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

We propose an on-line gas monitoring system for classifying various gases with different concentrations. Using thermal modulation of the operating temperature of two sensors, we extract patterns of gases from the voltage across the load resistance. We adopt the relative resistance as a preprocessing method, ART2 neural networks as a pattern recognition method, and a simple coordinator as a multi-sensor 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.