Optimization of ANN input parameters used in electric field level prediction model

This paper analyses the factors affecting the heating consumption of a heating substation. The input parameters of neural network prediction model are analysed and selected. The average absolute error, average absolute percentage error, and mean square error are used to evaluate the effect of the prediction model. The results show that when the model input parameters are the maximum outdoor temperature, the average outdoor temperature, the average temperature difference between the primary supply and return of domestic hot water, the heating load in the previous three days, the heating load in the previous two days, the heating load in the previous day and when the model input parameters are the maximum outdoor temperature, the minimum outdoor temperature, the average outdoor temperature, the average temperature difference between the primary supply and return of domestic hot water, the heating load of the previous three days, the heating load of the previous two days, the heating load of the previous day, the effects are better.

Download Full-text

Application of WOA–SVR in Seed Vigor of High-Voltage Electric Field Treatment on Aged Cotton (Gossypium spp.) Seeds

Agronomy ◽

10.3390/agronomy12010088 ◽

2021 ◽

Vol 12 (1) ◽

pp. 88

Author(s):

Zhanhua Song ◽

Junxiang Ma ◽

Qian Peng ◽

Baoji Liu ◽

Fade Li ◽

...

Keyword(s):

Electric Field ◽

Prediction Model ◽

High Voltage ◽

Treatment Time ◽

Seed Vigor ◽

Germination Index ◽

Support Vector ◽

Gossypium Spp ◽

Whale Optimization ◽

Input Variables

When seeds are treated with a high-voltage electric field (HVEF) to improve seed vigor, due to the large differences in the biological electromagnetic effects on different types of seeds, the methods of variance analysis and regression analysis based on data statistics are generally used to construct the optimal electric field dose prediction model; however, the generalization performance of the prediction model tends to be poor. To solve this problem, the electric intensity, frequency and treatment time were taken as the input variables for hybrid support vector regression (SVR) analysis to establish the prediction model of the seed comprehensive germination index. The whale optimization algorithm (WOA) was used to optimize the kernel parameters of the SVR. The optimized hybrid WOA–SVR model predicted the optimal comprehensive germination index of aged cotton (Gossypium spp.) seeds to be 329, the optimal HVEF dosage was 3.64 kV/cm × 99 s, and the frequency was 1.4 Hz. The aged cotton seeds were treated with the optimal HVEF and the germination test was carried out. Compared with the check (CK), the comprehensive germination index of seeds increased by 48%. The research results provided a new method and new idea for the optimal design of parameters for seed treatment with HVEF.

Download Full-text

Macrocell electric field strength prediction model based upon artificial neural networks

IEEE Journal on Selected Areas in Communications ◽

10.1109/jsac.2002.801217 ◽

2002 ◽

Vol 20 (6) ◽

pp. 1170-1177 ◽

Cited By ~ 22

Author(s):

A. Neskovic ◽

N. Neskovic ◽

D. Paunovic

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Field Strength ◽

Electric Field ◽

Prediction Model ◽

Electric Field Strength ◽

Strength Prediction ◽

Model Based ◽

Artificial Neural

Download Full-text

Integrated versus isolated scenario for prediction dissolved oxygen at progression of water quality monitoring stations

Hydrology and Earth System Sciences ◽

10.5194/hess-15-2693-2011 ◽

2011 ◽

Vol 15 (8) ◽

pp. 2693-2708 ◽

Cited By ~ 16

Author(s):

A. Najah ◽

A. El-Shafie ◽

O. A. Karim ◽

O. Jaafar

Keyword(s):

Water Quality ◽

Dissolved Oxygen ◽

Prediction Model ◽

Quality Parameters ◽

Water Quality Parameters ◽

Effective Parameters ◽

Data Set ◽

Proposed Model ◽

Input Parameters ◽

Predicted Values

Abstract. This study examined the potential of Multi-layer Perceptron Neural Network (MLP-NN) in predicting dissolved oxygen (DO) at Johor River Basin. The river water quality parameters were monitored regularly each month at four different stations by the Department of Environment (DOE) over a period of ten years, i.e. from 1998 to 2007. The following five water quality parameters were selected for the proposed MLP-NN modelling, namely; temperature (Temp), water pH, electrical conductivity (COND), nitrate (NO3) and ammonical nitrogen (NH3-NL). In this study, two scenarios were introduced; the first scenario (Scenario 1) was to establish the prediction model for DO at each station based on five input parameters, while the second scenario (Scenario 2) was to establish the prediction model for DO based on the five input parameters and DO predicted at previous station (upstream). The model needs to verify when output results and the observed values are close enough to satisfy the verification criteria. Therefore, in order to investigate the efficiency of the proposed model, the verification of MLP-NN based on collection of field data within duration 2009–2010 is presented. To evaluate the effect of input parameters on the model, the sensitivity analysis was adopted. It was found that the most effective inputs were oxygen-containing (NO3) and oxygen demand (NH3-NL). On the other hand, Temp and pH were found to be the least effective parameters, whereas COND contributed the lowest to the proposed model. In addition, 17 neurons were selected as the best number of neurons in the hidden layer for the MLP-NN architecture. To evaluate the performance of the proposed model, three statistical indexes were used, namely; Coefficient of Efficiency (CE), Mean Square Error (MSE) and Coefficient of Correlation (CC). A relatively low correlation between the observed and predicted values in the testing data set was obtained in Scenario 1. In contrast, high coefficients of correlation were obtained between the observed and predicted values for the test sets of 0.98, 0.96 and 0.97 for all stations after adopting Scenario 2. It appeared that the results for Scenario 2 were more adequate than Scenario 1, with a significant improvement for all stations ranging from 4 % to 8 %.

Download Full-text