Using Wavelet Packet Decomposition Technique on Fuzzy Classify Model for Underwater Acoustic Signal Recognition
A0021Chu-Kuei Tu Department of Information and Computer Engineering, Chung Yuan University
A0022Liang-Ching Lin Department of Information and Computer Engineering, Chung Yuan University
Underwater acoustic signal is affected by reverberation, inhomogeneity
and other various factors causing by the ocean environment, therefore,
it reveal characteristics of non-linear and time-variant. Hence, a
real time fuzzy logic recognition system is developed. The functions
of the proposed system include two subjects, the first subject is
underwater acoustic signal feature extraction by using of wavelet
packet decomposition, the second subject is underwater signal pattern
recognition by using of fuzzy logic model. Finally, combine two parts
and establish a practical, real time underwater Acoustic recognition
During the feature parameter extraction stage, signal characteristic
analysis and feature extraction are studied. The results proved that
using wavelet packet decomposition method for feature extraction can
obtain multi-resolution characteristics, this is the keypoint that the
system can identify the different ships’ signature effectively.
Besides, by using of the self-organization map neural network, the
input feature data are clustering, and the centers of data set are
generate which are the templates of feature parameters. During the
underwater signal pattern recognition stage, signal identification is
performed by using of fuzzy logic theory. Furthermore, by defining
the linguistic variables of the feature and the membership function of
the fuzzy rules, a fuzzy logic algorithm is developed for the purpose
of underwater signal recognition.
A simulation is designed using ships’ signature as input data, the
results have demonstrated the effective performance of proposed system.
Following the analysis of the results, conclusions and recommendations
will be provided. The proposed system can be used to analysis and
recognize an underwater acoustic signal, which may encounter in the
area of ocean Engineering and environment measurement.