Study on Back-Propagation Neural Networks in Hydrological Forecast

2014 ◽  
Vol 687-691 ◽  
pp. 2153-2156
Author(s):  
Ri Jun Zhang ◽  
Zhong Sheng Li
Keyword(s):  
Neural Networks ◽  
Traditional Method ◽  
Back Propagation ◽  
Projection Pursuit ◽  
Forecasting Model ◽  
Bp Network ◽  
Hydrological Forecasting ◽  
New Methods ◽  
Hydrological Forecast ◽  
Bp Model

The hydrological forecasting model are established respectively by the traditional method and the new methods, BP network and projection pursuit, in order to study the feasibility and practicality. The result shows that the accuracy of the BP model is within 10%, has better forecasting effect and more practical value than the others.

Application of BP on Hydrological Forecast Model

2014 ◽  
Vol 568-570 ◽  
pp. 883-886
Author(s):  
Ri Jun Zhang ◽  
Zhong Sheng Li ◽  
Feng Chun Zhang
Keyword(s):  
Traditional Method ◽  
Projection Pursuit ◽  
Forecast Model ◽  
Forecasting Model ◽  
Bp Network ◽  
Hydrological Forecasting ◽  
New Methods ◽  
Hydrological Forecast ◽  
Bp Model

In order to study the feasibility and practicality, the hydrological forecasting model are established respectively by the traditional method and the new methods, BP network and projection pursuit. The result shows that the accuracy of the BP model is within 10%, has better forecasting effect and more practical value than the others.

Non-Math-Modelling Data Analytical Methods Base on Artificial Neural Networks (ANNs) Applied to Optimize Preparation of Norcantharidin-Loaded Chitosan Nanoparticles

2012 ◽  
Vol 443-444 ◽  
pp. 319-324
Author(s):  
Yang Liu ◽  
Wei Zhang ◽  
Xue Nong Zhang
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Chitosan Nanoparticles ◽  
Back Propagation ◽  
Multiple Regression Model ◽  
Bp Network ◽  
Object A ◽  
Cross Linkage ◽  
Artificial Neural ◽  
Modelling Data

The artificial neural networks (ANNs) non-modeling methods were selected to optimize the preparation of loading norcantharidin chitosan nanoparticles (NPs) by ionic cross-linkage. A multiple regression model was constructed for fitting several preparation factors and each of the factor level values was arranged in the L9(34) design table and their linear weighted sum of the normalized value was taken as optimized object. A Back-Propagation (BP) network (3×7×2) in ANNs was created and trained for further checking the optimal results and the trained network was applied to simulate the experiment system and screen the optimal conditions. Finally, the best condition was obtained.

Application of BP Neural Networks in Damage Prediction of Multilayer Medium Penetration and Blasting

2012 ◽  
Vol 446-449 ◽  
pp. 1417-1420
Author(s):  
Xiao Ling Liu ◽  
Ting Lei ◽  
Yong Yao
Keyword(s):  
Experimental Data ◽  
Neural Networks ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Bp Neural Networks ◽  
Bp Network ◽  
Damage Prediction ◽  
Multilayer Medium ◽  
Feed Forward Network ◽  
The Neural Networks

Back-propagation method (BP method) is the supervised learning algorithm that is the most widely and successfully used in feed forward network nowadays. This paper dealt with the penetration and blasting experimental data by BP Neural networks, including of the influence of the velocity and attack angles to damage of multilayer medium penetration and blasting. Through handling of the experimental data by the BP Network system, coupled effects of quantity of explosive and buried depth can be uncoupled. The curves of infundibular crater radius vs. quantity of explosive and infundibular crater depth vs. buried depth of explosive was given. Base on computing results, it is shown that the neural networks method can be used to predict the damage of multilayer medium penetration and blasting.

Study on the Forecast Model of Water Quantity on the Basis of BP Artificial Neural Network

2013 ◽  
Vol 475-476 ◽  
pp. 188-191
Author(s):  
Xiao Bin Ding
Keyword(s):  
Water Flow ◽  
Yellow River ◽  
Back Propagation ◽  
Forecast Model ◽  
Bp Network ◽  
Bp Artificial Neural Network ◽  
Functional Fitting ◽  
Artificial Neural ◽  
Propagation Network ◽  
Bp Model

Back Propagation network, Widely used in automatic control, image recognition, hydrological forecasting and water quality evaluation, etc., as one of the Artificial Neural Networks, has stronger property of mapping, classification, functional fitting. This article takes the water flow of Lanzhou section of Yellow river as example by use of BP model to predict the water flow. It is well proved that BP network model can reach the purposes of early warning and forecasting.

Backpropagation and Kohonen Self-Organizing Feature Map in Bankruptcy Prediction

2011 ◽  
pp. 158-171 ◽  
Author(s):  
Kidong Lee ◽  
David Booth ◽  
Pervaiz Alam
Keyword(s):  
Neural Networks ◽  
Logistic Regression ◽  
Artificial Neural Networks ◽  
Prediction Accuracy ◽  
Back Propagation ◽  
Bankruptcy Prediction ◽  
Bp Network ◽  
Feature Map ◽  
Performance Benchmarks ◽  
Self Organizing

The back-propagation (BP) network and the Kohonen self-organizing feature map, selected as the representative types for the supervised and unsupervised artificial neural networks (ANN) respectively, are compared in terms of prediction accuracy in the area of bankruptcy prediction. Discriminant analysis and logistic regression are also performed to provide performance benchmarks. The findings suggest that the BP network is a better choice when a target vector is available. Advantages as well as limitations of the studied methods are also identified and discussed.

A Robust Algorithm for Wind Power Forecasting Based on Projection Pursuit and Back Propagation Neural Network

2013 ◽  
Vol 291-294 ◽  
pp. 429-434
Author(s):  
Wen Xia Liu ◽  
Ying Zhi Li
Keyword(s):  
Neural Network ◽  
Principal Components ◽  
Wind Farm ◽  
Back Propagation ◽  
Projection Pursuit ◽  
Back Propagation Neural Network ◽  
Forecasting Model ◽  
Absolute Deviation ◽  
Index Function ◽  
Trained Network

This paper has proposed a wind farm generation output forecasting model based on projection pursuit (PP) and back propagation neural network (BPNN), in order to eliminate the influence of the bad points and mutations on and enhance robustness of the forecasting model. A median absolute deviation is used as projection index function, effectively avoiding the influence of the outlier. Firstly, Extract the principal components of each factor by PP. Then, input the principal components to the BPNN for training the network. Finally, forecast the wind farm generation output via the trained network. The simulation shows that the proposed approach is of higher accuracy.

Evaluation of road condition based on BA-BP algorithm

2021 ◽  
Vol 40 (1) ◽  
pp. 331-348
Author(s):  
Dongyao Jia ◽  
Chuanwang Zhang ◽  
Dandan Lv
Keyword(s):  
Large Scale ◽  
Evaluation Method ◽  
Back Propagation ◽  
Bat Algorithm ◽  
Back Propagation Algorithm ◽  
Bp Network ◽  
Condition Evaluation ◽  
Lower Accuracy ◽  
Road Condition ◽  
Bp Model

BP (Back Propagation) neural network has been widely applied for classification tasks including road condition evaluation, however, BP model has the problem of lower accuracy and slow convergence rate. A novel road condition evaluation method based on BA-BP (Bat-Back Propagation) algorithm is proposed for the unstructured small road condition evaluation, which filled the vacancy of specific small road scenes. Firstly, five kinds of road condition features including roughness, curvature, obstacle width to height ratio, obstacle effective area ratio, obstacle coefficient are defined and extracted. Then obstacles from region of interest (ROI) in front of the vehicle are analyzed. Finally, Bat algorithm is used to optimize the searching of initial network weights and thresholds, which obtained a higher accuracy of 95.15% and efficient training process. Comparison experiments showed that the proposed approach improved the accuracy with 5.31%, 3.32%, 3.17% than the BP, GA-BP and FA-BP model, respectively. As for the processing time of collected road data, BA-BP network consumed less time of 2 s and 3.9 s compared with GA-BP and FA-BP. Proposed method also outperformed than most of the state-of-the-art approaches with higher accuracy and simpler hardware environments, which proved its potential of being popularized in large scale real-time systems.

Directional observation on lipid of male nectary of Lindera megaphylla hemsl. by the rapid embedding method with polyethylene glycol (PEG)

1990 ◽  
Vol 48 (3) ◽  
pp. 718-719
Author(s):  
Dai Dalin ◽  
Guo Jianmin
Keyword(s):  
Electron Microscope ◽  
Polyethylene Glycol ◽  
Chemical Reaction ◽  
Traditional Method ◽  
Osmium Tetroxide ◽  
Unsaturated Lipid ◽  
Embedding Method ◽  
Long Period ◽  
New Methods

Lipid cytochemistry has not yet advanced far at the EM level. A major problem has been the loss of lipid during dehydration and embedding. Although the adoption of glutaraldehyde and osmium tetroxide accelerate the chemical reaction of lipid and osmium tetroxide can react on the double bouds of unsaturated lipid to from the osmium black, osmium tetroxide can be reduced in saturated lipid and subsequently some of unsaturated lipid are lost during dehydration. In order to reduce the loss of lipid by traditional method, some researchers adopted a few new methods, such as the change of embedding procedure and the adoption of new embedding media, to solve the problem. In a sense, these new methods are effective. They, however, usually require a long period of preparation. In this paper, we do research on the fiora nectary strucure of lauraceae by the rapid-embedding method wwith PEG under electron microscope and attempt to find a better method to solve the problem mentioned above.

Fuzzy ART Neural Network Model for Automated Detection of Freeway Incidents

1998 ◽  
Vol 1634 (1) ◽  
pp. 56-63 ◽  
Author(s):  
Sherif S. Ishak ◽  
Haitham M. Al-Deek
Keyword(s):  
Neural Networks ◽  
False Alarm ◽  
False Alarm Rate ◽  
Back Propagation ◽  
Incident Detection ◽  
Traffic Patterns ◽  
Traffic Pattern ◽  
Detection Algorithms ◽  
Fuzzy Art ◽  
Freeway Incidents

Pattern recognition techniques such as artificial neural networks continue to offer potential solutions to many of the existing problems associated with freeway incident-detection algorithms. This study focuses on the application of Fuzzy ART neural networks to incident detection on freeways. Unlike back-propagation models, Fuzzy ART is capable of fast, stable learning of recognition categories. It is an incremental approach that has the potential for on-line implementation. Fuzzy ART is trained with traffic patterns that are represented by 30-s loop-detector data of occupancy, speed, or a combination of both. Traffic patterns observed at the incident time and location are mapped to a group of categories. Each incident category maps incidents with similar traffic pattern characteristics, which are affected by the type and severity of the incident and the prevailing traffic conditions. Detection rate and false alarm rate are used to measure the performance of the Fuzzy ART algorithm. To reduce the false alarm rate that results from occasional misclassification of traffic patterns, a persistence time period of 3 min was arbitrarily selected. The algorithm performance improves when the temporal size of traffic patterns increases from one to two 30-s periods for all traffic parameters. An interesting finding is that the speed patterns produced better results than did the occupancy patterns. However, when combined, occupancy–speed patterns produced the best results. When compared with California algorithms 7 and 8, the Fuzzy ART model produced better performance.

Sign in / Sign up

Export Citation Format

Share Document