Automatic Classification of Digitally Modulated Signals.

Abstract

This experiment investigates the performance of an adaptive technique for the classification of the following types of digitally modulated signals: binary amplitude shift keying (BASK), binary phase shift keying (BPSK), quaternary phase shift keying (QPSK), and binary frequency shift keying (BFSK). The feature extraction process uses the mean and variance of the signal, and magnitudes and locations of the maxima in the spectrum of the signal, the spectrum of the signal squared, and the spectrum of the signal raised to the fourth power. The process of raising the signal to the second and fourth power and searching for narrowband energy near twice and four times the intermediate frequency is shown to provide useful information for the classification of BPSK and QPSK signals. A computer simulation is performed to measure the properties of the classifier. First, the classifier is trained with a set of feature vectors calculated from 20 dB SNR signals. The Least Mean Squares (IMS) algorithm is the adaptive procedure used to generate the weight vectors used to form the linear decision functions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1987
Accession Number
ADA194623

Entities

People

  • Martin P. Desimio

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Electronic Warfare
  • Energy and Power Technologies
  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Amplitude Modulation
  • Bandwidth
  • Carrier Frequencies
  • Demodulation
  • Department Of Defense
  • Detection
  • Detectors
  • Electrical Engineering
  • Engineering
  • Feature Extraction
  • Frequency Shift
  • Intermediate Frequencies
  • Literature Surveys
  • Modulation
  • Notation
  • Signal Processing

Fields of Study

  • Engineering

Readers

  • Approximation Theory.
  • Neural Network Machine Learning.
  • Radio communications and signal processing.

Technology Areas

  • AI & ML