Abstract
In one-class classification problems, only the data for the target class is available, whereas the data for the non-target class may be completely absent. In this paper, we study one-class nearest neighbor (OCNN) classifiers and their different variants. We present a theoretical analysis to show the relationships among different variants of OCNN that may use different neighbors or thresholds to identify unseen examples of the non-target class. We also present a method based on inter-quartile range for optimizing parameters used in OCNN in the absence of non-target data during training. Then, we propose two ensemble approaches based on random subspace and random projection methods to create accurate OCNN ensembles. We tested the proposed methods on 15 benchmark and real world domain-specific datasets and show that random-projection ensembles of OCNN perform best.
Original language | English |
---|---|
Article number | 8293843 |
Pages (from-to) | 1796-1809 |
Number of pages | 14 |
Journal | IEEE Transactions on Knowledge and Data Engineering |
Volume | 30 |
Issue number | 9 |
DOIs | |
Publication status | Published - Sept 1 2018 |
Keywords
- One-class classification
- classifier ensemble
- nearest neighbor
- random projection
- random subspace
ASJC Scopus subject areas
- Information Systems
- Computer Science Applications
- Computational Theory and Mathematics