An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN

Fiber distributed acoustic sensing (FDAS) systems have been widely used in many fields such as oil and gas pipeline monitoring, urban safety monitoring, and perimeter security. An event recognition method for fiber distributed acoustic sensing (FDAS) systems is proposed in this paper. The Mel-frequency cepstrum coefficients (MFCC) of the acoustic signals collected by the FDAS system are computed as the features of the events, which are inputted into a convolutional neural network (CNN) to determine the type of the events. Experimental results based on 2300 training samples and 946 test samples show that the precision, recall, and f1-score of the classification model reach as high as 98.02%, 97.99%, and 97.98% respectively, which means that the combination of MFCC and CNN may be a promising event recognition method for FDAS systems.