The Analysis and Classification of Random Aperiodic Signals.

Abstract

Two classes of random aperiodic signals were analyzed using one- and two-dimensional Fourier transforms. Low-frequency filtering in the transform domain and the Euclidean distance metric were used to classify signals in one of the two classes. Linear decision boundaries, clustering algorithms, and a training algorithm using a linear categorizer were also used during the analysis. It was found that low-frequency spatial filtering in the two-dimensional Fourier-transform domain gave complete separation of the two classes of signals analyzed. (Author)

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1971
Accession Number
AD0722647

Entities

People

  • Charles F. Hall

Organizations

  • Air Force Institute of Technology

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Classification
  • Clustering
  • Dispersing
  • Filtration
  • Frequency
  • Spatial Filtering
  • Training
  • Two Dimensional

Fields of Study

  • Engineering

Readers

  • Image Processing and Computer Vision.
  • Mathematical Modeling and Probability Theory.
  • Neural Network Machine Learning.