Estimation of high-density regions using one-class neighbor machines

Muñoz, Alberto; Moguerza, Javier M.

doi:10.1109/tpami.2006.52

Cited by 57 publications

(40 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Muñoz and Moguerza propose the One-Class Neighbour Machine (OCNM) algorithm for estimating minimum volume sets [16]. The OCNM algorithm is a block-based procedure that provides a binary decision function indicating whether x t is a member of the MVS or not.…”

Section: B Minimum Volume Setsmentioning

confidence: 99%

Multivariate Online Anomaly Detection Using Kernel Recursive Least Squares

Ahmed

Coates

Lakhina

2007

IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications

115

View full text Add to dashboard Cite

Abstract-High-speed backbones are regularly affected by various kinds of network anomalies, ranging from malicious attacks to harmless large data transfers. Different types of anomalies affect the network in different ways, and it is difficult to know a priori how a potential anomaly will exhibit itself in traffic statistics. In this paper we describe an online, sequential, anomaly detection algorithm, that is suitable for use with multivariate data. The proposed algorithm is based on the kernel version of the recursive least squares algorithm. It assumes no model for network traffic or anomalies, and constructs and adapts a dictionary of features that approximately spans the subspace of normal behaviour. The algorithm raises an alarm immediately upon encountering a deviation from the norm. Through comparison with existing block-based offline methods based upon Principal Component Analysis, we demonstrate that our online algorithm is equally effective but has much faster time-to-detection and lower computational complexity. We also explore minimum volume set approaches in identifying the region of normality.

show abstract

Section: B Minimum Volume Setsmentioning

confidence: 99%

Multivariate Online Anomaly Detection Using Kernel Recursive Least Squares

Ahmed

Coates

Lakhina

2007

IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications

115

View full text Add to dashboard Cite

show abstract

“…Regarding further research, a natural extension is to study the application of this methodology to non-supervised problems (see, for instance, Muñoz and Moguerza 2006), and straightforwardly its use within other kernel-based classification methods.…”

Section: Discussionmentioning

confidence: 99%

“…It is important to remark that the representation z x is calculated (for every data point) using always the training data set, that is, we are defining a kernel whose expression in closed-form depends on a fixed data sample (the training set, see for instance, Muñoz and Moguerza 2006). From a computational point of view, this technique is very cheap in practice as it only requires a product of two matrices and it is advisable when the size of the kernel matrix involved is large.…”

Section: Second Power Of the Kernel Matrixmentioning

confidence: 99%

Methods for the combination of kernel matrices within a support vector framework

2009

View full text Add to dashboard Cite

The problem of combining different sources of information arises in several situations, for instance, the classification of data with asymmetric similarity matrices or the construction of an optimal classifier from a collection of kernels. Often, each source of information can be expressed as a similarity matrix. In this paper we propose a new class of methods in order to produce, for classification purposes, a single kernel matrix from a collection of kernel (similarity) matrices. Then, the constructed kernel matrix is used to train a Support Vector Machine (SVM). The key ideas within the kernel construction are twofold: the quantification, relative to the classification labels, of the difference of information among the similarities; and the extension of the concept of linear combination of similarity matrices to the concept of functional combination of similarity matrices. The proposed methods have been successfully evaluated and compared with other powerful classifiers and kernel combination techniques on a variety of artificial and real classification problems.

show abstract

“…We use a nearest centroid (NC) method for classification, in which a new measurement x i is assigned to category j, for which the distance between w T x i and w T μ j is minimal. Many other classifier choices are possible in the reduced R c−1 space, including nearest neighbor (NN) [20], nearest subspace [38], support vector machines (SVM) [42], and sparse representation for classification (SRC) [61]. While it is possible that these classifiers may improve the accuracy of the decision, we restricted our attention to NC since the focus of this work is not on the specific classifier algorithm, but rather on the method of learning sensor locations.…”

Section: Pca Lda and Classificationmentioning

confidence: 99%

Sparse Sensor Placement Optimization for Classification

Brunton¹,

Brunton²,

Proctor³

et al. 2016

SIAM J. Appl. Math.

View full text Add to dashboard Cite

Abstract. Choosing a limited set of sensor locations to characterize or classify a high-dimensional system is an important challenge in engineering design. Traditionally, optimizing the sensor locations involves a brute-force, combinatorial search, which is NP-hard and is computationally intractable for even moderately large problems. Using recent advances in sparsity-promoting techniques, we present a novel algorithm to solve this sparse sensor placement optimization for classification (SSPOC) that exploits low-dimensional structure exhibited by many high-dimensional systems. Our approach is inspired by compressed sensing, a framework that reconstructs data from few measurements. If only classification is required, reconstruction can be circumvented and the measurements needed are orders-of-magnitude fewer still. Our algorithm solves an 1 minimization to find the fewest nonzero entries of the full measurement vector that exactly reconstruct the discriminant vector in feature space; these entries represent sensor locations that best inform the decision task. We demonstrate the SSPOC algorithm on five classification tasks, using datasets from a diverse set of examples, including physical dynamical systems, image recognition, and microarray cancer identification. Once training identifies sensor locations, data taken at these locations forms a low-dimensional measurement space, and we perform computationally efficient classification with accuracy approaching that of classification using full-state data. The algorithm also works when trained on heavily subsampled data, eliminating the need for unrealistic full-state training data.

show abstract

Estimation of high-density regions using one-class neighbor machines

Cited by 57 publications

References 7 publications

Multivariate Online Anomaly Detection Using Kernel Recursive Least Squares

Multivariate Online Anomaly Detection Using Kernel Recursive Least Squares

Methods for the combination of kernel matrices within a support vector framework

Sparse Sensor Placement Optimization for Classification

Contact Info

Product

Resources

About