Open AccessProceedings Article
Blind Data Classification using Hyper-Dimensional Convex Polytopes
Brent T. McBride,Gilbert L. Peterson +1 more
- 01 Jan 2004
pp 520-525
TL;DR: A blind classification algorithm is presented that uses hyperdimensional geometric algorithms to locate a hypothesis, in the form of a convex polytope or hyper-sphere, resulting in a hybrid anomaly/signature-based classifier.
read more
Abstract: A blind classification algorithm is presented that uses hyperdimensional geometric algorithms to locate a hypothesis, in the form of a convex polytope or hyper-sphere. The convex polytope geometric model provides a well-fitted class representation that does not require training with instances of opposing classes. Further, the classification algorithm creates models for as many training classes of data as are available resulting in a hybrid anomaly/signature-based classifier. A method for handling non-numeric data types is explained. Classification accuracy is enhanced through the
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
An empirical Bayes approach to detect anomalies in dynamic multidimensional arrays
D. Agarwal
- 27 Nov 2005
TL;DR: An empirical Bayes method is used which works by fitting a two component Gaussian mixture to deviations at current time to suppress deviations that are merely the consequence of sharp changes in the marginal distributions.
61
A new blind method for detecting novel steganography
TL;DR: A blind classification algorithm that uses hyper-dimensional geometric methods to model steganography-free jpeg images and provides superior anomaly detection compared to previous research, which increases Jsteg detection accuracy to 95%.
48
Steganography anomaly detection using simple one-class classification
Benjamin M. Rodriguez,Gilbert L. Peterson,Sos S. Agaian +2 more
- 02 May 2007
TL;DR: Two methods are compared that classify cell phone images as either an anomaly or clean, where a clean image is one in which no alterations have been made and an anomalous image isone in which information has been hidden within the image.
14
Steganalysis Embedding Percentage Determination with Learning Vector Quantization
Benjamin M. Rodriguez,Gilbert L. Peterson,Kenneth W. Bauer,Sos S. Agaian +3 more
- 01 Oct 2006
TL;DR: The results demonstrate that LVQ not only more accurately identify when an image contains LSB hidden information when compared to k-means or using just the raw feature sets, but also provides a simple method for determining the percentage of embedding given low information embedding percentages.
13
The importance of generalizability for anomaly detection
TL;DR: This article confirms that in anomaly detection as in other forms of classification a tight fit does not supersede model generality and is shown using three systems each with a different geometric bias in the decision space.
12
References
The quickhull algorithm for convex hulls
TL;DR: This article presents a practical convex hull algorithm that combines the two-dimensional Quickhull algorithm with the general-dimension Beneath-Beyond Algorithm, and provides empirical evidence that the algorithm runs faster when the input contains nonextreme points and that it used less memory.
Three-dimensional alpha shapes
TL;DR: This article introduces the formal notion of the family of α-shapes of a finite point set in R 3 .
2.2K
Three-dimensional alpha shapes
Herbert Edelsbrunner,Ernst Peter Mucke +1 more
- 01 Dec 1992
TL;DR: This article introduces the formal notion of the family of α-shapes of a finite point set in R, a well-defined polytope, derived from the Delaunay triangulation of the point set, with a parameter α ε R controlling the desired level of detail.
1.1K
•Posted Content
Three-dimensional alpha shapes
TL;DR: In this paper, the authors introduce the formal notion of the family of α-shapes of a finite point set in real time, where α is a well-defined polytope, derived from the Delaunay triangulation of the point set.