Accession Number : AD0722647

Title :   The Analysis and Classification of Random Aperiodic Signals.

Descriptive Note : Master's thesis,

Corporate Author : AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OHIO SCHOOL OF ENGINEERING

Personal Author(s) : Hall,Charles F.

Report Date : MAR 1971

Pagination or Media Count : 118

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)

Descriptors :   (*DATA PROCESSING, *PATTERN RECOGNITION), (*TIME SERIES ANALYSIS, SPECTRUM ANALYZERS), FOURIER ANALYSIS, INTEGRAL TRANSFORMS, BANACH SPACE, CLASSIFICATION, LOW PASS FILTERS, ELECTROMAGNETIC PULSES, THESES

Subject Categories : Theoretical Mathematics

Distribution Statement : APPROVED FOR PUBLIC RELEASE