Master-leader-slave cuckoo search with parameter control for ANN optimization and its real-world application to water quality prediction

Najmeh Sadat Jaddi, Salwani Abdullah, Marlinda Abdul Malek

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent Lévy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.

Original languageEnglish
Article numbere0170372
JournalPLoS One
Volume12
Issue number1
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Slaves
Water Quality
neural networks
Water quality
water quality
Neural networks
Neural Networks (Computer)
prediction
nests
Benchmarking
Time series
time series analysis
Statistical methods
statistical analysis
flight
methodology
Weights and Measures
Population

ASJC Scopus subject areas

  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Master-leader-slave cuckoo search with parameter control for ANN optimization and its real-world application to water quality prediction. / Jaddi, Najmeh Sadat; Abdullah, Salwani; Malek, Marlinda Abdul.

In: PLoS One, Vol. 12, No. 1, e0170372, 01.01.2017.

Research output: Contribution to journalArticle

@article{343fcc24e7e24bc693f3b7a833dc3a3e,
title = "Master-leader-slave cuckoo search with parameter control for ANN optimization and its real-world application to water quality prediction",
abstract = "Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent L{\'e}vy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.",
author = "Jaddi, {Najmeh Sadat} and Salwani Abdullah and Malek, {Marlinda Abdul}",
year = "2017",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0170372",
language = "English",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

TY - JOUR

T1 - Master-leader-slave cuckoo search with parameter control for ANN optimization and its real-world application to water quality prediction

AU - Jaddi, Najmeh Sadat

AU - Abdullah, Salwani

AU - Malek, Marlinda Abdul

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent Lévy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.

AB - Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent Lévy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.

UR - http://www.scopus.com/inward/record.url?scp=85011661902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011661902&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0170372

DO - 10.1371/journal.pone.0170372

M3 - Article

C2 - 28125609

AN - SCOPUS:85011661902

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 1

M1 - e0170372

ER -