Vehicle identification using acoustic and seismic signals

In this study, we have designed a vehicle classification system which classifies Assault Amphibian Vehicle and Dragon Wagon, using acoustic and sesimic features. We implemented Mel Frequency Cepstral Coefficient (MFCC) algorithm to extract features of the acoustic and sesimic data, and these extracted features were reduced by using Vector Quantizaton algorithm. Both Support Vector Machine (SVM) and k-Nearest Neighborhood (k-NN) algorithms were implemented and their classification performances were evaluated.