Ionic-channel signal processing using artificial neural network

A specifically designed neural network is used to process ionic-channel signals. The model includes three major stages: the normalization, neural network main body and postprocessing stages. In the normalization stage, the real world signal is preprocessed and preconditioned for the use by the neural network. The main body of the model, the neural network, functions as a pattern recognizer, using a multilayered feedforward architecture along with a supervised back-propagation training algorithm. The postprocessing stage includes interpretation of the neural network outputs to establish the best estimates of the locations of step changes in the input signal.<<ETX>>