Model Selection for Anomaly Detection

Abstract

Anomaly detection based on one-class classification algorithms is broadly used in many applied domains like image processing (e.g. detection of whether a patient is "cancerous" or "healthy" from mammography image), network intrusion detection, etc. Performance of an anomaly detection algorithm crucially depends on a kernel, used to measure similarity in a feature space. The standard approaches (e.g. cross-validation) for kernel selection, used in two-class classification problems, can not be used directly due to the specific nature of a data (absence of a second, abnormal, class data). In this paper we generalize several kernel selection methods from binary-class case to the case of one-class classification and perform extensive comparison of these approaches using both synthetic and real-world data.

6 pages, 3 figures, Eighth International Conference on Machine Vision (December 8, 2015)

References in corpus (1)

• Influence of Resampling on Accuracy of Imbalanced Classification

Cited by in corpus (6)

• A Predictive Model for Steady-State Multiphase Pipe Flow: Machine Learning on Lab Data
• Inductive Conformal Martingales for Change-Point Detection
• DCSO: Dynamic Combination of Detector Scores for Outlier Ensembles
• Conformalized density- and distance-based anomaly detection in time-series data
• Learning Ensembles of Anomaly Detectors on Synthetic Data
• Usage of multiple RTL features for Earthquake prediction