Skip to main navigation Skip to search Skip to main content

On-line monitoring of indoor environmental gases using ART2 neural networks and multi-sensor fusion

  • Jung Hwan Cho
  • , Chang Hyun Shim
  • , In Soo Lee
  • , Gi Joon Jeon
  • Kyungpook National University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We propose an on-line gas monitoring system for classifying various gases with different concentrations. Using thermal modulation of operating temperature of two sensors, we extract patterns of gases from the voltage across the load resistance. We adopt the relative resistance as a pre-processing method, ART2 neural networks as a pattern recognition method, and a simple coordinator as a multisensor fusion method to provide more reliable and accurate information. The proposed method has been implemented in a real time embedded system with tin oxide gas sensors, TGS 2611, 2602, and an MSP430 ultra-low power microcontroller in the test chamber

Original languageEnglish
Title of host publicationProceedings of the 2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, ISSNIP '04
EditorsM. Palaniswami, B. Krishnamachari, A. Sowmya, S. Challa, M. Palaniswami, B. Krishnamachari, A. Sowmya, S. Challa
Pages125-129
Number of pages5
StatePublished - 2004
Event2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, ISSNIP '04 - Melbourne, Australia
Duration: 14 Dec 200417 Dec 2004

Publication series

NameProceedings of the 2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, ISSNIP '04

Conference

Conference2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, ISSNIP '04
Country/TerritoryAustralia
CityMelbourne
Period14/12/0417/12/04

Fingerprint

Dive into the research topics of 'On-line monitoring of indoor environmental gases using ART2 neural networks and multi-sensor fusion'. Together they form a unique fingerprint.

Cite this