Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering

Affinity propagation (AP) clustering is a well-known effective clustering algorithm that outperforms other traditional clustering algorithms. However, the quality of clustering results depends considerably on related sensitive parameters (i.e., preferences and the damping factor). Thus, a feasible p...

Full description

Bibliographic Details
Main Authors: Libin Jiao, Rongfang Bie, Guangzhi Zhang, Shenling Wang, Rashid Mehmood
Format: Article
Language:English
Published: SAGE Publishing 2016-07-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/155014779807206
id doaj-c7fa0ea3dd304f15aaf132afd2f95cea
record_format Article
spelling doaj-c7fa0ea3dd304f15aaf132afd2f95cea2020-11-25T03:34:05ZengSAGE PublishingInternational Journal of Distributed Sensor Networks1550-14772016-07-011210.1177/155014779807206Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation ClusteringLibin Jiao0Rongfang Bie1Guangzhi Zhang2Shenling Wang3Rashid Mehmood4 College of Information Science and Technology, Beijing Normal University, Beijing 100875, China College of Information Science and Technology, Beijing Normal University, Beijing 100875, China College of Information Science and Technology, Beijing Normal University, Beijing 100875, China College of Information Science and Technology, Beijing Normal University, Beijing 100875, China Department of Computer Science and Information Technology, University of Management Sciences and Information Technology, Kotli, Azad Jammu and Kashmir 11100, PakistanAffinity propagation (AP) clustering is a well-known effective clustering algorithm that outperforms other traditional clustering algorithms. However, the quality of clustering results depends considerably on related sensitive parameters (i.e., preferences and the damping factor). Thus, a feasible procedure based on golden section (GS) and the genetic algorithm (GA) is proposed. This procedure, called the “GS/GA-AP” algorithm, can perform proper global shared preference detection, including identifying a suitable number of clusters. A global shared preference is provided using the GS value between the minimum and maximum of similarities for AP as a default option, and the unsatisfactory clustering result becomes robust when the parameter with GA is selected. Finally, satisfactory experiments using one simulation data set and eight benchmark data sets are performed to verify the effectiveness of the proposed algorithm. The results indicate that GS/GA-AP clearly outperforms the original AP clustering algorithm.https://doi.org/10.1177/155014779807206
collection DOAJ
language English
format Article
sources DOAJ
author Libin Jiao
Rongfang Bie
Guangzhi Zhang
Shenling Wang
Rashid Mehmood
spellingShingle Libin Jiao
Rongfang Bie
Guangzhi Zhang
Shenling Wang
Rashid Mehmood
Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
International Journal of Distributed Sensor Networks
author_facet Libin Jiao
Rongfang Bie
Guangzhi Zhang
Shenling Wang
Rashid Mehmood
author_sort Libin Jiao
title Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
title_short Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
title_full Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
title_fullStr Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
title_full_unstemmed Proper Global Shared Preference Detection Based on Golden Section and Genetic Algorithm for Affinity Propagation Clustering
title_sort proper global shared preference detection based on golden section and genetic algorithm for affinity propagation clustering
publisher SAGE Publishing
series International Journal of Distributed Sensor Networks
issn 1550-1477
publishDate 2016-07-01
description Affinity propagation (AP) clustering is a well-known effective clustering algorithm that outperforms other traditional clustering algorithms. However, the quality of clustering results depends considerably on related sensitive parameters (i.e., preferences and the damping factor). Thus, a feasible procedure based on golden section (GS) and the genetic algorithm (GA) is proposed. This procedure, called the “GS/GA-AP” algorithm, can perform proper global shared preference detection, including identifying a suitable number of clusters. A global shared preference is provided using the GS value between the minimum and maximum of similarities for AP as a default option, and the unsatisfactory clustering result becomes robust when the parameter with GA is selected. Finally, satisfactory experiments using one simulation data set and eight benchmark data sets are performed to verify the effectiveness of the proposed algorithm. The results indicate that GS/GA-AP clearly outperforms the original AP clustering algorithm.
url https://doi.org/10.1177/155014779807206
work_keys_str_mv AT libinjiao properglobalsharedpreferencedetectionbasedongoldensectionandgeneticalgorithmforaffinitypropagationclustering
AT rongfangbie properglobalsharedpreferencedetectionbasedongoldensectionandgeneticalgorithmforaffinitypropagationclustering
AT guangzhizhang properglobalsharedpreferencedetectionbasedongoldensectionandgeneticalgorithmforaffinitypropagationclustering
AT shenlingwang properglobalsharedpreferencedetectionbasedongoldensectionandgeneticalgorithmforaffinitypropagationclustering
AT rashidmehmood properglobalsharedpreferencedetectionbasedongoldensectionandgeneticalgorithmforaffinitypropagationclustering
_version_ 1724560689312301056