k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data

Due to the growing amount of data generated and stored in relational databases, relational learning has attracted the interest of researchers in recent years.Many approaches have been developed in order to learn relational data.One of the approaches used to learn relational data is Dynamic Aggregati...

Full description

Bibliographic Details
Main Authors: Alfred, Rayner, Shin, Kung Ke, Sainin, Mohd Shamrie, On, Chin Kim, Pandiyan, Paulraj Murugesa, Ag Ibrahim, Ag Asri
Other Authors: Akagi, Masato
Format: Book Section
Published: Springer International Publishing 2016
Subjects:
_version_ 1825804377764397056
author Alfred, Rayner
Shin, Kung Ke
Sainin, Mohd Shamrie
On, Chin Kim
Pandiyan, Paulraj Murugesa
Ag Ibrahim, Ag Asri
author2 Akagi, Masato
author_facet Akagi, Masato
Alfred, Rayner
Shin, Kung Ke
Sainin, Mohd Shamrie
On, Chin Kim
Pandiyan, Paulraj Murugesa
Ag Ibrahim, Ag Asri
author_sort Alfred, Rayner
collection UUM
description Due to the growing amount of data generated and stored in relational databases, relational learning has attracted the interest of researchers in recent years.Many approaches have been developed in order to learn relational data.One of the approaches used to learn relational data is Dynamic Aggregation of Relational Attributes (DARA).The DARA algorithm is designed to summarize relational data with one-to-many relations. However, DARA suffers a major drawback when the cardinalities of attributes are very high because the size of the vector space representation depends on the number of unique values that exist for all attributes in the dataset.A feature selection process can be introduced to overcome this problem.These selected features can be further optimized to achieve a good classification result.Several clustering runs can be performed for different values of k to yield an ensemble of clustering results. This paper proposes a two-layered genetic algorithm-based feature selection in order to improve the classification performance of learning relational database using a k-NN ensemble classifier.The proposed method involves the task of omitting less relevant features but retaining the diversity of the classifiers so as to improve the performance of the k-NN ensemble. The result shows that the proposed k-NN ensemble is able to improve the performance of traditional k-NN classifiers.
first_indexed 2024-07-04T06:13:33Z
format Book Section
id uum-20483
institution Universiti Utara Malaysia
last_indexed 2024-07-04T06:13:33Z
publishDate 2016
publisher Springer International Publishing
record_format eprints
spelling uum-204832017-01-02T08:37:24Z https://repo.uum.edu.my/id/eprint/20483/ k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data Alfred, Rayner Shin, Kung Ke Sainin, Mohd Shamrie On, Chin Kim Pandiyan, Paulraj Murugesa Ag Ibrahim, Ag Asri QA75 Electronic computers. Computer science Due to the growing amount of data generated and stored in relational databases, relational learning has attracted the interest of researchers in recent years.Many approaches have been developed in order to learn relational data.One of the approaches used to learn relational data is Dynamic Aggregation of Relational Attributes (DARA).The DARA algorithm is designed to summarize relational data with one-to-many relations. However, DARA suffers a major drawback when the cardinalities of attributes are very high because the size of the vector space representation depends on the number of unique values that exist for all attributes in the dataset.A feature selection process can be introduced to overcome this problem.These selected features can be further optimized to achieve a good classification result.Several clustering runs can be performed for different values of k to yield an ensemble of clustering results. This paper proposes a two-layered genetic algorithm-based feature selection in order to improve the classification performance of learning relational database using a k-NN ensemble classifier.The proposed method involves the task of omitting less relevant features but retaining the diversity of the classifiers so as to improve the performance of the k-NN ensemble. The result shows that the proposed k-NN ensemble is able to improve the performance of traditional k-NN classifiers. Springer International Publishing Akagi, Masato Nguyen, Thanh-Thuy Vu, Duc-Thai Phung, Trung-Nghia Huynh, Van-Nam 2016 Book Section PeerReviewed Alfred, Rayner and Shin, Kung Ke and Sainin, Mohd Shamrie and On, Chin Kim and Pandiyan, Paulraj Murugesa and Ag Ibrahim, Ag Asri (2016) k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data. In: Advances in Information and Communication Technology. Springer International Publishing, pp. 322-331. ISBN 978-3-319-49072-4 http://doi.org/10.1007/978-3-319-49073-1_35 doi:10.1007/978-3-319-49073-1_35 doi:10.1007/978-3-319-49073-1_35
spellingShingle QA75 Electronic computers. Computer science
Alfred, Rayner
Shin, Kung Ke
Sainin, Mohd Shamrie
On, Chin Kim
Pandiyan, Paulraj Murugesa
Ag Ibrahim, Ag Asri
k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title_full k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title_fullStr k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title_full_unstemmed k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title_short k-nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
title_sort k nearest neighbour using ensemble clustering based on feature selection approach to learning relational data
topic QA75 Electronic computers. Computer science
work_keys_str_mv AT alfredrayner knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata
AT shinkungke knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata
AT saininmohdshamrie knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata
AT onchinkim knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata
AT pandiyanpaulrajmurugesa knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata
AT agibrahimagasri knearestneighbourusingensembleclusteringbasedonfeatureselectionapproachtolearningrelationaldata