Relationship between Variants of One-Class Nearest Neighbours and Creating their Accurate Ensembles
نویسندگان
چکیده
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 neighbour (OCNN) classifiers and their different variants. We present a theoretical analysis to show the relationships among different variants of OCNN that may use different neighbours 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 to use two ensemble approaches based on random subspace and random projection methods to create accurate OCNN ensembles that significantly outperforms the baseline OCNN. We tested the proposed methods on 15 benchmark and real world domain-specific datasets to show their superior performance. The results give strong evidence that the random projection ensemble of the proposed OCNN with optimized parameters perform significantly and consistently better than the single OCNN on all the tested datasets.
منابع مشابه
Ensembles of Nearest Neighbours for Cancer Classification Using Gene Expression Data
It is known that an ensemble of classifiers can outperform a single best classifier if classifiers in the ensemble are sufficiently diverse (i.e., their errors are as much uncorrelated as possible) and accurate. We study ensembles of nearest neighbours for cancer classification based on gene expression data. Such ensembles have been rarely used, because the traditional ensemble methods such as ...
متن کاملPseudo-Likelihood Inference Underestimates Model Uncertainty: Evidence from Bayesian Nearest Neighbours
When using the K-nearest neighbours (KNN) method, one often ignores the uncertainty in the choice of K. To account for such uncertainty, Bayesian KNN (BKNN) has been proposed and studied (Holmes and Adams 2002 Cucala et al. 2009). We present some evidence to show that the pseudo-likelihood approach for BKNN, even after being corrected by Cucala et al. (2009), still significantly underest...
متن کامل2 3 Ja n 20 06 Test of Universality in Anisotropic 3 D Ising Model
Chen and Dohm predicted theoretically in 2004 that the widely believed universality principle is violated in the Ising model on the simple cubic lattice with more than only six nearest neighbours. Schulte and Drope by Monte Carlo simulations found such violation, but not in the predicted direction. Selke and Shchur tested the square lattice. Here we check only this univer-sality for the suscept...
متن کاملEnsembles of nearest neighbour classifiers and serial analysis of gene expression
In this paper, we represent experimental results obtained with ensembles of nearest neighbour classifiers on the binary classification problem of cancer classification using serial analysis of gene expression (SAGE) data. Nearest neighbours are selected as classifiers since they were rarely employed in building ensembles because their predictions are stable to small perturbations of data, which...
متن کاملNearest-neighbour classifiers in natural scene analysis
It is now well-established that k nearest-neighbour classi"ers o!er a quick and reliable method of data classi"cation. In this paper we extend the basic de"nition of the standard k nearest-neighbour algorithm to include the ability to resolve con#icts when the highest number of nearest neighbours are found for more than one training class (model-1). We also propose model-2 of nearest-neighbour ...
متن کامل