Application of artificial neural networks on mosquito Olfactory Receptor Neurons for an olfactory biosensor.

Various odorants such as carbon dioxide (CO2) and 1-octen-3-ol, underlie the host-seeking behaviors of the major malaria vector Anopheles Gambiae. Highlighted by the olfactory processing strength of the mosquito, such a powerful olfactory sense could serve as the sensors of an artificial olfactory biosensor. In this work, we use the firing rates of the A. Gambiae mosquito Olfactory Receptor Neurons (ORNs), to train an Artificial Neural Network (ANN) for the classification of volatile odorants into their known chemical classes and assess their suitability for an olfactory biosensor. With the implementation of bootstrapping, a more representative result was obtained wherein we demonstrate the training of a hybrid ANN consisting of an array of Multi-Layer Perceptrons (MLPs) with optimal number of hidden neurons. The ANN system was able to correctly class 90.1% of the previously unseen odorants, thus demonstrating very strong evidence for the use of A. Gambiae olfactory receptors coupled with an ANN as an olfactory biosensor.