A fast hybrid classification algorithm based on the minimum distance and the k-NN classifiers

Authors:
Stefanos Ougiaroglou;Georgios Evangelidis;Dimitris A. Dervos
Affiliations:
University of Macedonia, Thessaloniki, Greece;University of Macedonia, Thessaloniki, Greece;Alexander T. E. I. of Thessaloniki, Sindos, Greece
Venue:
Proceedings of the Fourth International Conference on SImilarity Search and APplications
Year:
2011

Citing 13
Cited 0

Classification algorithms

Classification algorithms
A sample set condensation algorithm for the class sensitive artificial neural network

Pattern Recognition Letters
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Data structures and algorithms for nearest neighbor search in general metric spaces

SODA '93 Proceedings of the fourth annual ACM-SIAM Symposium on Discrete algorithms
Distance browsing in spatial databases

ACM Transactions on Database Systems (TODS)
Reduction Techniques for Instance-BasedLearning Algorithms

Machine Learning
Data mining: concepts and techniques

Data mining: concepts and techniques
On the effects of dimensionality reduction on high dimensional similarity search

PODS '01 Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
The K-D-B-tree: a search structure for large multidimensional dynamic indexes

SIGMOD '81 Proceedings of the 1981 ACM SIGMOD international conference on Management of data
R-trees: a dynamic index structure for spatial searching

SIGMOD '84 Proceedings of the 1984 ACM SIGMOD international conference on Management of data
Centroid-Based Document Classification: Analysis and Experimental Results

PKDD '00 Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery
A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
The k-Nearest Neighbour Join: Turbo Charging the KDD Process

Knowledge and Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some of the most commonly used classifiers are based on the retrieval and examination of the k Nearest Neighbors of unclassified instances. However, since the size of datasets can be large, these classifiers are inapplicable when the time-costly sequential search over all instances is used to find the neighbors. The Minimum Distance Classifier is a very fast classification approach but it usually achieves much lower classification accuracy than the k-NN classifier. In this paper, a fast, hybrid and model-free classification algorithm is introduced that combines the Minimum Distance and the k-NN classifiers. The proposed algorithm aims at maximizing the reduction of computational cost, by keeping classification accuracy at a high level. The experimental results illustrate that the proposed approach can be applicable in dynamic, time-constrained environments.