특징벡터를 이용한 수중소음원의 식별

Abstract

Underwater ambient noise originating from the geophysical, biological, and man-made acoustic sources contains information on the sources and the ocean environment affecting the performance of the sonar equipment. In this thesis, three steps are used to identify the ambient noise source, i.e. detection, feature extraction, and similarity measurement. First, we use zero-crossing rate to detect the ambient noise source from background noise. Then, a set of feature vectors of the ambient noise source using Hilbert-Huang transform, MFCC, and Karhunen-Loeve transform is proposed. Finally, the Euclidean distance is used to measure the similarity between the standard feature vector and the feature vector of unknown ambient noise source. The developed algorithm is applied to the observed ocean data, and the results are presented and discussed.