Analysis of an impact linear relationship between input variables having on prediction of BP neural network

The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.

Download Full-text

Sunlight Greenhouse Temperature Prediction Model Based on Bayesian Regularization BP Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.740.871 ◽

2015 ◽

Vol 740 ◽

pp. 871-874

Author(s):

Hui Zhao ◽

Li Rong Shi ◽

Hong Jun Wang

Keyword(s):

Neural Network ◽

Network Structure ◽

Bp Neural Network ◽

Principal Component ◽

Coupling Factor ◽

Bayesian Regularization ◽

The Neural Network ◽

Neural Network Structure ◽

Input Variables ◽

Bp Neural Network Model

Directing against the problems of too large size of the neural network structure due to the existence of a complex relationship between the input coupling factor and too many input factors in establishing model for predicting temperature of sunlight greenhouse. This article chose the environmental factors that affect the sunlight greenhouse temperature as data sample. Through the principal component analysis of data samples, three main factors were extracted. These selected principal component values were taken as the input variables of BP neural network model. Use the Bayesian regularization algorithm to improve the BP neural network. The empirical results show that this method is utilized modify BP neural network, which can simplify network structure and smooth fitting curve, has good generalization capability.

Download Full-text

A Novel Method of Stereo Camera Calibration Using BP Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.29-32.2692 ◽

2010 ◽

Vol 29-32 ◽

pp. 2692-2697

Author(s):

Jiu Long Xiong ◽

Jun Ying Xia ◽

Xian Quan Xu ◽

Zhen Tian

Keyword(s):

Neural Network ◽

Linear Relationship ◽

Camera Calibration ◽

Bp Neural Network ◽

Calibration Method ◽

Two Stage ◽

Non Linear ◽

Novel Method ◽

Calibration Accuracy ◽

The Relationship

Camera calibration establishes the relationship between 2D coordinates in the image and 3D coordinates in the 3D world. BP neural network can model non-linear relationship, and therefore was used for calibrating camera by avoiding the non-linear factors of the camera in this paper. The calibration results are compared with the results of Tsai’s two stage method. The comparison show that calibration method based BP neural network improved the calibration accuracy.

Download Full-text

Based on the Genetic Algorithm to Optimize the BP Neural Network in the Degree of Concrete Creep Prediction Model

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.584-586.1346 ◽

2014 ◽

Vol 584-586 ◽

pp. 1346-1350

Author(s):

Hui Qin Yao ◽

Ye Long Jiang

Keyword(s):

Neural Network ◽

Prediction Model ◽

Network Model ◽

Neural Network Model ◽

Bp Neural Network ◽

Reference Value ◽

Concrete Creep ◽

Practical Engineering ◽

Input Variables ◽

Bp Neural Network Model

The BP neural network model for creep degree of concrete is established,in which concrete age under load and loading time as input variables and the creep degree of concrete as output variable. In order to get best optimal weight and threshold of the BP neural network, genetic algorithms method has been used by selection, crossover and mutation operation. The BP neural network model is applied to the engineering of “515”dam.Comparison the prediction results of the BP neural network and the eight-parameters formula of concrete creep degree, the BP neural network model has high prediction accuracy. What’s more, this intelligent prediction model for creep degree of concrete has good credibility and reference value in practical engineering.

Download Full-text

Construction of entrepreneurship evaluation system for college graduates ——Empirical analysis based on BP neural network

E3S Web of Conferences ◽

10.1051/e3sconf/202129202043 ◽

2021 ◽

Vol 292 ◽

pp. 02043

Author(s):

Xiaoyi Wang ◽

Hui Che

Keyword(s):

Neural Network ◽

College Students ◽

Success Rate ◽

Bp Neural Network ◽

Evaluation System ◽

College Graduates ◽

Influence Factors ◽

Entrepreneurial Success ◽

Training Process ◽

Input Variables

In order to accurately and efficiently evaluate the entrepreneurial success rate and the risks in the entrepreneurial process of college graduates. BP Neural Network is used to establish the evaluation system of College Students’ entrepreneurship process, making contributions to the underwriting system of entrepreneurship insurance. 12 influence factors are selected as input variables, and the neuron weight and learning rateare adjusted in the training process.

Download Full-text

Driving Rhythm Method for Driving Comfort Analysis on Rural Highways

PROMET - Traffic&Transportation ◽

10.7307/ptt.v29i4.2217 ◽

2017 ◽

Vol 29 (4) ◽

pp. 371-379 ◽

Cited By ~ 1

Author(s):

Bo Yu ◽

Yuren Chen

Keyword(s):

Neural Network ◽

Visual Perception ◽

Bp Neural Network ◽

Shape Parameters ◽

Rural Highways ◽

Driving Speed ◽

Variation Characteristics ◽

Input Variables ◽

New Perspective ◽

Real Vehicle

Driving comfort is of great significance for rural highways, since the variation characteristics of driving speed are comparatively complex on rural highways. Earlier studies about driving comfort were usually based on the actual geometric road alignments and automobiles, without considering the driver’s visual perception. However, some scholars have shown that there is a discrepancy between actual and perceived geometric alignments, especially on rural highways. Moreover, few studies focus on rural highways. Therefore, in this paper the driver’s visual lane model was established based on the Catmull-Rom spline, in order to describe the driver’s visual perception of rural highways. The real vehicle experiment was conducted on 100 km rural highways in Tibet. The driving rhythm was presented to signify the information during the driving process. Shape parameters of the driver’s visual lane model were chosen as input variables to predict the driving rhythm by BP neural network. Wavelet transform was used to explore which part of the driving rhythm is related to the driving comfort. Then the probabilities of good, fair and bad driving comfort can be calculated by wavelets of the driving rhythm. This work not only provides a new perspective into driving comfort analysis and quantifies the driver’s visual perception, but also pays attention to the unique characteristics of rural highways.

Download Full-text

Intrusion Detection Engineering Management Based on Optimization of BP Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.416-417.1228 ◽

2013 ◽

Vol 416-417 ◽

pp. 1228-1232

Author(s):

Jian Hua Zhao

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Bp Neural Network ◽

Fitness Function ◽

Engineering Management ◽

Data Set ◽

Binary Coding ◽

Optimized Model ◽

Input Variables ◽

The Individual

In order to short the modelling time of BP neural network, this paper designs a kind of genetic algorithm to optimize it. By encoding the individual components, initializing the number of populations, and designing proper fitness function, a binary coding genetic algorithm is provided for BP neural network. And it is used to optimize input variables of BP neural network and reduce its dimension. The experiment is carried out based on KDD Cup 99 data set. The results show that the optimized model has shorter modelling time.

Download Full-text

Research on Gas Load Forecasting Using Artificial Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.717.423 ◽

2013 ◽

Vol 717 ◽

pp. 423-427 ◽

Cited By ~ 1

Author(s):

Wei Ya Shi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Bp Neural Network ◽

Load Forecasting ◽

Weather Condition ◽

Short Term ◽

Implicit Relation ◽

Accurate Forecast ◽

Artificial Neural ◽

Input Variables

In this paper, we give a short survey and analysis on natural gas load forecasting technology using artificial neural network. Different input variables are used to compare the result of forecasting the short term gas load. The experiment results show that the BP neural network can be used to find the implicit relation among historical gas load, weather condition and the future gas load. We also conclude that the input variables have no important influence on the accurate forecast.

Download Full-text

Quality Prediction Model Based on PCA-BP Neural Network for Tobacco Leaves Redrying Process

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.201-203.1627 ◽

2011 ◽

Vol 201-203 ◽

pp. 1627-1631

Author(s):

Jian Kang Yin ◽

Chang Hua Chen ◽

Jing Min Li ◽

Fei Zhang ◽

Jin Yao

Keyword(s):

Neural Network ◽

Prediction Model ◽

Bp Neural Network ◽

Back Propagation ◽

Principal Component ◽

Absolute Error ◽

Quality Prediction ◽

Tobacco Leaves ◽

Model Based ◽

Input Variables

Aiming to the problem that is very difficult to establish the mechanism model of quality for the process of tobacco leaves redrying, this paper proposes a quality prediction model based on principal component analysis (PCA) and improved back propagation (BP)neural network for tobacco leaves redrying process. Firstly, 12 input variables are confirmed by analyzing the factors on quality of tobacco leaves redrying process. Second, the methods of PCA is used to eliminate the correlation of original input layer data, in which 12 input variables are transformed into 6 uncorrelated indicators. Then, the quality prediction model based on improved BP neural network is established. Finally, a simulation experiment is conducted and the average prediction error is as low as 1.03%, the absolute error for forecasting is fluctuated in the range of 0.16% - 2.49%. The result indicates that the model is simpler and has higher stability for prediction, which can completely meet the actual requirements of the tobacco leaves redrying process.

Download Full-text

Prediction of Grain Yield in Henan Province Based on Grey BP Neural Network Model

Discrete Dynamics in Nature and Society ◽

10.1155/2021/9919332 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Bingjun Li ◽

Yifan Zhang ◽

Shuhua Zhang ◽

Wenyan Li

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Henan Province ◽

Grain Production ◽

Relational Analysis ◽

Key Variables ◽

Input Variables ◽

Bp Neural Network Model ◽

Grey Relational ◽

Bpnn Model

BP neural network (BPNN) is widely used due to its good generalization and robustness, but the model has the defect that it cannot automatically optimize the input variables. In response to this problem, this study uses the grey relational analysis method to rank the importance of input variables, obtains the key variables and the best BPNN model structure through multiple training and learning for the BPNN models, and proposes a variable optimization selection algorithm combining grey relational analysis and BP neural network. The predicted values from the metabolic GM (1, 1) model for key variables was used as input to the best BPNN model for prediction modeling, and a grey BP neural network model prediction model (GR-BPNN) was proposed. The long short-term memory neural network (LSTM), convolutional neural network (CNN), traditional BP neural network (BP), GM (1, N) model, and stepwise regression (SR) are also implemented as benchmark models to prove the superiority and applicability of the new model. Finally, the GR-BPNN forecasting model was applied to the grain yield forecast of the whole province and subregions for Henan Province. The forecasting results found that the growth rate of grain production in Henan Province slowed down and the center of gravity for grain production shifted northwards.

Download Full-text