A Novel Template Reduction Approach for the K-Nearest Neighbor Method

The K -nearest neighbor (KNN) rule is one of the most widely used pattern classification algorithms. For large data sets, the computational demands for classifying patterns using KNN can be prohibitive. A way to alleviate this problem is through the condensing approach. This means we remove patterns...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on neural networks Vol. 20; no. 5; pp. 890 - 896
Main Authors Fayed, H.A., Atiya, A.F.
Format Journal Article
LanguageEnglish
Published New York, NY IEEE 01.05.2009
Institute of Electrical and Electronics Engineers
Subjects
Accuracy
Algorithms
Applied sciences
Artificial intelligence
Boundaries
Cellular neural networks
Chains
Classification
Classification algorithms
Computation
Computer science; control theory; systems
Condensing
Connectionism. Neural networks
cross validation
Design engineering
editing
Exact sciences and technology
K -nearest neighbor (KNN)
Layout
Mathematics
Medical diagnosis
Nearest neighbor searches
Neural networks
Pattern classification
Prototypes
Satellites
template reduction
Nearest neighbour
Pattern classification
Very large databases
Condensing
Nearest neighbor approximation
Cross validation
Neural network
template reduction
Fast algorithm
K-nearest neighbor (KNN)
editing
Online AccessGet full text

Cover

More Information
Summary:The K -nearest neighbor (KNN) rule is one of the most widely used pattern classification algorithms. For large data sets, the computational demands for classifying patterns using KNN can be prohibitive. A way to alleviate this problem is through the condensing approach. This means we remove patterns that are more of a computational burden but do not contribute to better classification accuracy. In this brief, we propose a new condensing algorithm. The proposed idea is based on defining the so-called chain. This is a sequence of nearest neighbors from alternating classes. We make the point that patterns further down the chain are close to the classification boundary and based on that we set a cutoff for the patterns we keep in the training set. Experiments show that the proposed approach effectively reduces the number of prototypes while maintaining the same level of classification accuracy as the traditional KNN. Moreover, it is a simple and a fast condensing algorithm.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1045-9227
1941-0093
DOI:10.1109/TNN.2009.2018547