File(s) under permanent embargo
R1SVM: a randomised nonlinear approach to large-scale anomaly detection
conference contribution
posted on 2015-01-01, 00:00 authored by S M Erfani, M Baktashmotlagh, Sutharshan RajasegararSutharshan Rajasegarar, S Karunasekera, C LeckieThe problem of unsupervised anomaly detection arises in a wide variety of practical applications. While one-class support vector machines have demonstrated their effectiveness as an anomaly detection technique, their ability to model large datasets is limited due to their memory and time complexity for training. To address this issue for supervised learning of kernel machines, there has been growing interest in random projection methods as an alternative to the computationally expensive problems of kernel matrix construction and support vector optimisation. In this paper we leverage the theory of nonlinear random projections and propose the Randomised One-class SVM (R1SVM), which is an efficient and scalable anomaly detection technique that can be trained on large-scale datasets. Our empirical analysis on several real-life and synthetic datasets shows that our randomised 1SVM algorithm achieves comparable or better accuracy to deep autoen-coder and traditional kernelised approaches for anomaly detection, while being approximately 100 times faster in training and testing.
History
Event
AAAI Conference on Artificial Intelligence: Workshop 15-14 (29th : 2015 : Austin, Texas)Volume
1Pagination
432 - 438Publisher
AAAI PublicationsLocation
Austin, TexasPlace of publication
Palo Alto, Calif.Start date
2015-01-25End date
2015-01-30ISSN
2374-3468ISBN-13
9781577356998Language
engPublication classification
E Conference publication; E1.1 Full written paper - refereedCopyright notice
2015, AAAI PublicationsEditor/Contributor(s)
[Unknown]Title of proceedings
AAAI 2015: Proceedings of the Artificial Intelligence 2015 ConferenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC