Nearest neighbour distance matrix classification

A distance based classification is one of the popular methods for classifying instances using a point-to-point distance based on the nearest neighbour or k-NEAREST NEIGHBOUR (k-NN).The representation of distance measure can be one of the various measures available (e.g. Euclidean distance, Manhattan...

Full description

Saved in:
Bibliographic Details
Main Authors: Sainin, Mohd Shamrie, Alfred, Rayner
Other Authors: Longbing, Chao
Format: Book Section
Published: Springer 2010
Subjects:
Online Access:http://repo.uum.edu.my/12419/
http://dx.doi.org/10.1007/978-3-642-17316-5_11
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uum.repo.12419
record_format eprints
spelling my.uum.repo.124192014-10-23T07:36:09Z http://repo.uum.edu.my/12419/ Nearest neighbour distance matrix classification Sainin, Mohd Shamrie Alfred, Rayner QA76 Computer software A distance based classification is one of the popular methods for classifying instances using a point-to-point distance based on the nearest neighbour or k-NEAREST NEIGHBOUR (k-NN).The representation of distance measure can be one of the various measures available (e.g. Euclidean distance, Manhattan distance, Mahalanobis distance or other specific distance measures).In this paper, we propose a modified nearest neighbour method called Nearest Neighbour Distance Matrix (NNDM) for classification based on unsupervised and supervised distance matrix.In the proposed NNDM method, an Euclidean distance method coupled with a distance loss function is used to create a distance matrix. In our approach, distances of each instance to the rest of the training instances data will be used to create the training distance matrix (TADM). Then, the TADM will be used to classify a new instance.In supervised NNDM, two instances that belong to different classes will be pushed apart from each other. This is to ensure that the instances that are located next to each other belong to the same class. Based on the experimental results, we found that the trained distance matrix yields reasonable performance in classification. Springer Longbing, Chao Yong, Feng Jiang, Zhong 2010 Book Section PeerReviewed Sainin, Mohd Shamrie and Alfred, Rayner (2010) Nearest neighbour distance matrix classification. In: Advanced Data Mining and Applications. Lecture Notes in Computer Science, 6440 . Springer, pp. 114-124. ISBN 978-3-642-17315-8 http://dx.doi.org/10.1007/978-3-642-17316-5_11 doi:10.1007/978-3-642-17316-5_11
institution Universiti Utara Malaysia
building UUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Utara Malaysia
content_source UUM Institutionali Repository
url_provider http://repo.uum.edu.my/
topic QA76 Computer software
spellingShingle QA76 Computer software
Sainin, Mohd Shamrie
Alfred, Rayner
Nearest neighbour distance matrix classification
description A distance based classification is one of the popular methods for classifying instances using a point-to-point distance based on the nearest neighbour or k-NEAREST NEIGHBOUR (k-NN).The representation of distance measure can be one of the various measures available (e.g. Euclidean distance, Manhattan distance, Mahalanobis distance or other specific distance measures).In this paper, we propose a modified nearest neighbour method called Nearest Neighbour Distance Matrix (NNDM) for classification based on unsupervised and supervised distance matrix.In the proposed NNDM method, an Euclidean distance method coupled with a distance loss function is used to create a distance matrix. In our approach, distances of each instance to the rest of the training instances data will be used to create the training distance matrix (TADM). Then, the TADM will be used to classify a new instance.In supervised NNDM, two instances that belong to different classes will be pushed apart from each other. This is to ensure that the instances that are located next to each other belong to the same class. Based on the experimental results, we found that the trained distance matrix yields reasonable performance in classification.
author2 Longbing, Chao
author_facet Longbing, Chao
Sainin, Mohd Shamrie
Alfred, Rayner
format Book Section
author Sainin, Mohd Shamrie
Alfred, Rayner
author_sort Sainin, Mohd Shamrie
title Nearest neighbour distance matrix classification
title_short Nearest neighbour distance matrix classification
title_full Nearest neighbour distance matrix classification
title_fullStr Nearest neighbour distance matrix classification
title_full_unstemmed Nearest neighbour distance matrix classification
title_sort nearest neighbour distance matrix classification
publisher Springer
publishDate 2010
url http://repo.uum.edu.my/12419/
http://dx.doi.org/10.1007/978-3-642-17316-5_11
_version_ 1644280907451858944
score 13.209306