This document presents research using artificial neural networks to identify toxic gases in real time. A multi-layer perceptron neural network was trained using data from a multi-sensor system that detected hydrogen sulfide, nitrogen dioxide, and their mixture. Features extracted from the sensor responses were used as inputs to the neural network. The network was trained online using backpropagation and achieved 100% accuracy classifying gases during training and 96.6% accuracy during testing, with low error rates. This model achieved better performance than previous methods and can identify low concentrations of toxic gases in real time, which has applications for air quality monitoring and safety.