Date of Award

12-1992

Document Type

Thesis

Degree Name

Master of Science in Electrical Engineering

Department

Department of Electrical and Computer Engineering

First Advisor

Steven K. Rogers, PhD

Abstract

This study investigated classification of 30 radar emitters with 16 signal features using Intel's 80170NX chip, the Electronically Trainable Analog Neural Network (ETANN). Software tools were developed to characterize the ETANN sigmoidal transfer function for use in a custom simulator, known as Neural Graphics. Neural Graphics operates on a Silicon Graphics workstation. The Intel Neural Network Training System simulators were used in early experiments, but were found to be inefficient in training on data used in this research. Using a modified Neural Graphics simulator, single chip and multi-chip experiments were performed to provide benchmark results prior to performing chip-in-loop training. By maximizing off-chip training accuracy, the need for on-chip training is minimized and therefore the device life is prolonged. Several single chip and multi-chip configurations were tried; the final architecture which produced the maximum on-chip classification accuracy was a hierarchical network. The maximum on-chip classification accuracy for a single chip implementation of 30 classes without chip-in-loop training was 83 percent. Again without chip-in- loop training, the maximum on-chip classification accuracy for a hierarchical configuration with the 30-class problem was 87 percent.

AFIT Designator

AFIT-GE-ENG-92D-08

DTIC Accession Number

ADA259077

Comments

The author's Vita page is omitted.

Download

Share

COinS