Reducing non-determinism of k-NN searching in non-ordered discrete data spaces |
| |
Authors: | Dashiell Kolbe Qiang Zhu |
| |
Affiliation: | a Michigan State University, East Lansing, MI, United States b University of Michigan - Dearborn, Dearborn, MI, United States |
| |
Abstract: | We propose a generalized version of the Granularity-Enhanced Hamming (GEH) distance for use in k-NN queries in non-ordered discrete data spaces (NDDS). The use of the GEH distance metric improves search semantics by reducing the degree of non-determinism of k-NN queries in NDDSs. The generalized form presented here enables the GEH distance to be used for a much greater variety of scenarios than was possible with the original form. |
| |
Keywords: | Algorithms Databases Information retrieval Non-ordered discrete data space k-nearest neighbor search |
本文献已被 ScienceDirect 等数据库收录! |