Flow-injection determination of phenols with tyrosinase amperometric biosensor and data processing by neural network

A multi-membrane amperometric biosensor prepared with immobilized tyrosinas e on a platinum disk electrode in a large-volume wall-jet flow-through cell was applied for the determination of phenolic compounds via flow-injection measurements. For data processing of measurements carried out simultaneous ly with several biosensors of different selectivity using different membran es in three-component mixtures of phenol, catechol and m-cresol, a three la yer artificial neural network with feedforward connections, sigmoidal trans fer function and back propagation learning algorithm was employed. The best functional parameters of the network were found to be 5 inputs, 3 neurons in the hidden layer and 10000 learning cycles. For 36 samples analyzed the best correlation coefficient values were obtained for catechol (0.96) and p henol (0.88). Results for m-cresol, which produced the smallest: amperometr ic signal with all biosensors tested were only semi-quantitative (correlati on coefficient 0.67).