Real-Time Probabilistic Neural Network Performance and Optimization for Fire Detection and Nuisance Alarm Rejection: Test Series 1 Results

Abstract

A series of tests were conducted to evaluate and improve the multivariate data analysis methods and candidate sensor suites used for the Early Warning Fire Detection (EWFD) system under development. The EWFD system is to provide reliable warning of actual fire conditions in less time with fewer nuisance alarms than commercially available smoke detection systems. Tests were conducted from 7-18 February 2000, onboard the ex-USS Sizadwell. This report documents the performance of the probabilistic neural network achieved in real-time during this test series. Further optimization of the algorithm yielded performance gains over the real-time results. Simulation studies have been done to examine the effects of sensor drop-out, excessive noise, and erroneous sensor values.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 31, 2000
Accession Number
ADA382015

Entities

People

  • Daniel T. Gottuk
  • Mark H. Hammond
  • Ronald E. Shaffer
  • Sean J. Hart
  • Susan L. Rose-Pehrsson

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Chemistry
  • Data Acquisition
  • Data Analysis
  • Detection
  • Detectors
  • Dielectric Gases
  • Failure Mode And Effect Analysis
  • False Alarms
  • Neural Networks
  • Optimization
  • Rejection
  • Simulations
  • Smoke Detectors
  • Standards
  • Training
  • Warning Systems

Readers

  • Aerospace Test and Evaluation
  • Fire Suppression Systems Design.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks