Neural Network Constant False Alarm Rate Detection

Abstract

This document presents an approach to augmenting and improving cell averaging constant false alarm detectors with a neural network based approach. The simulated results show that the neural network is able to perform as well as the optimal detector and remove the losses typically associated with estimating the noise power in standard approaches. A feasible implementation of the neural network detector is also presented. Preliminary results demonstrate that the neural network requires the same inputs as the cell averaging constant false alarm rate detector and can work across a range of unknown input signal to noise ratios.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 25, 2023
Accession Number
AD1206723

Entities

People

  • Huy V. Le
  • Kevin Wagner

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Computations
  • Computing System Architectures
  • Data Sets
  • Detection
  • Detectors
  • Dimensionality Reduction
  • False Alarms
  • Information Science
  • Information Theory
  • Machine Learning
  • Network Architecture
  • Neural Networks
  • Pattern Recognition
  • Probability
  • Radar
  • Signal Processing
  • Standards
  • Supervised Machine Learning
  • Training
  • Warning Systems

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Neuroscience
  • Radio communications and signal processing.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks