Probabilistic neural network based olfactory classification for household burning in early fire detection application

S Ragunathan, Allan M. Andrew, Latifah Munirah Kamarudin, David Lorater Ndzi, S.M Mamduh, Ali Yeon Md. Shakaff, Ammar Zakaria, Abdul H. Adom

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review

Abstract

Determination of burning smell is important because it can help in early fire detection and prevention. In this paper, a household burning smell classification system for early fire detection application has been proposed using Probabilistic Neural Network (PNN) and peA analysis. The experiments were performed on recorded smell samples from combustion of ten different commonly available household, including candle,joss sticks, air freshener, mosquito coil, newspaper, card board, plastic materials, Styrofoam and wood. All the experiments were done in a test chamber with humidity and temperature sensors. Portable Electronic Nose (PEN3) from Airsense Analytics is used as the measurement device. The smell source is placed O.3m from the PEN3 and the time-series signal is measured for two minutes. The odour metrics is modelled using Probabilistic Neural Network. It is found that the average classification accuracy for the model is 99.62%.
Original languageEnglish
Title of host publication2013 IEEE Conference on Open Systems (ICOS 2013)
PublisherIEEE
Pages221-225
Number of pages5
ISBN (Print)9781479902866, 978-1-4799-3152-1
DOIs
Publication statusPublished - 2 Dec 2013
EventIEEE Conference on Open Systems - Kuching, Sarawak, Malaysia
Duration: 2 Dec 20134 Dec 2013

Conference

ConferenceIEEE Conference on Open Systems
Abbreviated titleICOS
Country/TerritoryMalaysia
CitySarawak
Period2/12/134/12/13

Keywords

  • olfactory
  • fire detection
  • time series signal
  • classification
  • neural network

Fingerprint

Dive into the research topics of 'Probabilistic neural network based olfactory classification for household burning in early fire detection application'. Together they form a unique fingerprint.

Cite this