Controlling false alarms with support vector machines

Mark A. Davenport, Richard G. Baraniuk, Clayton D. Scott

Research output: Chapter in Book/Report/Conference proceedingConference contribution

43 Scopus citations

Abstract

We study the problem of designing support vector classifiers with respect to a Neyman-Pearson criterion. Specifically, given a user-specified level α ε (0,1), how can we ensure a false alarm rate no greater than α while minimizing the miss rate? We examine two approaches, one based on shifting the offset of a conventionally trained SVM and the other based on the introduction of classspecific weights. Our contributions include a novel heuristic for improved error estimation and a strategy for efficiently searching the parameter space of the second method. We also provide a characterization of the feasible parameter set of the 2ν-SVM on which the second approach is based. The proposed methods are compared on four benchmark datasets.

Original languageEnglish (US)
Title of host publication2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
Volume5
StatePublished - Dec 1 2006
Event2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 - Toulouse, France
Duration: May 14 2006May 19 2006

Other

Other2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
Country/TerritoryFrance
CityToulouse
Period5/14/065/19/06

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Controlling false alarms with support vector machines'. Together they form a unique fingerprint.

Cite this