One-Class Classification based on searching for the problem features limits

• Published in: Expert systems with applications 2014-11, Vol.41 (16), p.7182-7199
• Main Authors: Cabral, George G., Oliveira, Adriano L.I.
• Format: Article
• Language: English
• Subjects: Algorithmics. Computability. Computer arithmetics; Anomaly detection; Applied sciences; Breakdown; Classification; Computer science; control theory; systems; Consumer goods; Data processing. List processing. Character string processing; Exact sciences and technology; Expert systems; Mathematics; Memory organisation. Data processing; Monitoring; Nearest neighbor rule; Novelty detection; One-Class Classification; Probability and statistics; Sampling theory, sample surveys; Sciences and techniques of general use; Searching; Software; Statistics; Theoretical computing; Trains
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2014.05.037

•We introduce and analyze a new version of our novelty detection method, namely FBDOCC.•We introduce a heuristic aimed at reducing the training time of the method.•We perform a rigorous theoretical study of the algorithm complexity.•We carry out a number of experiments in order to compare the proposed methods to the methods in the state of the art. Novelty detection is a problem with a large number of relevant applications. For some applications, the main interest is the prevention or detection of undesired states. In some cases, these undesired states are not known in advance; in others, such as machine monitoring, for instance, machine breakdown may be very rare and examples of this event may be unavailable. In such cases, the most widely accepted approach is to model the normal behavior of the system in order to subsequently detect unknown events. This is the basic concept of One-Class Classification (OCC). In some preliminary works we have proposed the Feature Boundaries Detector for One-Class Classification FBDOCC method, which operates by examining each problem feature at a time. In this paper we propose an extensive study of the behavior of the FBDOCC and introduce another version of the method, namely FBDOCC2. This work, also considers the use of the Particle Swarm Optimization (PSO) algorithm to find the best parameter configuration of the proposed method. Furthermore, this work also introduces a procedure to improve the training time performance without degrading the quality of the classification as well as some other contributions hereafter described. A number of experiments were carried out with synthetic and real datasets aiming at comparing both versions of the FBDOCC method with the most recent and effective OCC methods, namely: SVDD, One-class SVM, Least Squares One-class SVM, Kernel PCA, Gaussian Process Prior OCC, Condensed Nearest Neighbor Data Description and One-class Random Forests. The evaluation metrics considered in the experiments are: (i) the Area Under the ROC Curve (AUC); (ii) the Matthews Correlation Coefficient (MCC); (iii) the training time; and (iv) the prototype reduction rate. Regarding the metrics AUC and MCC, the first FBDOCC version has presented the best overall results among all the methods whereas the FBDOCC2 obtained results comparable to the best methods in some experiments where the standard FBDOCC yielded a poorer performance. FBDOCC was the faster method to train in comparison to the other methods in all but on