Parametric models for helicopter identification using ANN

An artificial neural network (ANN) based helicopter identification system i s proposed. The feature vectors are based on both the tonal and the broadba nd spectrum of the helicopter signal. ANN pattern classifiers are trained u sing various parametric spectral representation techniques. Specifically, l inear prediction, reflection coefficients, cepstrum, and line spectral freq uencies (LSF) are compared in terms of recognition accuracy and robustness against additive noise. Finally, an 8-helicopter ANN classifier is evaluate d, It is also shown that the classifier performance is dramatically improve d if it is trained using both clean data and data corrupted with additive n oise.