Target detecting neural network architecture for serial sensor data streams

Tim L. Overman, Ahmed Louri

Research output: Contribution to conferencePaperpeer-review

Abstract

A Neural Network Target Detection Architecture is presented based on the Multilayer Perceptron Neural Receiver defined by Watterson. The neural network was trained to detect a Gaussian spot and allowed to detect the target through various levels of white Gaussian noise. Investigation into the architecture's performance through Monte Carlo simulations shows that the architecture gives 75% improvement in the probability of detection than the Rayleigh Channel Receiver. Finally, the real-time computing requirements for the neural network architecture are addressed and presented.

Original languageEnglish (US)
Pages393-403
Number of pages11
StatePublished - Dec 1 1994
EventProceedings of the Electro'94 International Conference - Boston, MA, USA
Duration: May 10 1994May 12 1994

Other

OtherProceedings of the Electro'94 International Conference
CityBoston, MA, USA
Period5/10/945/12/94

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Target detecting neural network architecture for serial sensor data streams'. Together they form a unique fingerprint.

Cite this