DocumentCode
1966080
Title
Notice of Retraction
New algorithm based on the BP neural network
Author
Zi-sheng Zhang ; Ji-guang Wang ; Zhen-ya Yang ; Zhen-lei Xiao ; Bo Zhang ; Zhi-qiang Liu ; Qing Li
Author_Institution
Electrostatic Res. Inst., Hebei Univ., Baoding, China
Volume
2
fYear
2010
fDate
10-11 July 2010
Firstpage
68
Lastpage
70
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.
In allusion to the defects of the slow convergence speed and the local minimum for traditional BP algorithm, a new algorithm is proposed. The new algorithm is designed by hierarchical genetic algorithm together with the algorithm of automatically adjusting the S form function, which combines with the BP network to improve the efficiency of fault detection. With calculation and simulation, compared with the traditional BP algorithm, the new algorithm has high precision of training, low training times, and small relative mean square error, which achieves better optimization results.
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.
In allusion to the defects of the slow convergence speed and the local minimum for traditional BP algorithm, a new algorithm is proposed. The new algorithm is designed by hierarchical genetic algorithm together with the algorithm of automatically adjusting the S form function, which combines with the BP network to improve the efficiency of fault detection. With calculation and simulation, compared with the traditional BP algorithm, the new algorithm has high precision of training, low training times, and small relative mean square error, which achieves better optimization results.
Keywords
backpropagation; genetic algorithms; neural nets; BP neural network algorithm; S form function; fault detection; hierarchical genetic algorithm; relative mean square error; algorithm; artificial neural network; hierarchical genetic algorithm; traditional BP algorithm;
fLanguage
English
Publisher
ieee
Conference_Titel
Industrial and Information Systems (IIS), 2010 2nd International Conference on
Conference_Location
Dalian
Print_ISBN
978-1-4244-7860-6
Type
conf
DOI
10.1109/INDUSIS.2010.5565676
Filename
5565676
Link To Document