ABSTRACT
This chapter is concerned with the problem of classifying processes using temporal characteristics. To this end the approach followed employs the temporal information in sequences of hyperspectral images that are obtained as the processes take place. In other words, classification is achieved taking into account the temporal evolution of the process in the discrimination that must be made. To facilitate obtaining the appropriate classifiers, a particular type of artificial neural networks with trainable delays in their synapses as well as a training algorithm that permits adapting these temporal delays to the process are considered. The classification scheme is presented and applied to a real processing problem in the area of curing resins. Several experiments that considered different proportions of resin components as well as varying environmental parameters such as humidity were carried out and are described here.
