and testing data are selected.

Combination of multiple neural networks using data fusion techniques for enhanced nonlinear process modelling

Combining multiple neural networks appears to be a very promising approach in improving neural network generalisation since it is very difficult, if not impossible, to develop a perfect single neural network. This paper proposes using data fusion techniques to combine multiple neural networks and the combination weights change with the model input data. At each given model input data point, the probability of a particular network being the true model is estimated and the network with the highest probability is assigned a combination weight of 1 while other networks assigned combination weights of 0. This probability is calculated using the estimated sum of squared prediction errors of the individual networks on a sliding window covering the most recent sampling times. A nearest neighbour method is used to estimate the network prediction error for a given model input data point. This is to facilitate long range predictions where future prediction errors are unknown and have to be estimated. The proposed techniques are applied to dynamic nonlinear process modelling and modelling of the real world data for the water discharged in Sg Langat Malaysia. Application results demonstrate that the proposed techniques can significantly improve model generalisation especially in long range predictions.

Rejection of the Feed-Flow Disturbances in a Multi-Component Distillation Column Using a Multiple Neural Network Model-Predictive Controller

This article deals with the issues associated with developing a new design methodology for the nonlinear model-predictive control (MPC) of a chemical plant. A combination of multiple neural networks is selected and used to model a nonlinear multi-input multi-output (MIMO) process with time delays. An optimization procedure for a neural MPC algorithm based on this model is then developed. The proposed scheme has been tested on a model of an 18-plate multi-component distillation column. The algorithm provides excellent disturbance rejection for this process.

Bayesian selective combination of multiple neural networks for improving long-range predictions in nonlinear process modelling

A Bayesian selective combination method is proposed for combining multiple neural networks in nonlinear dynamic process modelling. Instead of using fixed combination weights, the probability of a particular network being the true model is used as the combination weight for combining that network. The prior probability is calculated using the sum of squared errors of individual networks on a sliding window covering the most recent sampling times. A nearest neighbour method is used for estimating the network error for a given input data point, which is then used in calculating the combination weights for individual networks. Forward selection and backward elimination are used to select the individual networks to be combined. In forward selection, individual networks are gradually added into the aggregated network until the aggregated network error on the original training and testing data sets cannot be further reduced. In backward elimination, all the individual networks are initially aggregated and some of the individual networks are then gradually eliminated until the aggregated network error on the original training and testing data sets cannot be further reduced. Application results demonstrate that the proposed techniques can significantly improve model generalisation and perform better than aggregating all the individual networks.

The nonlinear model-predictive control of a chemical plant using multiple neural networks

A combination of multiple neural networks (NNs) is selected and used to model nonlinear multi-input multi-output (MIMO) processes with time delays. An optimisation procedure for a nonlinear model-predictive control (MPC) algorithm based on this model is then developed. The proposed scheme has been applied and evaluated for two example problems, including the MPC of a multi-component distillation column.