Title :
Neighborhood Counting Measure and Minimum Risk Metric
Author_Institution :
Sch. of Comput. & Math., Univ. of Ulster, Newtownabbey, UK
fDate :
4/1/2010 12:00:00 AM
Abstract :
The neighborhood counting measure is a similarity measure based on the counting of all common neighborhoods in a data space. The minimum risk metric (MRM) is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri refutes a remark about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper is a response to the paper by Argentini and Blanzieri. The original remark is clarified by a combination of theoretical analysis of different implementations of MRM and experimental comparison of MRM and NCM using straightforward implementations of the two measures.
Keywords :
computational complexity; pattern classification; distance measure; minimum risk metric; neighborhood counting measure metric; risk misclassification minimization; theoretical analysis; time complexity; Minimum risk metric; k-nearest neighbor.; neighborhood counting measure;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2010.16
