DocumentCode
1947850
Title
Notice of Retraction
Determination of component proportion based on BP neural networks
Author
Fugang Zheng ; Xing Liu
Author_Institution
Dept of State Key Lab. of Hydrol.-Water, Hohai Univ. Nanjing, Nanjing, China
Volume
8
fYear
2010
fDate
9-11 July 2010
Firstpage
28
Lastpage
32
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Component proportion sometimes is necessary in order to evaluate the state of research objects quantitatively or to do some specific studies. Back propagation neural network (BPNN) is one of mostly used neural networks because of its ability to achieve a high precision simulation for data problem or target function which is hardly to be established by conventional mathematical theory. In this paper, the conventional neural network model, which can effectively separate the influences of weights and bias on output, is established. Combined with the proposed method, component proportion can be obtained taking advantage of structure of this model. Through simulations of concrete examples, the results show that the method is feasibility and validity in dealing with both linear problem and some nonlinear problems.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Component proportion sometimes is necessary in order to evaluate the state of research objects quantitatively or to do some specific studies. Back propagation neural network (BPNN) is one of mostly used neural networks because of its ability to achieve a high precision simulation for data problem or target function which is hardly to be established by conventional mathematical theory. In this paper, the conventional neural network model, which can effectively separate the influences of weights and bias on output, is established. Combined with the proposed method, component proportion can be obtained taking advantage of structure of this model. Through simulations of concrete examples, the results show that the method is feasibility and validity in dealing with both linear problem and some nonlinear problems.
Keywords
backpropagation; genetic algorithms; neural nets; BP neural networks; component proportion; data problem; high precision simulation; linear problem; nonlinear problems; object research; target function; Aging; Genetic Algorithm; back propagation neural networks; bias; component proportion; weights;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on
Conference_Location
Chengdu
Print_ISBN
978-1-4244-5537-9
Type
conf
DOI
10.1109/ICCSIT.2010.5564506
Filename
5564506
Link To Document