Lake bed classification using acoustic data

Applied Mathematics and Computer Science
By: , and 


  • The Publications Warehouse does not have links to digital versions of this publication at this time
  • Download citation as: RIS | Dublin Core


As part of our effort to identify the lake bed surficial substrates using remote sensing data, this work designs pattern classifiers by multivariate statistical methods. Probability distribution of the preprocessed acoustic signal is analyzed first. A confidence region approach is then adopted to improve the design of the existing classifier. A technique for further isolation is proposed which minimizes the expected loss from misclassification. The devices constructed are applicable for real-time lake bed categorization. A mimimax approach is suggested to treat more general cases where the a priori probability distribution of the substrate types is unknown. Comparison of the suggested methods with the traditional likelihood ratio tests is discussed.
Publication type Article
Publication Subtype Journal Article
Title Lake bed classification using acoustic data
Series title Applied Mathematics and Computer Science
Volume 8
Issue 4
Year Published 1998
Language English
Contributing office(s) Great Lakes Science Center
Description p. 841-864
Larger Work Type Article
Larger Work Subtype Journal Article
Larger Work Title Applied Mathematics and Computer Science
First page 841
Last page 864
Google Analytic Metrics Metrics page
Additional publication details