Prediction of health of dairy cattle from breath samples using neural network with parametric model of dynamic response of array of semiconducting gas sensors

The authors report on the use of a sampling device to collect the breath from individual members of a herd of dairy cattle juring a two-week period. The response of an array of sis semiconducting oxide gas sensors to the breaths samples has been recorded and subsequently modelled by a time-dependent, linear, second-order system. Four characteristics sensor parameters have been estimated using a neural network;. and these parameters have been used to train a predictive multilayer perceptron network. The results show that either a static response parameter (based on the difference in the signal from zero time) or a single time constant can be used to predict reasonably well the health of the cow as judged against blood samples. In both cases, the identification rate of unknown samples being about 76%. Further improvements may be possible through the use of network compensation of variation?; in sample temperature and humidity.