Quantification of Odours from Piggery Effluent Ponds using an Electronic Nose and an Artificial Neural Network

Abstract

An Artificial Neural Network (ANN) and an electronic nose, AromaScan, were used to predict the piggery odour concentrations emanating from an effluent pond and to develop a confident, rapid, and cost-effective technique for odour measurement. Odour samples from five different piggery effluent ponds were analysed using the AromaScan and dynamic dilution olfactometry. The resulting sensor data were used to train the artificial neural network to correlate the responses to the odour concentrations measured by olfactometry. Effectiveness was evaluated through simulation with various pre-processing techniques and network architectures. The simulation results have shown that a two-layer back-propagation neural network, which has a tan-sigmoid transfer function in the hidden layer and a linear transfer function in the output layer, could be trained to predict piggery odour concentrations with high value of the correlation coefficient R of 0·984 under the best network performance. The results from the application of scaling and principal component analysis suggest that these techniques are necessary not only to avoid the failure of the network caused by saturation but also to enhance performance. An early stopping technique was shown to provide benefits to the network performance in terms of a decrease in computation time and overfitting. It was found that the optimal number of hidden neurons for the network was 20. Odour concentration of unknown samples were able to be predicted with significant accuracy.