Image restoration by using new AGA optimized BPNN

Farooq Umar; Ting Zhi Shen; San Yuan Zhao; Muhammad Imran

doi:10.1016/j.proeng.2012.01.434

Image restoration by using new AGA optimized BPNN

Farooq Umar^*, Ting Zhi Shen, San Yuan Zhao, Muhammad Imran

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

5 Citations (Scopus)

Abstract

In this paper a new method of Adaptive Genetic Algorithm (AGA) is introduced to optimize the back propagation neural network for Image restoration. In this new AGA, we added permutation operator in addition to traditional mutation and Pooling Operator is introduced. To increase the convergence rate, we used adaptive crossover rate and mutation rate. It has been observed that with the addition of these two operators, the use of Genetic Algorithms (GA) for navigating the optimal combination of solution is more effective and the convergence can be achieved with more accuracy. In addition, it also decreases the value of Mean Square Error (MSE) significantly.

Original language	English
Pages (from-to)	3028-3032
Number of pages	5
Journal	Procedia Engineering
Volume	29
DOIs	https://doi.org/10.1016/j.proeng.2012.01.434
Publication status	Published - 2012
Event	2012 International Workshop on Information and Electronics Engineering, IWIEE 2012 - Harbin, China Duration: 10 Mar 2012 → 11 Mar 2012

Keywords

Adaptive crossover
Adaptive genetic algorithm
Adaptive mutation
Adaptive permutation
BPNN
Pooling operator

Access to Document

10.1016/j.proeng.2012.01.434

Cite this

@article{923c14f401fd43c9b5cfedd0c6171188,

title = "Image restoration by using new AGA optimized BPNN",

abstract = "In this paper a new method of Adaptive Genetic Algorithm (AGA) is introduced to optimize the back propagation neural network for Image restoration. In this new AGA, we added permutation operator in addition to traditional mutation and Pooling Operator is introduced. To increase the convergence rate, we used adaptive crossover rate and mutation rate. It has been observed that with the addition of these two operators, the use of Genetic Algorithms (GA) for navigating the optimal combination of solution is more effective and the convergence can be achieved with more accuracy. In addition, it also decreases the value of Mean Square Error (MSE) significantly.",

keywords = "Adaptive crossover, Adaptive genetic algorithm, Adaptive mutation, Adaptive permutation, BPNN, Pooling operator",

author = "Farooq Umar and Shen, {Ting Zhi} and Zhao, {San Yuan} and Muhammad Imran",

year = "2012",

doi = "10.1016/j.proeng.2012.01.434",

language = "English",

volume = "29",

pages = "3028--3032",

journal = "Procedia Engineering",

issn = "1877-7058",

publisher = "Elsevier B.V.",

note = "2012 International Workshop on Information and Electronics Engineering, IWIEE 2012 ; Conference date: 10-03-2012 Through 11-03-2012",

}

TY - JOUR

T1 - Image restoration by using new AGA optimized BPNN

AU - Umar, Farooq

AU - Shen, Ting Zhi

AU - Zhao, San Yuan

AU - Imran, Muhammad

PY - 2012

Y1 - 2012

N2 - In this paper a new method of Adaptive Genetic Algorithm (AGA) is introduced to optimize the back propagation neural network for Image restoration. In this new AGA, we added permutation operator in addition to traditional mutation and Pooling Operator is introduced. To increase the convergence rate, we used adaptive crossover rate and mutation rate. It has been observed that with the addition of these two operators, the use of Genetic Algorithms (GA) for navigating the optimal combination of solution is more effective and the convergence can be achieved with more accuracy. In addition, it also decreases the value of Mean Square Error (MSE) significantly.

AB - In this paper a new method of Adaptive Genetic Algorithm (AGA) is introduced to optimize the back propagation neural network for Image restoration. In this new AGA, we added permutation operator in addition to traditional mutation and Pooling Operator is introduced. To increase the convergence rate, we used adaptive crossover rate and mutation rate. It has been observed that with the addition of these two operators, the use of Genetic Algorithms (GA) for navigating the optimal combination of solution is more effective and the convergence can be achieved with more accuracy. In addition, it also decreases the value of Mean Square Error (MSE) significantly.

KW - Adaptive crossover

KW - Adaptive genetic algorithm

KW - Adaptive mutation

KW - Adaptive permutation

KW - BPNN

KW - Pooling operator

UR - http://www.scopus.com/inward/record.url?scp=84858382878&partnerID=8YFLogxK

U2 - 10.1016/j.proeng.2012.01.434

DO - 10.1016/j.proeng.2012.01.434

M3 - Conference article

AN - SCOPUS:84858382878

SN - 1877-7058

VL - 29

SP - 3028

EP - 3032

JO - Procedia Engineering

JF - Procedia Engineering

T2 - 2012 International Workshop on Information and Electronics Engineering, IWIEE 2012

Y2 - 10 March 2012 through 11 March 2012

ER -

Image restoration by using new AGA optimized BPNN

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this